AI Coding Unity

AI Coding Unity — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Human image synthesis

  Human image synthesis is technology that can be applied to make believable and even photorealistic renditions of human-likenesses, moving or still. It has effectively existed since the early 2000s. Many films using computer generated imagery have featured synthetic images of human-like characters digitally composited onto the real or other simulated film material. Towards the end of the 2010s deep learning artificial intelligence has been applied to synthesize images and video that look like humans, without need for human assistance, once the training phase has been completed, whereas the old school 7D-route required massive amounts of human work. == Timeline of human image synthesis == In 1971 Henri Gouraud made the first CG geometry capture and representation of a human face. Modeling was his wife Sylvie Gouraud. The 3D model was a simple wire-frame model and he applied the Gouraud shader he is most known for to produce the first known representation of human-likeness on computer. The 1972 short film A Computer Animated Hand by Edwin Catmull and Fred Parke was the first time that computer-generated imagery was used in film to simulate moving human appearance. The film featured a computer simulated hand and face (watch film here). The 1976 film Futureworld reused parts of A Computer Animated Hand on the big screen. The 1983 music video for song Musique Non-Stop by German band Kraftwerk aired in 1986. Created by the artist Rebecca Allen, it features non-realistic looking, but clearly recognizable computer simulations of the band members. The 1994 film The Crow was the first film production to make use of digital compositing of a computer simulated representation of a face onto scenes filmed using a body double. Necessity was the muse as the actor Brandon Lee portraying the protagonist was tragically killed accidentally on-stage. In 1999 Paul Debevec et al. of USC captured the reflectance field of a human face with their first version of a light stage. They presented their method at the SIGGRAPH 2000 In 2003 audience debut of photo realistic human-likenesses in the 2003 films The Matrix Reloaded in the burly brawl sequence where up-to-100 Agent Smiths fight Neo and in The Matrix Revolutions where at the start of the end showdown Agent Smith's cheekbone gets punched in by Neo leaving the digital look-alike unnaturally unhurt. The Matrix Revolutions bonus DVD documents and depicts the process in some detail and the techniques used, including facial motion capture and limbal motion capture, and projection onto models. In 2003 The Animatrix: Final Flight of the Osiris a state-of-the-art want-to-be human likenesses not quite fooling the watcher made by Square Pictures. In 2003 digital likeness of Tobey Maguire was made for movies Spider-man 2 and Spider-man 3 by Sony Pictures Imageworks. In 2005 the Face of the Future project was an established. by the University of St Andrews and Perception Lab, funded by the EPSRC. The website contains a "Face Transformer", which enables users to transform their face into any ethnicity and age as well as the ability to transform their face into a painting (in the style of either Sandro Botticelli or Amedeo Modigliani). This process is achieved by combining the user's photograph with an average face. In 2009 Debevec et al. presented new digital likenesses, made by Image Metrics, this time of actress Emily O'Brien whose reflectance was captured with the USC light stage 5 Motion looks fairly convincing contrasted to the clunky run in the Animatrix: Final Flight of the Osiris which was state-of-the-art in 2003 if photorealism was the intention of the animators. In 2009 a digital look-alike of a younger Arnold Schwarzenegger was made for the movie Terminator Salvation though the end result was critiqued as unconvincing. Facial geometry was acquired from a 1984 mold of Schwarzenegger. In 2010 Walt Disney Pictures released a sci-fi sequel entitled Tron: Legacy with a digitally rejuvenated digital look-alike of actor Jeff Bridges playing the antagonist CLU. In SIGGGRAPH 2013 Activision and USC presented a real-time "Digital Ira" a digital face look-alike of Ari Shapiro, an ICT USC research