AI Driven Spreadsheet

AI Driven Spreadsheet — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Macromedia FreeHand

  Macromedia FreeHand (formerly Aldus FreeHand) is a discontinued computer application for creating two-dimensional vector graphics oriented primarily to professional illustration, desktop publishing and content creation for the Web. FreeHand was similar in scope, intended market, and functionality to Adobe Illustrator, CorelDRAW and Xara Designer Pro. Because of FreeHand's dedicated page layout and text control features, it also compares to Adobe InDesign and QuarkXPress. Professions using FreeHand include graphic design, illustration, cartography, fashion and textile design, product design, architects, scientific research, and multimedia production. FreeHand was created by Altsys Corporation in 1988 and licensed to Aldus Corporation, which released versions 1 through 4. In 1994, Aldus merged with Adobe Systems and because of the overlapping market with Adobe Illustrator, FreeHand was returned to Altsys by order of the Federal Trade Commission. Altsys was later bought by Macromedia, which released FreeHand versions 5 through 11 (FreeHand MX). In 2005, Adobe Systems acquired Macromedia and its product line which included FreeHand MX, under whose ownership it presently resides. Since 2003, FreeHand development has been discontinued; in the Adobe Systems catalog, FreeHand has been replaced by Adobe Illustrator. FreeHand MX continues to run under Windows 11 and under Mac OS X 10.6 (Snow Leopard) within Rosetta, a PowerPC code emulator, and requires a registration patch supplied by Adobe. FreeHand 10 runs without problems on Mac OS X Snow Leopard with Rosetta enabled, and does not require a registration patch. Later versions of macOS can use a Mac OS X Snow Leopard Server virtual machine to emulate the required PowerPC support. == History == === Altsys and Aldus FreeHand === In 1984, James R. Von Ehr founded Altsys Corporation to develop graphics applications for personal computers. Based in Plano, Texas, the company initially produced font editing and conversion software; Fontastic Plus, Metamorphosis, and the Art Importer. Their premier PostScript font-design package, Fontographer, was released in 1986 and was the first such program on the market. With the PostScript background having been established by Fontographer, Altsys also developed FreeHand (originally called Masterpiece) as a Macintosh Postscript-based illustration program that used Bézier curves for drawing and was similar to Adobe Illustrator. FreeHand was announced as "... a Macintosh graphics program described as having all the features of Adobe's Illustrator plus drawing tools such as those in Mac Paint and Mac Draft and special effects similar to those in Cricket Draw." Seattle's Aldus Corporation acquired a licensing agreement with Altsys Corporation to release FreeHand along with their flagship product, Pagemaker, and Aldus FreeHand 1.0 was released in 1988. FreeHand's product name used intercaps; the F and H were capitalized. The partnership between the two companies continued with Altsys developing FreeHand and with Aldus controlling marketing and sales. After 1988, a competitive exchange between Aldus FreeHand and Adobe Illustrator ensued on the Macintosh platform with each software advancing new tools, achieving better speed, and matching significant features. Windows PC development also allowed Illustrator 2 (aka, Illustrator 88 on the Mac) and FreeHand 3 to release Windows versions to the graphics market. FreeHand 1.0 sold for $495 in 1988. It included the standard drawing tools and features as other draw programs including special effects in fills and screens, text manipulation tools, and full support for CMYK color printing. It was also possible to create and insert PostScript routines anywhere within the program. FreeHand performed in preview mode instead of keyline mode but performance was slower. FreeHand 2.0 sold for $495 in 1989. Besides improving on the features of FreeHand 1.0, FreeHand 2 added faster operation, Pantone colors, stroked text, flexible fill patterns and automatically import graphic assets from other programs. It added accurate control over a color monitor screen display, limited only by its resolution. FreeHand 3.0 sold for $595 in 1991. New features included resizable color, style, and layer panels including an Attributes menu. Also tighter precision of both the existing tools and aligning of objects. FH3 created compound Paths. Text could be converted to paths, applied to an ellipse, or made vertical. Carried over from version 1.0, FreeHand 3 suffered by having text entered into a dialog box instead of directly to the page. In October 1991, a 3.1 upgrade made FreeHand work with System 7 but additionally, it supported pressure-sensitive drawing which offered varying line widths with a users stroke. It improved element manipulation and added more import/export options. FreeHand 4.0 sold for $595 in 1994. Altsys ported FreeHand 3.0 to the NeXT system creating a new program named Virtuoso. Virtuoso continued its development at Altsys and version 2.0 of Virtuoso was feature-equivalent to FreeHand 4 (with the addition of NeXT-specific features such as Services and Display PostScript) and file compatible, with Virtuoso 2 able to open FreeHand 4 files and vice versa. A prominent feature of this version was the ability to type directly into the page and wrap inside or outside any shape. It also included drag-and-drop color imaging, a larger pasteboard, and a user interface that featured floating, rollup panels. The colors palette included a color mixer for adding new colors to the swatch list. Speed increases were made. In the same year of FreeHand 4 release, Adobe Systems announced merger plans with Aldus Corporation for $525 million. Fear about the end of competition between these two leading applications was reported in the media and expressed by customers (Illustrator versus FreeHand and Adobe Photoshop versus Aldus PhotoStyler.) Because of this overlapping of the market, Altsys stepped in by suing Aldus, saying that the merger deal was "a prima facie violation of a non-compete clause within the FreeHand licensing agreement." Altsys CEO Jim Von Ehr explained, "No one loves FreeHand more than we do. We will do whatever it takes to see it survive." The Federal Trade Commission issued a complaint against Adobe Systems on October 18, 1994, ordering a divestiture of FreeHand to "remedy the lessening of competition resulting from the acquisition as alleged in the Commission's complaint," and further, the FTC ordering, "That for a period of ten (10) years from the date on which this order becomes final, respondents shall not, without the prior approval of the Commission, directly or indirectly, through subsidiaries, partnerships, or otherwise .. Acquire any Professional Illustration Software or acquire or enter into any exclusive license to Professional Illustration Software;" (referring to FreeHand.) FreeHand was returned to Altsys with all licensing and marketing rights as well as Aldus FreeHand's customer list. === Macromedia Freehand === By late 1994, Altsys still retained all rights to FreeHand. Despite brief plans to keep it in-house to sell it along with Fontographer and Virtuoso, Altsys reached an agreement with the multimedia software company, Macromedia, to be acquired. This mutual agreement provided FreeHand and Fontographer a new home with ample resources for marketing, sales, and competition against the newly merged Adobe-Aldus company. Altsys would remain in Richardson, Texas, but would be renamed as the Digital Arts Group of Macromedia and was responsible for the continued development of FreeHand. Macromedia received FreeHand's 200,000 customers and expanded its traditional product line of multimedia graphics software to illustration and design graphics software. CEO James Von Ehr became a Macromedia vice-president until 1997 when he left to start another venture. FreeHand 5.0 sold for $595 in 1995. This version featured a more customizable and expanded workspace, multiple views, stronger design and editing tools, a report generator, spell check, paragraph styles, multicolor gradient fills up to 64 colors, speed improvements, and it accepted Illustrator plugins. In September 1995, a 5.5 upgrade added Photoshop plug-in support, PDF import capabilities, the Extract feature, inline graphics to text, improved auto-expanding text containers, the Crop feature, and the Create PICT Image feature. A FreeHand 5.5 upgrade was part of the FreeHand Graphics Studio (a suite that included Fontographer, Macromedia xRes image editing application, and Extreme 3D animation and modeling application). FreeHand 6.0 in 1996. This version only existed in beta. Some Freehand 7 prerelease versions were released under the Freehand 6 tag. FreeHand 7.0 sold for $399 in 1996, or $449 as part of the FreeHand Graphics Studio (see above.) Features included a redesigned user interface that allowed recombining Inspectors, Panel Tabs, Dockable Panels, Smart Cursors,