scientist, utilizing the USC light stage X by Ghosh et al. for both reflectance field and motion capture. The end result both precomputed and real-time rendering with the modernest game GPU shown here and looks fairly realistic. In 2014 The Presidential Portrait by USC Institute for Creative Technologies in conjunction with the Smithsonian Institution was made using the latest USC mobile light stage wherein President Barack Obama had his geometry, textures and reflectance captured. In 2014 Ian Goodfellow et al. presented the principles of a generative adversarial network. GANs made the headlines in early 2018 with the deepfakes controversies. For the 2015 film Furious 7 a digital look-alike of actor Paul Walker who died in an accident during the filming was done by Weta Digital to enable the completion of the film. In 2016 techniques which allow near real-time counterfeiting of facial expressions in existing 2D video have been believably demonstrated. In 2016 a digital look-alike of Peter Cushing was made for the Rogue One film where its appearance would appear to be of same age as the actor was during the filming of the original 1977 Star Wars film. In SIGGRAPH 2017 an audio driven digital look-alike of upper torso of Barack Obama was presented by researchers from University of Washington. It was driven only by a voice track as source data for the animation after the training phase to acquire lip sync and wider facial information from training material consisting 2D videos with audio had been completed. Late 2017 and early 2018 saw the surfacing of the deepfakes controversy where porn videos were doctored using deep machine learning so that the face of the actress was replaced by the software's opinion of what another persons face would look like in the same pose and lighting. In 2018 Game Developers Conference Epic Games and Tencent Games demonstrated "Siren", a digital look-alike of the actress Bingjie Jiang. It was made possible with the following technologies: CubicMotion's computer vision system, 3Lateral's facial rigging system and Vicon's motion capture system. The demonstration ran in near real time at 60 frames per second in the Unreal Engine 4. In 2018 at the World Internet Conference in Wuzhen the Xinhua News Agency presented two digital look-alikes made to the resemblance of its real news anchors Qiu Hao (Chinese language) and Zhang Zhao (English language). The digital look-alikes were made in conjunction with Sogou. Neither the speech synthesis used nor the gesturing of the digital look-alike anchors were good enough to deceive the watcher to mistake them for real humans imaged with a TV camera. In September 2018 Google added "involuntary synthetic pornographic imagery" to its ban list, allowing anyone to request the search engine block results that falsely depict them as "nude or in a sexually explicit situation." In February 2019 Nvidia open sources StyleGAN, a novel generative adversarial network. Right after this Phillip Wang made the website ThisPersonDoesNotExist.com with StyleGAN to demonstrate that unlimited amounts of often photo-realistic looking facial portraits of no-one can be made automatically using a GAN. Nvidia's StyleGAN was presented in a not yet peer reviewed paper in late 2018. At the June 2019 CVPR the MIT CSAIL presented a system titled "Speech2Face: Learning the Face Behind a Voice" that synthesizes likely faces based on just a recording of a voice. It was trained with massive amounts of video of people speaking. Since 1 July 2019 Virginia has criminalized the sale and dissemination of unauthorized synthetic pornography, but not the manufacture., as § 18.2–386.2 titled 'Unlawful dissemination or sale of images of another; penalty.' became part of the Code of Virginia. The law text states: "Any person who, with the intent to coerce, harass, or intimidate, maliciously disseminates or sells any videographic or still image created by any means whatsoever that depicts another person who is totally nude, or in a state of undress so as to expose the genitals, pubic area, buttocks, or female breast, where such person knows or has reason to know that he is not licensed or authorized to disseminate or sell such videographic or still image is guilty of a Class 1 misdemeanor.". The identical bills were House Bill 2678 presented by Delegate Marcus Simon to the Virginia House of Delegates on 14 January 2019 and three-day later an identical Senate bill 1736 was introduced to the Senate of Virginia by Senator Adam Ebbin. Since 1 September 2019 Texas senate bill SB 751 amendments to the election code came into effect, giving candidates in elections a 30-day protection period to the elections during which making and distributing digital look-alikes or synthetic fakes of the candidates is an offense. Th