  Read more →
• 

  Robust principal component analysis

  Robust Principal Component Analysis (RPCA) is a modification of the widely used statistical procedure of principal component analysis (PCA) which works well with respect to grossly corrupted observations. A number of different approaches exist for Robust PCA, including an idealized version of Robust PCA, which aims to recover a low-rank matrix L0 from highly corrupted measurements M = L0 +S0. This decomposition in low-rank and sparse matrices can be achieved by techniques such as Principal Component Pursuit method (PCP), Stable PCP, Quantized PCP, Block based PCP, and Local PCP. Then, optimization methods are used such as the Augmented Lagrange Multiplier Method (ALM), Alternating Direction Method (ADM), Fast Alternating Minimization (FAM), Iteratively Reweighted Least Squares (IRLS ) or alternating projections (AP). == Algorithms == === Non-convex method === The 2014 guaranteed algorithm for the robust PCA problem (with the input matrix being M = L + S {\displaystyle M=L+S} ) is an alternating minimization type algorithm. The computational complexity is O ( m n r 2 log ⁡ 1 ϵ ) {\displaystyle O\left(mnr^{2}\log {\frac {1}{\epsilon }}\right)} where the input is the superposition of a low-rank (of rank r {\displaystyle r} ) and a sparse matrix of dimension m × n {\displaystyle m\times n} and ϵ {\displaystyle \epsilon } is the desired accuracy of the recovered solution, i.e., ‖ L ^ − L ‖ F ≤ ϵ {\displaystyle \|{\widehat {L}}-L\|_{F}\leq \epsilon } where L {\displaystyle L} is the true low-rank component and L ^ {\displaystyle {\widehat {L}}} is the estimated or recovered low-rank component. Intuitively, this algorithm performs projections of the residual onto the set of low-rank matrices (via the SVD operation) and sparse matrices (via entry-wise hard thresholding) in an alternating manner - that is, low-rank projection of the difference the input matrix and the sparse matrix obtained at a given iteration followed by sparse projection of the difference of the input matrix and the low-rank matrix obtained in the previous step, and iterating the two steps until convergence. This alternating projections algorithm is later improved by an accelerated version, coined AccAltProj. The acceleration is achieved by applying a tangent space projection before projecting the residue onto the set of low-rank matrices. This trick improves the computational complexity to O ( m n r log ⁡ 1 ϵ ) {\displaystyle O\left(mnr\log {\frac {1}{\epsilon }}\right)} with a much smaller constant in front while it maintains the theoretically guaranteed linear convergence. Another fast version of accelerated alternating projections algorithm is IRCUR. It uses the structure of CUR decomposition in alternating projections framework to dramatically reduces the computational complexity of RPCA to O ( max { m , n } r 2 log ⁡ ( m ) log ⁡ ( n ) log ⁡ 1 ϵ ) {\displaystyle O\left(\max\{m,n\}r^{2}\log(m)\log(n)\log {\frac {1}{\epsilon }}\right)} === Convex relaxation === This method consists of relaxing the rank constraint r a n k ( L ) {\displaystyle rank(L)} in the optimization problem to the nuclear norm ‖ L ‖ ∗ {\displaystyle \|L\|_{}} and the sparsity constraint ‖ S ‖ 0 {\displaystyle \|S\|_{0}} to ℓ 1 {\displaystyle \ell _{1}} -norm ‖ S ‖ 1 {\displaystyle \|S\|_{1}} . The resulting program can be solved using methods such as the method of Augmented Lagrange Multipliers. === Deep-learning augmented method === Some recent works propose RPCA algorithms with learnable/training parameters. Such a learnable/trainable algorithm can be unfolded as a deep neural network whose parameters can be learned via machine learning techniques from a given dataset or problem distribution. The learned algorithm will have superior performance on the corresponding problem distribution. == Applications == RPCA has many real life important applications particularly when the data under study can naturally be modeled as a low-rank plus a sparse contribution. Following examples are inspired by contemporary challenges in computer science, and depending on the applications, either the low-rank component or the sparse component could be the object of interest: === Video surveillance === Given a sequence of surveillance video frames, it is often required to identify the activities that stand out from the background. If we stack the video frames as columns of a matrix M, then the low-rank component L0 naturally corresponds to the stationary background and the sparse component S0 captures the moving objects in the foreground. === Face recognition === Images of a convex, Lambertian surface under varying illuminations span a low-dimensional subspace. This is one of the reasons for effectiveness of low-dimensional models for imagery data. In particular, it is easy to approximate images of a human's face by a low-dimensional subspace. To be able to correctly retrieve this subspace is crucial in many applications such as face recognition and alignment. It turns out that RPCA can be applied successfully to this problem to exactly recover the face.

  Read more →
• 

  Concept class

  In computational learning theory in mathematics, a concept over a domain X is a total Boolean function over X. A concept class is a class of concepts. Concept classes are a subject of computational learning theory. Concept class terminology frequently appears in model theory associated with probably approximately correct (PAC) learning. In this setting, if one takes a set Y as a set of (classifier output) labels, and X is a set of examples, the map c : X → Y {\displaystyle c:X\to Y} , i.e. from examples to classifier labels (where Y = { 0 , 1 } {\displaystyle Y=\{0,1\}} and where c is a subset of X), c is then said to be a concept. A concept class C {\displaystyle C} is then a collection of such concepts. Given a class of concepts C, a subclass D is reachable if there exists a sample s such that D contains exactly those concepts in C that are extensions to s. Not every subclass is reachable. == Background == A sample s {\displaystyle s} is a partial function from X {\displaystyle X} to { 0 , 1 } {\displaystyle \{0,1\}} . Identifying a concept with its characteristic function mapping X {\displaystyle X} to { 0 , 1 } {\displaystyle \{0,1\}} , it is a special case of a sample. Two samples are consistent if they agree on the intersection of their domains. A sample s ′ {\displaystyle s'} extends another sample s {\displaystyle s} if the two are consistent and the domain of s {\displaystyle s} is contained in the domain of s ′ {\displaystyle s'} . == Examples == Suppose that C = S + ( X ) {\displaystyle C=S^{+}(X)} . Then: the subclass { { x } } {\displaystyle \{\{x\}\}} is reachable with the sample s = { ( x , 1 ) } {\displaystyle s=\{(x,1)\}} ; the subclass S + ( Y ) {\displaystyle S^{+}(Y)} for Y ⊆ X {\displaystyle Y\subseteq X} are reachable with a sample that maps the elements of X − Y {\displaystyle X-Y} to zero; the subclass S ( X ) {\displaystyle S(X)} , which consists of the singleton sets, is not reachable. == Applications == Let C {\displaystyle C} be some concept class. For any concept c ∈ C {\displaystyle c\in C} , we call this concept 1 / d {\displaystyle 1/d} -good for a positive integer d {\displaystyle d} if, for all x ∈ X {\displaystyle x\in X} , at least 1 / d {\displaystyle 1/d} of the concepts in C {\displaystyle C} agree with c {\displaystyle c} on the classification of x {\displaystyle x} . The fingerprint dimension F D ( C ) {\displaystyle FD(C)} of the entire concept class C {\displaystyle C} is the least positive integer d {\displaystyle d} such that every reachable subclass C ′ ⊆ C {\displaystyle C'\subseteq C} contains a concept that is 1 / d {\displaystyle 1/d} -good for it. This quantity can be used to bound the minimum number of equivalence queries needed to learn a class of concepts according to the following inequality: F D ( C ) − 1 ≤ # E Q ( C ) ≤ ⌈ F D ( C ) ln ⁡ ( | C | ) ⌉ {\textstyle FD(C)-1\leq \#EQ(C)\leq \lceil FD(C)\ln(|C|)\rceil } .

  Read more →
• 

  Relation network

  A relation network (RN) is an artificial neural network component with a structure that can reason about relations among objects. An example category of such relations is spatial relations (above, below, left, right, in front of, behind). RNs can infer relations, they are data efficient, and they operate on a set of objects without regard to the objects' order. == History == In June 2017, DeepMind announced the first relation network. It claimed that the technology had achieved "superhuman" performance on multiple question-answering problem sets. == Design == RNs constrain the functional form of a neural network to capture the common properties of relational reasoning. These properties are explicitly added to the system, rather than established by learning just as the capacity to reason about spatial, translation-invariant properties is explicitly part of convolutional neural networks (CNN). The data to be considered can be presented as a simple list or as a directed graph whose nodes are objects and whose edges are the pairs of objects whose relationships are to be considered. The RN is a composite function: R N ( O ) = f ϕ ( ∑ i , j g θ ( o i , o j , q ) ) , {\displaystyle RN\left(O\right)=f_{\phi }\left(\sum _{i,j}g_{\theta }\left(o_{i},o_{j},q\right)\right),} where the input is a set of "objects" O = { o 1 , o 2 , . . . , o n } , o i ∈ R m {\displaystyle O=\left\lbrace o_{1},o_{2},...,o_{n}\right\rbrace ,o_{i}\in \mathbb {R} ^{m}} is the ith object, and fφ and gθ are functions with parameters φ and θ, respectively and q is the question. fφ and gθ are multilayer perceptrons, while the 2 parameters are learnable synaptic weights. RNs are differentiable. The output of gθ is a "relation"; therefore, the role of gθ is to infer any ways in which two objects are related. Image (128x128 pixel) processing is done with a 4-layer CNN. Outputs from the CNN are treated as the objects for relation analysis, without regard for what those "objects" explicitly represent. Questions were processed with a long short-term memory network.

  Read more →
• 

  Biomedical data science

  Biomedical data science is a multidisciplinary field which leverages large volumes of data to promote biomedical innovation and discovery. Biomedical data science draws from various fields including Biostatistics, Biomedical informatics, and machine learning, with the goal of understanding biological and medical data. It can be viewed as the study and application of data science to solve biomedical problems. Modern biomedical datasets often have specific features which make their analyses difficult, including: Large numbers of feature (sometimes billions), typically far larger than the number of samples (typically tens or hundreds) Noisy and missing data Privacy concerns (e.g., electronic health record confidentiality) Requirement of interpretability from decision makers and regulatory bodies Many biomedical data science projects apply machine learning to such datasets. These characteristics, while also present in many data science applications more generally, make biomedical data science a specific field. Examples of biomedical data science research include: Computational genomics Computational imaging Electronic health records data mining Biomedical network science Clinical Natural Language Processing (NLP) == Computational Imaging and Deep Learning == Computational imaging is a cornerstone of biomedical data science, focusing on the development of algorithms to enhance, analyze, and interpret medical imagery. In recent years, the field has been transformed by the integration of deep learning, particularly through the use of Convolutional Neural Networks. Deep learning started from researchers manually defining characteristics like edge detection or texture representation learning. In a more modern approach of computational imaging, models automatically learn a hierarchy of features directly from raw pixel data. This overlap between data science and deep learning is applied across several key tasks: Classification: Identifying the presence of specific diseases, such as distinguishing between benign and malignant tumors in histopathology slides or detecting pneumonia in chest X-rays. Segmentation: The precise delineation of anatomical structures or lesions. A notable example is the U-Net architecture, which is widely used for biomedical image segmentation to help clinicians quantify organ volume or track tumor growth. Detection: Automating the localization of small objects, such as identifying microcalcifications in mammograms or polyps during colonoscopies. Registration: The process of aligning multiple images to provide a comprehensive view of the patient's anatomy. Even with all of these enhancements, the application of deep learning in medical imaging requires accomplishing vigorous challenges. An example of these changes is building large, annotated datasets and creating the imperative for model interpretability in clinical decision-making. == Electronic Health Records == Electronic Health Records (EHRs) are a digital alternative to patient paper charts, usually including individual records or population health information. EHRs can be used in a wide variety of applications, including research and analysation as they often include demographics, diagnoses, medications, test results, and personal statistics. === History === ==== 1960s ==== The earliest precursor is considered Dr. Lawrence Weed's problem-oriented medical record (POMR) published in the 1968 which sorts and groups medical records by medical diagnoses and symptoms. The POMR was the first system to organize based off of patient information rather than the source (doctors, nurses, attendings, etc.). In 1969, the Regenstrief Institute developed and published the Regenstrief Medical Record System which established electronic writing, storage, and retrieval of records which served as the basis for modern EHR systems. ==== 2000s ==== In 2009, the Health Information Technology for Economic and Clinical Health Act (HITECH Act) was passed in the United States. This act standardized privacy and distribution of EHRs and increased the acceptance and utilization of EHRs within medical and academic settings. == Artificial Intelligence and Machine Learning Applications == Machine Learning and Artificial Intelligence have become central tools in biomedical data science. Recent advances in large language models (LLMs) have expanded their role beyond text, with models trained directly on genomic sequences enabling tasks such as gene function prediction, variant effect analysis, and drug discovery. In clinical settings, Natural Language Processing (NLP) models are applied to electronic health records to extract structured insights from unstructured clinical notes and data, supporting diagnosis and treatment planning. Beyond genomics, AI models have been applied to protein structure prediction. AlphaFold, developed by Google DeepMind, uses deep learning to predict three-dimensional protein structures from amino acid sequences with high accuracy. These predictions have been used to support drug target identification and the study of disease mechanisms. == Knowledge Graphs == Knowledge graphs (KGs) are widely used in biomedical data science to represent and analyze complex relationships among biological and medical entities. By structuring data as nodes (e.g., genes, diseases, drugs) and edges (relationships), KGs enable computational methods to extract insights and support decision-making. These biomedical relationships can be efficiently modeled and queried using technologies such as Neo4j. === Biomedical Research Applications === KGs provide biomedical researchers with a way to model complex biological systems. They have been used to identify the relationships between diseases and biomolecules, support drug repurposing, and to uncover new biological insights. Additional applications include: Identification of novel antibiotic resistance genes through graph-based link prediction. Finding associations between miRNA and diseases. Prediction of protein-protein interactions. === Clinical Applications === In clinical settings, KGs can be used to make visual representations of a patient's electronic health records. The data obtained from these graphs can assist healthcare providers in improving patient diagnoses and prescribing more effective drugs. Additionally, embeddings derived from resources like the Unified Medical Language System (UMLS) enable natural language processing of clinical text and similarity analysis between medical concepts. === Limitations === Despite their advantages, knowledge graphs face several challenges. Some of these include: High algorithmic complexity and large biological datasets make the process computationally expensive. KG construction can be a time-consuming process that requires careful attention to assign appropriate node types and vocabularies. Using data from a wide range of datasets in one KG requires them to be effectively integrated. == Privacy == A primary challenge in biomedical data science is maintaining medical privacy. Conducting research requires that data be collected on a number of people for training and testing purposes and is stored within biomedical datasets. This poses a risk for violating patient confidentiality and may dissuade people from participating in studies. The main sources of health statistics are surveys administrative and medical records health care claims data, vital records surveillance disease registries grey literature and peer-reviewed literature. Large data collection is a useful tool for researching various medical conditions. Researchers use these large datasets of information to identify factors that may make people more susceptible to certain diseases. Large amounts of collected data can help researchers identify patterns for disease probabilities. The findings can show a person is more likely for a condition, or identify environmental, social, and personal habits that may lead to adverse health issues. Institutions researching using personal medical information come with a moral and legal responsibility to protect the use of that information. Protection of the collected information has become a big concern. Sophisticated and coordinated attacks on certain medical systems happen more frequently. Medical companies, medical insurance and private businesses have invested a great deal into the protection of personal data. Despite this, data breaches continue to be documented. The chart below shows the top healthcare breaches in 2025. For these reasons, many people have reservations about giving up their personal data. Aside from the legitimate use of personal data there have been instances where companies have found methods to profit from brokering medical information. Concerns exist regarding unauthorized use of sensitive information within these data companies. If a person is identified within a dataset, then sensitive data can be used to discriminate against them. For example, insurance companies may charge a hi

  Read more →
• 

  Genetic representation

  In computer programming, genetic representation is a way of presenting solutions/individuals in evolutionary computation methods. The term encompasses both the concrete data structures and data types used to realize the genetic material of the candidate solutions in the form of a genome, and the relationships between search space and problem space. In the simplest case, the search space corresponds to the problem space (direct representation). The choice of problem representation is tied to the choice of genetic operators, both of which have a decisive effect on the efficiency of the optimization. Genetic representation can encode appearance, behavior, physical qualities of individuals. Difference in genetic representations is one of the major criteria drawing a line between known classes of evolutionary computation. Terminology is often analogous with natural genetics. The block of computer memory that represents one candidate solution is called an individual. The data in that block is called a chromosome. Each chromosome consists of genes. The possible values of a particular gene are called alleles. A programmer may represent all the individuals of a population using binary encoding, permutational encoding, encoding by tree, or any one of several other representations. == Representations in some popular evolutionary algorithms == Genetic algorithms (GAs) are typically linear representations; these are often, but not always, binary. Holland's original description of GA used arrays of bits. Arrays of other types and structures can be used in essentially the same way. The main property that makes these genetic representations convenient is that their parts are easily aligned due to their fixed size. This facilitates simple crossover operation. Depending on the application, variable-length representations have also been successfully used and tested in evolutionary algorithms (EA) in general and genetic algorithms in particular, although the implementation of crossover is more complex in this case. Evolution strategy uses linear real-valued representations, e.g., an array of real values. It uses mostly gaussian mutation and blending/averaging crossover. Genetic programming (GP) pioneered tree-like representations and developed genetic operators suitable for such representations. Tree-like representations are used in GP to represent and evolve functional programs with desired properties. Human-based genetic algorithm (HBGA) offers a way to avoid solving hard representation problems by outsourcing all genetic operators to outside agents, in this case, humans. The algorithm has no need for knowledge of a particular fixed genetic representation as long as there are enough external agents capable of handling those representations, allowing for free-form and evolving genetic representations. === Common genetic representations === binary array integer or real-valued array binary tree natural language parse tree directed graph == Distinction between search space and problem space == Analogous to biology, EAs distinguish between problem space (corresponds to phenotype) and search space (corresponds to genotype). The problem space contains concrete solutions to the problem being addressed, while the search space contains the encoded solutions. The mapping from search space to problem space is called genotype-phenotype mapping. The genetic operators are applied to elements of the search space, and for evaluation, elements of the search space are mapped to elements of the problem space via genotype-phenotype mapping. == Relationships between search space and problem space == The importance of an appropriate choice of search space for the success of an EA application was recognized early on. The following requirements can be placed on a suitable search space and thus on a suitable genotype-phenotype mapping: === Completeness === All possible admissible solutions must be contained in the search space. === Redundancy === When more possible genotypes exist than phenotypes, the genetic representation of the EA is called redundant. In nature, this is termed a degenerate genetic code. In the case of a redundant representation, neutral mutations are possible. These are mutations that change the genotype but do not affect the phenotype. Thus, depending on the use of the genetic operators, there may be phenotypically unchanged offspring, which can lead to unnecessary fitness determinations, among other things. Since the evaluation in real-world applications usually accounts for the lion's share of the computation time, it can slow down the optimization process. In addition, this can cause the population to have higher genotypic diversity than phenotypic diversity, which can also hinder evolutionary progress. In biology, the Neutral Theory of Molecular Evolution states that this effect plays a dominant role in natural evolution. This has motivated researchers in the EA community to examine whether neutral mutations can improve EA functioning by giving populations that have converged to a local optimum a way to escape that local optimum through genetic drift. This is discussed controversially and there are no conclusive results on neutrality in EAs. On the other hand, there are other proven measures to handle premature convergence. === Locality === The locality of a genetic representation corresponds to the degree to which distances in the search space are preserved in the problem space after genotype-phenotype mapping. That is, a representation has a high locality exactly when neighbors in the search space are also neighbors in the problem space. In order for successful schemata not to be destroyed by genotype-phenotype mapping after a minor mutation, the locality of a representation must be high. === Scaling === In genotype-phenotype mapping, the elements of the genotype can be scaled (weighted) differently. The simplest case is uniform scaling: all elements of the genotype are equally weighted in the phenotype. A common scaling is exponential. If integers are binary coded, the individual digits of the resulting binary number have exponentially different weights in representing the phenotype. Example: The number 90 is written in binary (i.e., in base two) as 1011010. If now one of the front digits is changed in the binary notation, this has a significantly greater effect on the coded number than any changes at the rear digits (the selection pressure has an exponentially greater effect on the front digits). For this reason, exponential scaling has the effect of randomly fixing the "posterior" locations in the genotype before the population gets close enough to the optimum to adjust for these subtleties. == Hybridization and repair in genotype-phenotype mapping == When mapping the genotype to the phenotype being evaluated, domain-specific knowledge can be used to improve the phenotype and/or ensure that constraints are met. This is a commonly used method to improve EA performance in terms of runtime and solution quality. It is illustrated below by two of the three examples. == Examples == === Example of a direct representation === An obvious and commonly used encoding for the traveling salesman problem and related tasks is to number the cities to be visited consecutively and store them as integers in the chromosome. The genetic operators must be suitably adapted so that they only change the order of the cities (genes) and do not cause deletions or duplications. Thus, the gene order corresponds to the city order and there is a simple one-to-one mapping. === Example of a complex genotype-phenotype mapping === In a scheduling task with heterogeneous and partially alternative resources to be assigned to a set of subtasks, the genome must contain all necessary information for the individual scheduling operations or it must be possible to derive them from it. In addition to the order of the subtasks to be executed, this includes information about the resource selection. A phenotype then consists of a list of subtasks with their start times and assigned resources. In order to be able to create this, as many allocation matrices must be created as resources can be allocated to one subtask at most. In the simplest case this is one resource, e.g., one machine, which can perform the subtask. An allocation matrix is a two-dimensional matrix, with one dimension being the available time units and the other being the resources to be allocated. Empty matrix cells indicate availability, while an entry indicates the number of the assigned subtask. The creation of allocation matrices ensures firstly that there are no inadmissible multiple allocations. Secondly, the start times of the subtasks can be read from it as well as the assigned resources. A common constraint when scheduling resources to subtasks is that a resource can only be allocated once per time unit and that the reservation must be for a contiguous period of time. To achieve this in a timely manner, which is a c

  Read more →
• 

  Sum of absolute transformed differences

  The sum of absolute transformed differences (SATD) is a block matching criterion widely used in fractional motion estimation for video compression. It works by taking a frequency transform, usually a Hadamard transform, of the differences between the pixels in the original block and the corresponding pixels in the block being used for comparison. The transform itself is often of a small block rather than the entire macroblock. For example, in x264, a series of 4×4 blocks are transformed rather than doing the more processor-intensive 16×16 transform. == Comparison to other metrics == SATD is slower than the sum of absolute differences (SAD), both due to its increased complexity and the fact that SAD-specific MMX and SSE2 instructions exist, while there are no such instructions for SATD. However, SATD can still be optimized considerably with SIMD instructions on most modern CPUs. The benefit of SATD is that it more accurately models the number of bits required to transmit the residual error signal. As such, it is often used in video compressors, either as a way to drive and estimate rate explicitly, such as in the Theora encoder (since 1.1 alpha2), as an optional metric used in wide motion searches, such as in the Microsoft VC-1 encoder, or as a metric used in sub-pixel refinement, such as in x264.

  Read more →
• 

  Evolutionary algorithm

  Evolutionary algorithms (EA) reproduce essential elements of biological evolution in a computer algorithm in order to solve "difficult" problems, at least approximately, for which no exact or satisfactory solution methods are known. They are metaheuristics and population-based bio-inspired algorithms and evolutionary computation, which itself are part of the field of computational intelligence. The mechanisms of biological evolution that an EA mainly imitates are reproduction, mutation, recombination and selection. Candidate solutions to the optimization problem play the role of individuals in a population, and the fitness function determines the quality of the solutions (see also loss function). Evolution of the population then takes place after the repeated application of the above operators. Evolutionary algorithms often perform well approximating solutions to all types of problems because they ideally do not make any assumption about the underlying fitness landscape. Techniques from evolutionary algorithms applied to the modeling of biological evolution are generally limited to explorations of microevolution (microevolutionary processes) and planning models based upon cellular processes. In most real applications of EAs, computational complexity is a prohibiting factor. In fact, this computational complexity is due to fitness function evaluation. Fitness approximation is one of the solutions to overcome this difficulty. However, seemingly simple EA can solve often complex problems; therefore, there may be no direct link between algorithm complexity and problem complexity. == Generic definition == The following is an example of a generic evolutionary algorithm: Randomly generate the initial population of individuals, the first generation. Evaluate the fitness of each individual in the population. Check, if the goal is reached and the algorithm can be terminated. Select individuals as parents, preferably of higher fitness. Produce offspring with optional crossover (mimicking reproduction). Apply mutation operations on the offspring. Select individuals preferably of lower fitness for replacement with new individuals (mimicking natural selection). Return to 2 == Types == Similar techniques differ in genetic representation and other implementation details, and the nature of the particular applied problem. Genetic algorithm – This is the most popular type of EA. One seeks the solution of a problem in the form of strings of numbers (traditionally binary, although the best representations are usually those that reflect something about the problem being solved), by applying operators such as recombination and mutation (sometimes one, sometimes both). This type of EA is often used in optimization problems. Genetic programming – Here the solutions are in the form of computer programs, and their fitness is determined by their ability to solve a computational problem. There are many variants of Genetic Programming: Cartesian genetic programming Gene expression programming Grammatical evolution Linear genetic programming Multi expression programming Evolutionary programming – Similar to evolution strategy, but with a deterministic selection of all parents. Evolution strategy (ES) – Works with vectors of real numbers as representations of solutions, and typically uses self-adaptive mutation rates. The method is mainly used for numerical optimization, although there are also variants for combinatorial tasks. CMA-ES Natural evolution strategy Differential evolution – Based on vector differences and is therefore primarily suited for numerical optimization problems. Coevolutionary algorithm – Similar to genetic algorithms and evolution strategies, but the created solutions are compared on the basis of their outcomes from interactions with other solutions. Solutions can either compete or cooperate during the search process. Coevolutionary algorithms are often used in scenarios where the fitness landscape is dynamic, complex, or involves competitive interactions. Neuroevolution – Similar to genetic programming but the genomes represent artificial neural networks by describing structure and connection weights. The genome encoding can be direct or indirect. Learning classifier system – Here the solution is a set of classifiers (rules or conditions). A Michigan-LCS evolves at the level of individual classifiers whereas a Pittsburgh-LCS uses populations of classifier-sets. Initially, classifiers were only binary, but now include real, neural net, or S-expression types. Fitness is typically determined with either a strength or accuracy based reinforcement learning or supervised learning approach. Quality–Diversity algorithms – QD algorithms simultaneously aim for high-quality and diverse solutions. Unlike traditional optimization algorithms that solely focus on finding the best solution to a problem, QD algorithms explore a wide variety of solutions across a problem space and keep those that are not just high performing, but also diverse and unique. == Theoretical background == The following theoretical principles apply to all or almost all EAs. === No free lunch theorem === The no free lunch theorem of optimization states that all optimization strategies are equally effective when the set of all optimization problems is considered. Under the same condition, no evolutionary algorithm is fundamentally better than another. This can only be the case if the set of all problems is restricted. This is exactly what is inevitably done in practice. Therefore, to improve an EA, it must exploit problem knowledge in some form (e.g. by choosing a certain mutation strength or a problem-adapted coding). Thus, if two EAs are compared, this constraint is implied. In addition, an EA can use problem specific knowledge by, for example, not randomly generating the entire start population, but creating some individuals through heuristics or other procedures. Another possibility to tailor an EA to a given problem domain is to involve suitable heuristics, local search procedures or other problem-related procedures in the process of generating the offspring. This form of extension of an EA is also known as a memetic algorithm. Both extensions play a major role in practical applications, as they can speed up the search process and make it more robust. === Convergence === For EAs in which, in addition to the offspring, at least the best individual of the parent generation is used to form the subsequent generation (so-called elitist EAs), there is a general proof of convergence under the condition that an optimum exists. Without loss of generality, a maximum search is assumed for the proof: From the property of elitist offspring acceptance and the existence of the optimum it follows that per generation k {\displaystyle k} an improvement of the fitness F {\displaystyle F} of the respective best individual x ′ {\displaystyle x'} will occur with a probability P > 0 {\displaystyle P>0} . Thus: F ( x 1 ′ ) ≤ F ( x 2 ′ ) ≤ F ( x 3 ′ ) ≤ ⋯ ≤ F ( x k ′ ) ≤ ⋯ {\displaystyle F(x'_{1})\leq F(x'_{2})\leq F(x'_{3})\leq \cdots \leq F(x'_{k})\leq \cdots } I.e., the fitness values represent a monotonically non-decreasing sequence, which is bounded due to the existence of the optimum. From this follows the convergence of the sequence against the optimum. Since the proof makes no statement about the speed of convergence, it is of little help in practical applications of EAs. But it does justify the recommendation to use elitist EAs. However, when using the usual panmictic population model, elitist EAs tend to converge prematurely more than non-elitist ones. In a panmictic population model, mate selection (see step 4 of the generic definition) is such that every individual in the entire population is eligible as a mate. In non-panmictic populations, selection is suitably restricted, so that the dispersal speed of better individuals is reduced compared to panmictic ones. Thus, the general risk of premature convergence of elitist EAs can be significantly reduced by suitable population models that restrict mate selection. === Virtual alphabets === With the theory of virtual alphabets, David E. Goldberg showed in 1990 that by using a representation with real numbers, an EA that uses classical recombination operators (e.g. uniform or n-point crossover) cannot reach certain areas of the search space, in contrast to a coding with binary numbers. This results in the recommendation for EAs with real representation to use arithmetic operators for recombination (e.g. arithmetic mean or intermediate recombination). With suitable operators, real-valued representations are more effective than binary ones, contrary to earlier opinion. == Comparison to other concepts == === Biological processes === A possible limitation of many evolutionary algorithms is their lack of a clear genotype–phenotype distinction. In nature, the fertilized egg cell undergoes a complex process known as embryogenesis to become a mature p

  Read more →
• 

  Site reliability engineering

  Site reliability engineering (SRE) is a discipline in the field of software engineering and IT infrastructure support that monitors and improves the availability and performance of deployed software systems and large software services (which are expected to deliver reliable response times across events such as new software deployments, hardware failures, and cybersecurity attacks). There is typically a focus on automation and an infrastructure as code methodology. SRE uses elements of software engineering, IT infrastructure, web development, and operations to assist with reliability. It is similar to DevOps as they both aim to improve the reliability and availability of deployed software systems. == History == Site Reliability Engineering originated at Google with Benjamin Treynor Sloss, who founded SRE team in 2003. The concept expanded within the software development industry, leading various companies to employ site reliability engineers. By March 2016, Google had more than 1,000 site reliability engineers on staff. Dedicated SRE teams are common at larger web development companies. In middle-sized and smaller companies, DevOps teams sometimes perform SRE, as well. Organizations that have adopted the concept include Airbnb, Dropbox, IBM, LinkedIn, Netflix, and Wikimedia. == Definition == Site reliability engineers (SREs) are responsible for a combination of system availability, latency, performance, efficiency, change management, monitoring, emergency response, and capacity planning. SREs often have backgrounds in software engineering, systems engineering, and/or system administration. The focuses of SRE include automation, system design, and improvements to system resilience. SRE is considered a specific implementation of DevOps; focusing specifically on building reliable systems, whereas DevOps covers a broader scope of operations. Despite having different focuses, some companies have rebranded their operations teams to SRE teams. == Principles and practices == Common definitions of the practices include (but are not limited to): Automation of repetitive tasks for cost-effectiveness. Defining reliability goals to prevent endless effort. Design of systems with a goal to reduce risks to availability, latency, and efficiency. Observability, the ability to ask arbitrary questions about a system without having to know ahead of time what to ask. Common definitions of the principles include (but are not limited to): Toil management, the implementation of the first principle outlined above. Defining and measuring reliability goals—SLIs, SLOs, and error budgets. Non-Abstract Large Scale Systems Design (NALSD) with a focus on reliability. Designing for and implementing observability. Defining, testing, and running an incident management process. Capacity planning. Change and release management, including CI/CD. Chaos engineering. == Deployment == SRE teams collaborate with other departments within organizations to guide the implementation of the mentioned principles. Below is an overview of common practices: === Kitchen Sink === Kitchen Sink refers to the expansive and often unbounded scope of services and workflows that SRE teams oversee. Unlike traditional roles with clearly defined boundaries, SREs are tasked with various responsibilities, including system performance optimization, incident management, and automation. This approach allows SREs to address multiple challenges, ensuring that systems run efficiently and evolve in response to changing demands and complexities. === Infrastructure === Infrastructure SRE teams focus on maintaining and improving the reliability of systems that support other teams' workflows. While they sometimes collaborate with platform engineering teams, their primary responsibility is ensuring up-time, performance, and efficiency. Platform teams, on the other hand, primarily develop the software and systems used across the organization. While reliability is a goal for both, platform teams prioritize creating and maintaining the tools and services used by internal stakeholders, whereas Infrastructure SRE teams are tasked with ensuring those systems run smoothly and meet reliability standards. === Tools === SRE teams utilize a variety of tools with the aim of measuring, maintaining, and enhancing system reliability. These tools play a role in monitoring performance, identifying issues, and facilitating proactive maintenance. For instance, Nagios Core is commonly employed for system monitoring and alerting, while Prometheus (software) is frequently used for collecting and querying metrics in cloud-native environments. === Product or Application === SRE teams dedicated to specific products or applications are common in large organizations. These teams are responsible for ensuring the reliability, scalability, and performance of key services. In larger companies, it's typical to have multiple SRE teams, each focusing on different products or applications, ensuring that each area receives specialized attention to meet performance and availability targets. === Embedded === In an embedded model, individual SREs or small SRE pairs are integrated within software engineering teams. These SREs collaborate with developers, applying core SRE principles—such as automation, monitoring, and incident response—directly to the software development lifecycle. This approach aims to enhance reliability, performance, and collaboration between SREs and developers. === Consulting === Consulting SRE teams specialize in advising organizations on the implementation of SRE principles and practices. Typically composed of seasoned SREs with a history across various implementations, these teams provide insights and guidance for specific organizational needs. When working directly with clients, these SREs are often referred to as 'Customer Reliability Engineers.' In large organizations that have adopted SRE, a hybrid model is common. This model includes various implementations, such as multiple Product/Application SRE teams dedicated to addressing the specific reliability needs of different products. An Infrastructure SRE team may collaborate with a Platform engineering group to achieve shared reliability goals for a unified platform that supports all products and applications. == Industry == Since 2014, the USENIX organization has hosted the annual SREcon conference, bringing together site reliability engineers from various industries. This conference is a platform for professionals to share knowledge, explore effective practices, and discuss trends in site reliability engineering.

  Read more →
• 

  Shattered set

  A class of sets is said to shatter another set if it is possible to "pick out" any element of that set using intersection. The concept of shattered sets plays an important role in Vapnik–Chervonenkis theory, also known as VC-theory. Shattering and VC-theory are used in the study of empirical processes as well as in statistical computational learning theory. == Definition == Suppose A is a set and C is a class of sets. The class C shatters the set A if for each subset a of A, there is some element c of C such that a = c ∩ A . {\displaystyle a=c\cap A.} Equivalently, C shatters A when their intersection is equal to A's power set: P(A) = { c ∩ A | c ∈ C }. We employ the letter C to refer to a "class" or "collection" of sets, as in a Vapnik–Chervonenkis class (VC-class). The set A is often assumed to be finite because, in empirical processes, we are interested in the shattering of finite sets of data points. == Example == We will show that the class of all discs in the plane (two-dimensional space) does not shatter every set of four points on the unit circle, yet the class of all convex sets in the plane does shatter every finite set of points on the unit circle. Let A be a set of four points on the unit circle and let C be the class of all discs. To test where C shatters A, we attempt to draw a disc around every subset of points in A. First, we draw a disc around the subsets of each isolated point. Next, we try to draw a disc around every subset of point pairs. This turns out to be doable for adjacent points, but impossible for points on opposite sides of the circle. Any attempt to include those points on the opposite side will necessarily include other points not in that pair. Hence, any pair of opposite points cannot be isolated out of A using intersections with class C and so C does not shatter A. As visualized below: Because there is some subset which can not be isolated by any disc in C, we conclude then that A is not shattered by C. And, with a bit of thought, we can prove that no set of four points is shattered by this C. However, if we redefine C to be the class of all elliptical discs, we find that we can still isolate all the subsets from above, as well as the points that were formerly problematic. Thus, this specific set of 4 points is shattered by the class of elliptical discs. Visualized below: With a bit of thought, we could generalize that any set of finite points on a unit circle could be shattered by the class of all convex sets (visualize connecting the dots). == Shatter coefficient == To quantify the richness of a collection C of sets, we use the concept of shattering coefficients (also known as the growth function). For a collection C of sets s ⊂ Ω {\displaystyle s\subset \Omega } , Ω {\displaystyle \Omega } being any space, often a sample space, we define the nth shattering coefficient of C as S C ( n ) = max ∀ x 1 , x 2 , … , x n ∈ Ω card ⁡ { { x 1 , x 2 , … , x n } ∩ s , s ∈ C } {\displaystyle S_{C}(n)=\max _{\forall x_{1},x_{2},\dots ,x_{n}\in \Omega }\operatorname {card} \{\,\{\,x_{1},x_{2},\dots ,x_{n}\}\cap s,s\in C\}} where card {\displaystyle \operatorname {card} } denotes the cardinality of the set and x 1 , x 2 , … , x n ∈ Ω {\displaystyle x_{1},x_{2},\dots ,x_{n}\in \Omega } is any set of n points,. S C ( n ) {\displaystyle S_{C}(n)} is the largest number of subsets of any set A of n points that can be formed by intersecting A with the sets in collection C. For example, if set A contains 3 points, its power set, P ( A ) {\displaystyle P(A)} , contains 2 3 = 8 {\displaystyle 2^{3}=8} elements. If C shatters A, its shattering coefficient(3) would be 8 and S C ( 2 ) {\displaystyle S_{C}(2)} would be 2 2 = 4 {\displaystyle 2^{2}=4} . However, if one of those sets in P ( A ) {\displaystyle P(A)} cannot be obtained through intersections in c, then S C ( 3 ) {\displaystyle S_{C}(3)} would only be 7. If none of those sets can be obtained, S C ( 3 ) {\displaystyle S_{C}(3)} would be 0. Additionally, if S C ( 2 ) = 3 {\displaystyle S_{C}(2)=3} , for example, then there is an element in the set of all 2-point sets from A that cannot be obtained from intersections with C. It follows from this that S C ( 3 ) {\displaystyle S_{C}(3)} would also be less than 8 (i.e. C would not shatter A) because we have already located a "missing" set in the smaller power set of 2-point sets. This example illustrates some properties of S C ( n ) {\displaystyle S_{C}(n)} : S C ( n ) ≤ 2 n {\displaystyle S_{C}(n)\leq 2^{n}} for all n because { s ∩ A | s ∈ C } ⊆ P ( A ) {\displaystyle \{s\cap A|s\in C\}\subseteq P(A)} for any A ⊆ Ω {\displaystyle A\subseteq \Omega } . If S C ( n ) = 2 n {\displaystyle S_{C}(n)=2^{n}} , that means there is a set of cardinality n, which can be shattered by C. If S C ( N ) < 2 N {\displaystyle S_{C}(N)<2^{N}} for some N > 1 {\displaystyle N>1} then S C ( n ) < 2 n {\displaystyle S_{C}(n)<2^{n}} for all n ≥ N {\displaystyle n\geq N} . The third property means that if C cannot shatter any set of cardinality N then it can not shatter sets of larger cardinalities. == Vapnik–Chervonenkis class == If A cannot be shattered by C, there will be a smallest value of n that makes the shatter coefficient(n) less than 2 n {\displaystyle 2^{n}} because as n gets larger, there are more sets that could be missed. Alternatively, there is also a largest value of n for which the S C ( n ) {\displaystyle S_{C}(n)} is still 2 n {\displaystyle 2^{n}} , because as n gets smaller, there are fewer sets that could be omitted. The extreme of this is S C ( 0 ) {\displaystyle S_{C}(0)} (the shattering coefficient of the empty set), which must always be 2 0 = 1 {\displaystyle 2^{0}=1} . These statements lends themselves to defining the VC dimension of a class C as: V C ( C ) = min n { n : S C ( n ) < 2 n } {\displaystyle VC(C)={\underset {n}{\min }}\{n:S_{C}(n)<2^{n}\}\,} or, alternatively, as V C 0 ( C ) = max n { n : S C ( n ) = 2 n } . {\displaystyle VC_{0}(C)={\underset {n}{\max }}\{n:S_{C}(n)=2^{n}\}.\,} Note that V C ( C ) = V C 0 ( C ) + 1. {\displaystyle VC(C)=VC_{0}(C)+1.} . The VC dimension is usually defined as V C 0 {\displaystyle VC_{0}} , the largest cardinality of points chosen that will still shatter A (i.e. n such that S C ( n ) = 2 n {\displaystyle S_{C}(n)=2^{n}} ). Altneratively, if for any n there is a set of cardinality n which can be shattered by C, then S C ( n ) = 2 n {\displaystyle S_{C}(n)=2^{n}} for all n and the VC dimension of this class C is infinite. A class with finite VC dimension is called a Vapnik–Chervonenkis class or VC class. A class C is uniformly Glivenko–Cantelli if and only if it is a VC class.

  Read more →
• 

  Multispectral pattern recognition

  Multispectral remote sensing is the collection and analysis of reflected, emitted, or back-scattered energy from an object or an area of interest in multiple bands of regions of the electromagnetic spectrum (Jensen, 2005). Subcategories of multispectral remote sensing include hyperspectral, in which hundreds of bands are collected and analyzed, and ultraspectral remote sensing where many hundreds of bands are used (Logicon, 1997). The main purpose of multispectral imaging is the potential to classify the image using multispectral classification. This is a much faster method of image analysis than is possible by human interpretation. == Multispectral remote sensing systems == Remote sensing systems gather data via instruments typically carried on satellites in orbit around the Earth. The remote sensing scanner detects the energy that radiates from the object or area of interest. This energy is recorded as an analog electrical signal and converted into a digital value though an A-to-D conversion. There are several multispectral remote sensing systems that can be categorized in the following way: === Multispectral imaging using discrete detectors and scanning mirrors === Landsat Multispectral Scanner (MSS) Landsat Thematic Mapper (TM) NOAA Geostationary Operational Environmental Satellite (GOES) NOAA Advanced Very High Resolution Radiometer (AVHRR) NASA and ORBIMAGE, Inc., Sea-viewing Wide field-of-view Sensor (SeaWiFS) Daedalus, Inc., Aircraft Multispectral Scanner (AMS) NASA Airborne Terrestrial Applications Sensor (ATLAS) === Multispectral imaging using linear arrays === SPOT 1, 2, and 3 High Resolution Visible (HRV) sensors and Spot 4 and 5 High Resolution Visible Infrared (HRVIR) and vegetation sensor Indian Remote Sensing System (IRS) Linear Imaging Self-scanning Sensor (LISS) Space Imaging, Inc. (IKONOS) Digital Globe, Inc. (QuickBird) ORBIMAGE, Inc. (OrbView-3) ImageSat International, Inc. (EROS A1) NASA Terra Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) NASA Terra Multiangle Imaging Spectroradiometer (MISR) === Imaging spectrometry using linear and area arrays === NASA Jet Propulsion Laboratory Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) Compact Airborne Spectrographic Imager 3 (CASI 3) NASA Terra Moderate Resolution Imaging Spectrometer (MODIS) NASA Earth Observer (EO-1) Advanced Land Imager (ALI), Hyperion, and LEISA Atmospheric Corrector (LAC) === Satellite analog and digital photographic systems === Russian SPIN-2 TK-350, and KVR-1000 NASA Space Shuttle and International Space Station Imagery == Multispectral classification methods == A variety of methods can be used for the multispectral classification of images: Algorithms based on parametric and nonparametric statistics that use ratio-and interval-scaled data and nonmetric methods that can also incorporate nominal scale data (Duda et al., 2001), Supervised or unsupervised classification logic, Hard or soft (fuzzy) set classification logic to create hard or fuzzy thematic output products, Per-pixel or object-oriented classification logic, and Hybrid approaches == Supervised classification == In this classification method, the identity and location of some of the land-cover types are obtained beforehand from a combination of fieldwork, interpretation of aerial photography, map analysis, and personal experience. The analyst would locate sites that have similar characteristics to the known land-cover types. These areas are known as training sites because the known characteristics of these sites are used to train the classification algorithm for eventual land-cover mapping of the remainder of the image. Multivariate statistical parameters (means, standard deviations, covariance matrices, correlation matrices, etc.) are calculated for each training site. All pixels inside and outside of the training sites are evaluated and allocated to the class with the more similar characteristics. === Classification scheme === The first step in the supervised classification method is to identify the land-cover and land-use classes to be used. Land-cover refers to the type of material present on the site (e.g. water, crops, forest, wet land, asphalt, and concrete). Land-use refers to the modifications made by people to the land cover (e.g. agriculture, commerce, settlement). All classes should be selected and defined carefully to properly classify remotely sensed data into the correct land-use and/or land-cover information. To achieve this purpose, it is necessary to use a classification system that contains taxonomically correct definitions of classes. If a hard classification is desired, the following classes should be used: Mutually exclusive: there is not any taxonomic overlap of any classes (i.e., rain forest and evergreen forest are distinct classes). Exhaustive: all land-covers in the area have been included. Hierarchical: sub-level classes (e.g., single-family residential, multiple-family residential) are created, allowing that these classes can be included in a higher category (e.g., residential). Some examples of hard classification schemes are: American Planning Association Land-Based Classification System United States Geological Survey Land-use/Land-cover Classification System for Use with Remote Sensor Data U.S. Department of the Interior Fish and Wildlife Service U.S. National Vegetation and Classification System International Geosphere-Biosphere Program IGBP Land Cover Classification System === Training sites === Once the classification scheme is adopted, the image analyst may select training sites in the image that are representative of the land-cover or land-use of interest. If the environment where the data was collected is relatively homogeneous, the training data can be used. If different conditions are found in the site, it would not be possible to extend the remote sensing training data to the site. To solve this problem, a geographical stratification should be done during the preliminary stages of the project. All differences should be recorded (e.g. soil type, water turbidity, crop species, etc.). These differences should be recorded on the imagery and the selection training sites made based on the geographical stratification of this data. The final classification map would be a composite of the individual stratum classifications. After the data are organized in different training sites, a measurement vector is created. This vector would contain the brightness values for each pixel in each band in each training class. The mean, standard deviation, variance-covariance matrix, and correlation matrix are calculated from the measurement vectors. Once the statistics from each training site are determined, the most effective bands for each class should be selected. The objective of this discrimination is to eliminate the bands that can provide redundant information. Graphical and statistical methods can be used to achieve this objective. Some of the graphic methods are: Bar graph spectral plots Cospectral mean vector plots Feature space plots Cospectral parallelepiped or ellipse plots === Classification algorithm === The last step in supervised classification is selecting an appropriate algorithm. The choice of a specific algorithm depends on the input data and the desired output. Parametric algorithms are based on the fact that the data is normally distributed. If the data is not normally distributed, nonparametric algorithms should be used. The more common nonparametric algorithms are: One-dimensional density slicing Parallelipiped Minimum distance Nearest-neighbor Expert system analysis Convolutional neural network == Unsupervised classification == Unsupervised classification (also known as clustering) is a method of partitioning remote sensor image data in multispectral feature space and extracting land-cover information. Unsupervised classification require less input information from the analyst compared to supervised classification because clustering does not require training data. This process consists in a series of numerical operations to search for the spectral properties of pixels. From this process, a map with m spectral classes is obtained. Using the map, the analyst tries to assign or transform the spectral classes into thematic information of interest (i.e. forest, agriculture, urban). This process may not be easy because some spectral clusters represent mixed classes of surface materials and may not be useful. The analyst has to understand the spectral characteristics of the terrain to be able to label clusters as a specific information class. There are hundreds of clustering algorithms. Two of the most conceptually simple algorithms are the chain method and the ISODATA method. === Chain method === The algorithm used in this method operates in a two-pass mode (it passes through the multispectral dataset two times. In the first pass, the program reads through the dataset and sequentially builds clusters (groups of p

  Read more →
• 

  Implicit blockmodeling

  Implicit blockmodeling is an approach in blockmodeling, similar to a valued and homogeneity blockmodeling, where initially an additional normalization is used and then while specifying the parameter of the relevant link is replaced by the block maximum. This approach was first proposed by Batagelj and Ferligoj in 2000, and developed by Aleš Žiberna in 2007/08. Comparing with homogeneity, the implicit blockmodeling will perform similarly with max-regular equivalence, but slightly worse in other settings. It will perform worse than valued and homogeneity blockmodeling with a pre-specified blockmodel.

  Read more →
• 

  Adversarial stylometry

  Adversarial stylometry is the practice of altering writing style to reduce the potential for stylometry to discover the author's identity or their characteristics. This task is also known as authorship obfuscation or authorship anonymisation. Stylometry poses a significant privacy challenge in its ability to unmask anonymous authors or to link pseudonyms to an author's other identities, which, for example, creates difficulties for whistleblowers, activists, and hoaxers and fraudsters. The privacy risk is expected to grow as machine learning techniques and text corpora develop. All adversarial stylometry shares the core idea of faithfully paraphrasing the source text so that the meaning is unchanged but the stylistic signals are obscured. Such a faithful paraphrase is an adversarial example for a stylometric classifier. Several broad approaches to this exist, with some overlap: imitation, substituting the author's own style for another's; translation, applying machine translation with the hope that this eliminates characteristic style in the source text; and obfuscation, deliberately modifying a text's style to make it not resemble the author's own. Manually obscuring style is possible, but laborious; in some circumstances, it is preferable or necessary. Automated tooling, either semi- or fully-automatic, could assist an author. How best to perform the task and the design of such tools is an open research question. While some approaches have been shown to be able to defeat particular stylometric analyses, particularly those that do not account for the potential of adversariality, establishing safety in the face of unknown analyses is an issue. Ensuring the faithfulness of the paraphrase is a critical challenge for automated tools. It is uncertain if the practice of adversarial stylometry is detectable in itself. Some studies have found that particular methods produced signals in the output text, but a stylometrist who is uncertain of what methods may have been used may not be able to reliably detect them. == History == Rao & Rohatgi (2000), an early work in adversarial stylometry, identified machine translation as a possibility, but noted that the quality of translators available at the time presented severe challenges. Kacmarcik & Gamon (2006) is another early work. Brennan, Afroz & Greenstadt (2012) performed the first evaluation of adversarial stylometric methods on actual texts. Brennan & Greenstadt (2009) introduced the first corpus of adversarially authored texts specifically for evaluating stylometric methods; other corpora include the International Imitation Hemingway Competition, the Faux Faulkner contest, and the hoax blog A Gay Girl in Damascus. == Motivations == Rao & Rohatgi (2000) suggest that short, unattributed documents (i.e., anonymous posts) are not at risk of stylometric identification, but pseudonymous authors who have not practiced adversarial stylometry in producing corpuses of thousands of words may be vulnerable. Narayanan et al. (2012) attempted large-scale deanonymisation of 100,000 blog authors with mixed results: the identifications were significantly better than chance, but only accurately matched the blog and author a fifth of the time; identification improved with the number of posts written by the author in the corpus. Even if an author is not identified, some of their characteristics may still be deduced stylometrically, or stylometry may narrow the anonymity set of potential authors sufficiently for other information to complete the identification. Detecting author characteristics (e.g., gender or age) is often simpler than identifying an author from a large, possibly open, set of candidates. Modern machine learning techniques offer powerful tools for identification; further development of corpora and computational stylometric techniques are likely to raise further privacy issues. Gröndahl & Asokan (2020a) say that the general validity of the hypothesis underlying stylometry—that authors have invariant, content-independent 'style fingerprints'—is uncertain, but "the deanonymisation attack is a real privacy concern". Those interested in practicing adversarial stylometry and stylistic deception include whistleblowers avoiding retribution; journalists and activists; perpetrators of frauds and hoaxes; authors of fake reviews; literary forgers; criminals disguising their identity from investigators; and, generally, anyone with a desire for anonymity or pseudonymity. Authors, or agents acting on behalf of authors, may also attempt to remove stylistic clues to author characteristics (e.g., race or gender) so that knowledge of those characteristics cannot be used for discrimination (e.g., through algorithmic bias). Another possible use for adversarial stylometry is in disguising automatically generated text as human-authored. == Methods == With imitation, the author attempts to mislead stylometry by matching their style to another author's. An incomplete imitation, where some of the true author's unique characteristics appear alongside the imitated author's, can be a detectable signal for the use of adversarial stylometry. Imitation can be performed automatically with style transfer systems, though this typically requires a large corpus in the target style for the system to learn from. Another approach is translation, which employs machine translation of a source text to eliminate characteristic style, often through multiple translators in sequence to produce a round-trip translation. Such chained translation can lead to texts being significantly altered, even to the point of incomprehensibility; improved translation tools reduce this risk. More simply-structured texts can be easier to machine translate without losing the original meaning. Machine translation blurs into direct stylistic imitation or obfuscation achieved through automated style transfer, which can be viewed as a "translation" with the same language as input and output. With low-quality translation tools, an author can be required to manually correct major translation errors while avoiding the hazard of re-introducing stylistic characteristics. Wang, Juola & Riddell (2022) found that gross errors introduced by Google Translate were rare, but more common with several intermediate translations—however, occasional simple or short sentences and misspellings in the source text appeared verbatim in the output, potentially providing an identifying signal. Chain translation can leave characteristic traces of its application in a document, which may allow reconstruction of the intermediate languages used and the number of translation steps performed. Obfuscation involves deliberately changing the style of a text to reduce its similarity to other texts by some metric; this may be performed at the time of writing by conscious modification, or as part of a revision process with feedback from the metric being targeted as an input to decide when the text has been sufficiently obfuscated. In contrast to translation, complex texts can offer more opportunities for effective obfuscation without altering meaning, and likewise genres with more permissible variation allow more obfuscation. However, longer texts are harder to thoroughly obfuscate. Obfuscation can blend into imitation if the author develops a novel target style, distinct from their original style. With respect to masking author characteristics, obfuscation may aim to achieve a union (adding signals for imitated characteristics) or an intersection (removing signals and normalising) of other authors' styles. Avoiding the author's own idiosyncrasies and producing a "normalised" text is a critical obfuscatory step: an author may have a unique tendency to misspell certain words, use particular variants, or to format a document in a characteristic way. Stylometric signals vary in how simply they can be adversarially masked; an author may easily change their vocabulary by conscious choice, but altering the pattern of grammar or the letter frequency in their text may be harder to achieve, though Juola & Vescovi (2011) report that imitation typically succeeds at masking more characteristics than obfuscation. Automated obfuscation may require large amounts of training data written by the author. Concerning automated implementations of adversarial stylometry, two possible implementations are rule-based systems for paraphrasing; and encoder–decoder architectures, where the text passes through an intermediate format that is (intended to be) style-neutral. Another division in automated methods is whether there is feedback from an identification system or not. With such feedback, finding paraphrases for author masking has been characterised as a heuristic search problem, exploring textual variants until the result is stylistically sufficiently far (in the case of obfuscation) or near (in the case of imitation), which then constitutes an adversarial example for that identification system. == Evaluation == How

  Read more →
• 

  Oja's rule

  Oja's learning rule, or simply Oja's rule, named after Finnish computer scientist Erkki Oja (Finnish pronunciation: [ˈojɑ], AW-yuh), is a model of how neurons in the brain or in artificial neural networks change connection strength, or learn, over time. It is a modification of the standard Hebb's Rule that, through multiplicative normalization, solves all stability problems and generates an algorithm for principal components analysis. This is a computational form of an effect which is believed to happen in biological neurons. == Theory == Oja's rule requires a number of simplifications to derive, but in its final form it is demonstrably stable, unlike Hebb's rule. It is a single-neuron special case of the Generalized Hebbian Algorithm. However, Oja's rule can also be generalized in other ways to varying degrees of stability and success. === Formula === Consider a simplified model of a neuron y {\displaystyle y} that returns a linear combination of its inputs x using presynaptic weights w: y ( x ) = ∑ j = 1 m x j w j {\displaystyle \,y(\mathbf {x} )~=~\sum _{j=1}^{m}x_{j}w_{j}} Oja's rule defines the change in presynaptic weights w given the output response y {\displaystyle y} of a neuron to its inputs x to be Δ w = w n + 1 − w n = η y n ( x n − y n w n ) , {\displaystyle \,\Delta \mathbf {w} ~=~\mathbf {w} _{n+1}-\mathbf {w} _{n}~=~\eta \,y_{n}(\mathbf {x} _{n}-y_{n}\mathbf {w} _{n}),} where η is the learning rate which can also change with time. Note that the bold symbols are vectors and n defines a discrete time iteration. The rule can also be made for continuous iterations as d w d t = η y ( t ) ( x ( t ) − y ( t ) w ( t ) ) . {\displaystyle \,{\frac {d\mathbf {w} }{dt}}~=~\eta \,y(t)(\mathbf {x} (t)-y(t)\mathbf {w} (t)).} === Derivation === The simplest learning rule known is Hebb's rule, which states in conceptual terms that neurons that fire together, wire together. In component form as a difference equation, it is written Δ w = η y ( x n ) x n {\displaystyle \,\Delta \mathbf {w} ~=~\eta \,y(\mathbf {x} _{n})\mathbf {x} _{n}} , or in scalar form with implicit n-dependence, w i ( n + 1 ) = w i ( n ) + η y ( x ) x i {\displaystyle \,w_{i}(n+1)~=~w_{i}(n)+\eta \,y(\mathbf {x} )x_{i}} , where y(xn) is again the output, this time explicitly dependent on its input vector x. Hebb's rule has synaptic weights approaching infinity with a positive learning rate. We can stop this by normalizing the weights so that each weight's magnitude is restricted between 0, corresponding to no weight, and 1, corresponding to being the only input neuron with any weight. We do this by normalizing the weight vector to be of length one: w i ( n + 1 ) = w i ( n ) + η y ( x ) x i ( ∑ j = 1 m [ w j ( n ) + η y ( x ) x j ] p ) 1 / p {\displaystyle \,w_{i}(n+1)~=~{\frac {w_{i}(n)+\eta \,y(\mathbf {x} )x_{i}}{\left(\sum _{j=1}^{m}[w_{j}(n)+\eta \,y(\mathbf {x} )x_{j}]^{p}\right)^{1/p}}}} . Note that in Oja's original paper, p=2, corresponding to quadrature (root sum of squares), which is the familiar Cartesian normalization rule. However, any type of normalization, even linear, will give the same result without loss of generality. For a small learning rate | η | ≪ 1 {\displaystyle |\eta |\ll 1} the equation can be expanded as a Power series in η {\displaystyle \eta } . w i ( n + 1 ) = w i ( n ) ( ∑ j w j p ( n ) ) 1 / p + η ( y x i ( ∑ j w j p ( n ) ) 1 / p − w i ( n ) ∑ j y x j w j p − 1 ( n ) ( ∑ j w j p ( n ) ) ( 1 + 1 / p ) ) + O ( η 2 ) {\displaystyle \,w_{i}(n+1)~=~{\frac {w_{i}(n)}{\left(\sum _{j}w_{j}^{p}(n)\right)^{1/p}}}~+~\eta \left({\frac {yx_{i}}{\left(\sum _{j}w_{j}^{p}(n)\right)^{1/p}}}-{\frac {w_{i}(n)\sum _{j}yx_{j}w_{j}^{p-1}(n)}{\left(\sum _{j}w_{j}^{p}(n)\right)^{(1+1/p)}}}\right)~+~O(\eta ^{2})} . For small η, our higher-order terms O(η2) go to zero. We again make the specification of a linear neuron, that is, the output of the neuron is equal to the sum of the product of each input and its synaptic weight to the power of p-1, which in the case of p=2 is synaptic weight itself, or y ( x ) = ∑ j = 1 m x j w j p − 1 {\displaystyle \,y(\mathbf {x} )~=~\sum _{j=1}^{m}x_{j}w_{j}^{p-1}} . We also specify that our weights normalize to 1, which will be a necessary condition for stability, so | w | = ( ∑ j = 1 m w j p ) 1 / p = 1 {\displaystyle \,|\mathbf {w} |~=~\left(\sum _{j=1}^{m}w_{j}^{p}\right)^{1/p}~=~1} , which, when substituted into our expansion, gives Oja's rule, or w i ( n + 1 ) = w i ( n ) + η y ( x i − w i ( n ) y ) {\displaystyle \,w_{i}(n+1)~=~w_{i}(n)+\eta \,y(x_{i}-w_{i}(n)y)} . === Stability and PCA === In analyzing the convergence of a single neuron evolving by Oja's rule, one extracts the first principal component, or feature, of a data set. Furthermore, with extensions using the Generalized Hebbian Algorithm, one can create a multi-Oja neural network that can extract as many features as desired, allowing for principal components analysis. A principal component aj is extracted from a dataset x through some associated vector qj, or aj = qj⋅x, and we can restore our original dataset by taking x = ∑ j a j q j {\displaystyle \mathbf {x} ~=~\sum _{j}a_{j}\mathbf {q} _{j}} . In the case of a single neuron trained by Oja's rule, we find the weight vector converges to q1, or the first principal component, as time or number of iterations approaches infinity. We can also define, given a set of input vectors Xi, that its correlation matrix Rij = XiXj has an associated eigenvector given by qj with eigenvalue λj. The variance of outputs of our Oja neuron σ2(n) = ⟨y2(n)⟩ then converges with time iterations to the principal eigenvalue, or lim n → ∞ σ 2 ( n ) = λ 1 {\displaystyle \lim _{n\rightarrow \infty }\sigma ^{2}(n)~=~\lambda _{1}} . These results are derived using Lyapunov function analysis, and they show that Oja's neuron necessarily converges on strictly the first principal component if certain conditions are met in our original learning rule. Most importantly, our learning rate η is allowed to vary with time, but only such that its sum is divergent but its power sum is convergent, that is ∑ n = 1 ∞ η ( n ) = ∞ , ∑ n = 1 ∞ η ( n ) p < ∞ , p > 1 {\displaystyle \sum _{n=1}^{\infty }\eta (n)=\infty ,~~~\sum _{n=1}^{\infty }\eta (n)^{p}<\infty ,~~~p>1} . Our output activation function y(x(n)) is also allowed to be nonlinear and nonstatic, but it must be continuously differentiable in both x and w and have derivatives bounded in time. == Applications == Oja's rule was originally described in Oja's 1982 paper, but the principle of self-organization to which it is applied is first attributed to Alan Turing in 1952. PCA has also had a long history of use before Oja's rule formalized its use in network computation in 1989. The model can thus be applied to any problem of self-organizing mapping, in particular those in which feature extraction is of primary interest. Therefore, Oja's rule has an important place in image and speech processing. It is also useful as it expands easily to higher dimensions of processing, thus being able to integrate multiple outputs quickly. A canonical example is its use in binocular vision. === Biology and Oja's subspace rule === There is clear evidence for both long-term potentiation and long-term depression in biological neural networks, along with a normalization effect in both input weights and neuron outputs. However, while there is no direct experimental evidence yet of Oja's rule active in a biological neural network, a biophysical derivation of a generalization of the rule is possible. Such a derivation requires retrograde signalling from the postsynaptic neuron, which is biologically plausible (see neural backpropagation), and takes the form of Δ w i j ∝ ⟨ x i y j ⟩ − ϵ ⟨ ( c p r e ∗ ∑ k w i k y k ) ⋅ ( c p o s t ∗ y j ) ⟩ , {\displaystyle \Delta w_{ij}~\propto ~\langle x_{i}y_{j}\rangle -\epsilon \left\langle \left(c_{\mathrm {pre} }\sum _{k}w_{ik}y_{k}\right)\cdot \left(c_{\mathrm {post} }y_{j}\right)\right\rangle ,} where as before wij is the synaptic weight between the ith input and jth output neurons, x is the input, y is the postsynaptic output, and we define ε to be a constant analogous the learning rate, and cpre and cpost are presynaptic and postsynaptic functions that model the weakening of signals over time. Note that the angle brackets denote the average and the ∗ operator is a convolution. By taking the pre- and post-synaptic functions into frequency space and combining integration terms with the convolution, we find that this gives an arbitrary-dimensional generalization of Oja's rule known as Oja's Subspace, namely Δ w = C x ⋅ w − w ⋅ C y . {\displaystyle \Delta w~=~Cx\cdot w-w\cdot Cy.}

  Read more →
• 

  Dimensionality reduction

  Dimensionality reduction, or dimension reduction, is the transformation of data from a high-dimensional space into a low-dimensional space so that the low-dimensional representation retains some meaningful properties of the original data, ideally close to its intrinsic dimension. Working in high-dimensional spaces can be undesirable for many reasons; raw data are often sparse as a consequence of the curse of dimensionality, and analyzing the data is usually computationally intractable. Dimensionality reduction is common in fields that deal with large numbers of observations and/or large numbers of variables, such as signal processing, speech recognition, neuroinformatics, and bioinformatics. Methods are commonly divided into linear and nonlinear approaches. Linear approaches can be further divided into feature selection and feature extraction. Dimensionality reduction can be used for noise reduction, data visualization, cluster analysis, or as an intermediate step to facilitate other analyses. == Feature selection == The process of feature selection aims to find a suitable subset of the input variables (features, or attributes) for the task at hand. The three strategies are: the filter strategy (e.g., information gain), the wrapper strategy (e.g., accuracy-guided search), and the embedded strategy (features are added or removed while building the model based on prediction errors). Data analysis such as regression or classification can be done in the reduced space more accurately than in the original space. == Feature projection == Feature projection (also called feature extraction) transforms the data from the high-dimensional space to a space of fewer dimensions. The data transformation may be linear, as in principal component analysis (PCA), but many nonlinear dimensionality reduction techniques also exist. For multidimensional data, tensor representation can be used in dimensionality reduction through multilinear subspace learning. === Principal component analysis (PCA) === The main linear technique for dimensionality reduction, principal component analysis, performs a linear mapping of the data to a lower-dimensional space in such a way that the variance of the data in the low-dimensional representation is maximized. In practice, the covariance (and sometimes the correlation) matrix of the data is constructed and the eigenvectors on this matrix are computed. The eigenvectors that correspond to the largest eigenvalues (the principal components) can now be used to reconstruct a large fraction of the variance of the original data. Moreover, the first few eigenvectors can often be interpreted in terms of the large-scale physical behavior of the system, because they often contribute the vast majority of the system's energy, especially in low-dimensional systems. Still, this must be proved on a case-by-case basis as not all systems exhibit this behavior. The original space (with dimension of the number of points) has been reduced (with data loss, but hopefully retaining the most important variance) to the space spanned by a few eigenvectors. === Non-negative matrix factorization (NMF) === NMF decomposes a non-negative matrix to the product of two non-negative ones, which has been a promising tool in fields where only non-negative signals exist, such as astronomy. NMF is well known since the multiplicative update rule by Lee & Seung, which has been continuously developed: the inclusion of uncertainties, the consideration of missing data and parallel computation, sequential construction which leads to the stability and linearity of NMF, as well as other updates including handling missing data in digital image processing. With a stable component basis during construction, and a linear modeling process, sequential NMF is able to preserve the flux in direct imaging of circumstellar structures in astronomy, as one of the methods of detecting exoplanets, especially for the direct imaging of circumstellar discs. In comparison with PCA, NMF does not remove the mean of the matrices, which leads to physical non-negative fluxes; therefore NMF is able to preserve more information than PCA as demonstrated by Ren et al. === Kernel PCA === Principal component analysis can be employed in a nonlinear way by means of the kernel trick. The resulting technique is capable of constructing nonlinear mappings that maximize the variance in the data. The resulting technique is called kernel PCA. === Graph-based kernel PCA === Other prominent nonlinear techniques include manifold learning techniques such as Isomap, locally linear embedding (LLE), Hessian LLE, Laplacian eigenmaps, and methods based on tangent space analysis. These techniques assume that the high-dimensional input data lies near a low-dimensional manifold embedded in the ambient space, and construct a low-dimensional representation using a cost function that retains local properties of the data; they can be viewed as defining a graph-based kernel for Kernel PCA. More recently, techniques have been proposed that, instead of defining a fixed kernel, try to learn the kernel using semidefinite programming. The most prominent example of such a technique is maximum variance unfolding (MVU). The central idea of MVU is to exactly preserve all pairwise distances between nearest neighbors (in the inner product space) while maximizing the distances between points that are not nearest neighbors. An alternative approach to neighborhood preservation is through the minimization of a cost function that measures differences between distances in the input and output spaces. Important examples of such techniques include: classical multidimensional scaling, which is identical to PCA; Isomap, which uses geodesic distances in the data space; diffusion maps, which use diffusion distances in the data space; t-distributed stochastic neighbor embedding (t-SNE), which minimizes the divergence between distributions over pairs of points; and curvilinear component analysis. A different approach to nonlinear dimensionality reduction is through the use of autoencoders, a special kind of feedforward neural networks with a bottleneck hidden layer. The training of deep encoders is typically performed using a greedy layer-wise pre-training (e.g., using a stack of restricted Boltzmann machines) that is followed by a finetuning stage based on backpropagation. === Linear discriminant analysis (LDA) === Linear discriminant analysis (LDA) is a generalization of Fisher's linear discriminant, a method used in statistics, pattern recognition, and machine learning to find a linear combination of features that characterizes or separates two or more classes of objects or events. === Generalized discriminant analysis (GDA) === GDA deals with nonlinear discriminant analysis using kernel function operator. The underlying theory is close to the support-vector machines (SVM) insofar as the GDA method provides a mapping of the input vectors into high-dimensional feature space. Similar to LDA, the objective of GDA is to find a projection for the features into a lower dimensional space by maximizing the ratio of between-class scatter to within-class scatter. === Autoencoder === Autoencoders can be used to learn nonlinear dimension reduction functions and codings together with an inverse function from the coding to the original representation. === t-SNE === T-distributed Stochastic Neighbor Embedding (t-SNE) is a nonlinear dimensionality reduction technique useful for the visualization of high-dimensional datasets. It is not recommended for use in analysis such as clustering or outlier detection since it does not necessarily preserve densities or distances well. === UMAP === Uniform manifold approximation and projection (UMAP) is a nonlinear dimensionality reduction technique. Visually, it is similar to t-SNE, but it assumes that the data is uniformly distributed on a locally connected Riemannian manifold and that the Riemannian metric is locally constant or approximately locally constant. == Dimension reduction == For high-dimensional datasets, dimension reduction is usually performed prior to applying a k-nearest neighbors (k-NN) algorithm in order to mitigate the curse of dimensionality. Feature extraction and dimension reduction can be combined in one step, using principal component analysis (PCA), linear discriminant analysis (LDA), canonical correlation analysis (CCA), or non-negative matrix factorization (NMF) techniques to pre-process the data, followed by clustering via k-NN on feature vectors in a reduced-dimension space. In machine learning, this process is also called low-dimensional embedding. For high-dimensional datasets (e.g., when performing similarity search on live video streams, DNA data, or high-dimensional time series), running a fast approximate k-NN search using locality-sensitive hashing, random projection, "sketches", or other high-dimensional similarity search techniques from the VLDB conference toolbox may be the only fe

  Read more →