  Read more →
• 

  Randomized rounding

  In computer science and operations research, randomized rounding is a widely used approach for designing and analyzing approximation algorithms. Many combinatorial optimization problems are computationally intractable to solve exactly (to optimality). For such problems, randomized rounding can be used to design fast (polynomial time) approximation algorithms—that is, algorithms that are guaranteed to return an approximately optimal solution given any input. The basic idea of randomized rounding is to convert an optimal solution of a relaxation of the problem into an approximately-optimal solution to the original problem. The resulting algorithm is usually analyzed using the probabilistic method. == Overview == The basic approach has three steps: Formulate the problem to be solved as an integer linear program (ILP). Compute an optimal fractional solution x {\displaystyle x} to the linear programming relaxation (LP) of the ILP. Round the fractional solution x {\displaystyle x} of the LP to an integer solution x ′ {\displaystyle x'} of the ILP. (Although the approach is most commonly applied with linear programs, other kinds of relaxations are sometimes used. For example, see Goemans' and Williamson's semidefinite programming-based Max-Cut approximation algorithm.) In the first step, the challenge is to choose a suitable integer linear program. Familiarity with linear programming, in particular modelling using linear programs and integer linear programs, is required. For many problems, there is a natural integer linear program that works well, such as in the Set Cover example below. (The integer linear program should have a small integrality gap; indeed randomized rounding is often used to prove bounds on integrality gaps.) In the second step, the optimal fractional solution can typically be computed in polynomial time using any standard linear programming algorithm. In the third step, the fractional solution must be converted into an integer solution (and thus a solution to the original problem). This is called rounding the fractional solution. The resulting integer solution should (provably) have cost not much larger than the cost of the fractional solution. This will ensure that the cost of the integer solution is not much larger than the cost of the optimal integer solution. The main technique used to do the third step (rounding) is to use randomization, and then to use probabilistic arguments to bound the increase in cost due to the rounding (following the probabilistic method from combinatorics). Therein, probabilistic arguments are used to show the existence of discrete structures with desired properties. In this context, one uses such arguments to show the following: Given any fractional solution x {\displaystyle x} of the LP, with positive probability the randomized rounding process produces an integer solution x ′ {\displaystyle x'} that approximates x {\displaystyle x} according to some desired criterion. Finally, to make the third step computationally efficient, one either shows that x ′ {\displaystyle x'} approximates x {\displaystyle x} with high probability (so that the step can remain randomized) or one derandomizes the rounding step, typically using the method of conditional probabilities. The latter method converts the randomized rounding process into an efficient deterministic process that is guaranteed to reach a good outcome. == Example: the set cover problem == The following example illustrates how randomized rounding can be used to design an approximation algorithm for the set cover problem. Fix any instance ⟨ c , S ⟩ {\displaystyle \langle c,{\mathcal {S}}\rangle } of set cover over a universe U {\displaystyle {\mathcal {U}}} . === Computing the fractional solution === For step 1, let IP be the standard integer linear program for set cover for this instance. For step 2, let LP be the linear programming relaxation of IP, and compute an optimal solution x ∗ {\displaystyle x^{}} to LP using any standard linear programming algorithm. This takes time polynomial in the input size. The feasible solutions to LP are the vectors x {\displaystyle x} that assign each set s ∈ S {\displaystyle s\in {\mathcal {S}}} a non-negative weight x s {\displaystyle x_{s}} , such that, for each element e ∈ U {\displaystyle e\in {\mathcal {U}}} , x ′ {\displaystyle x'} covers e {\displaystyle e} —the total weight assigned to the sets containing e {\displaystyle e} is at least 1, that is, ∑ s ∋ e x s ≥ 1. {\displaystyle \sum _{s\ni e}x_{s}\geq 1.} The optimal solution x ∗ {\displaystyle x^{}} is a feasible solution whose cost ∑ s ∈ S c ( S ) x s ∗ {\displaystyle \sum _{s\in {\mathcal {S}}}c(S)x_{s}^{}} is as small as possible. Note that any set cover C {\displaystyle {\mathcal {C}}} for S {\displaystyle {\mathcal {S}}} gives a feasible solution x {\displaystyle x} (where x s = 1 {\displaystyle x_{s}=1} for s ∈ C {\displaystyle s\in {\mathcal {C}}} , x s = 0 {\displaystyle x_{s}=0} otherwise). The cost of this C {\displaystyle {\mathcal {C}}} equals the cost of x {\displaystyle x} , that is, ∑ s ∈ C c ( s ) = ∑ s ∈ S c ( s ) x s . {\displaystyle \sum _{s\in {\mathcal {C}}}c(s)=\sum _{s\in {\mathcal {S}}}c(s)x_{s}.} In other words, the linear program LP is a relaxation of the given set-cover problem. Since x ∗ {\displaystyle x^{}} has minimum cost among feasible solutions to the LP, the cost of x ∗ {\displaystyle x^{}} is a lower bound on the cost of the optimal set cover. === Randomized rounding step === In step 3, we must convert the minimum-cost fractional set cover x ∗ {\displaystyle x^{}} into a feasible integer solution x ′ {\displaystyle x'} (corresponding to a true set cover). The rounding step should produce an x ′ {\displaystyle x'} that, with positive probability, has cost within a small factor of the cost of x ∗ {\displaystyle x^{}} .Then (since the cost of x ∗ {\displaystyle x^{}} is a lower bound on the cost of the optimal set cover), the cost of x ′ {\displaystyle x'} will be within a small factor of the optimal cost. As a starting point, consider the most natural rounding scheme: For each set s ∈ S {\displaystyle s\in {\mathcal {S}}} in turn, take x s ′ = 1 {\displaystyle x'_{s}=1} with probability min ( 1 , x s ∗ ) {\displaystyle \min(1,x_{s}^{})} , otherwise take x s ′ = 0 {\displaystyle x'_{s}=0} . With this rounding scheme, the expected cost of the chosen sets is at most ∑ s c ( s ) x s ∗ {\displaystyle \sum _{s}c(s)x_{s}^{}} , the cost of the fractional cover. This is good. Unfortunately the coverage is not good. When the variables x s ∗ {\displaystyle x_{s}^{}} are small, the probability that an element e {\displaystyle e} is not covered is about ∏ s ∋ e 1 − x s ∗ ≈ ∏ s ∋ e exp ⁡ ( − x s ∗ ) = exp ⁡ ( − ∑ s ∋ e x s ∗ ) ≈ exp ⁡ ( − 1 ) . {\displaystyle \prod _{s\ni e}1-x_{s}^{}\approx \prod _{s\ni e}\exp(-x_{s}^{})=\exp {\Big (}-\sum _{s\ni e}x_{s}^{}{\Big )}\approx \exp(-1).} So only a constant fraction of the elements will be covered in expectation. To make x ′ {\displaystyle x'} cover every element with high probability, the standard rounding scheme first scales up the rounding probabilities by an appropriate factor λ > 1 {\displaystyle \lambda >1} . Here is the standard rounding scheme: Fix a parameter λ ≥ 1 {\displaystyle \lambda \geq 1} . For each set s ∈ S {\displaystyle s\in {\mathcal {S}}} in turn, take x s ′ = 1 {\displaystyle x'_{s}=1} with probability min ( λ x s ∗ , 1 ) {\displaystyle \min(\lambda x_{s}^{},1)} , otherwise take x s ′ = 0 {\displaystyle x'_{s}=0} . Scaling the probabilities up by λ {\displaystyle \lambda } increases the expected cost by λ {\displaystyle \lambda } , but makes coverage of all elements likely. The idea is to choose λ {\displaystyle \lambda } as small as possible so that all elements are provably covered with non-zero probability. Here is a detailed analysis. ==== Lemma (approximation guarantee for rounding scheme) ==== Fix λ = ln ⁡ ( 2 | U | ) {\displaystyle \lambda =\ln(2|{\mathcal {U}}|)} . With positive probability, the rounding scheme returns a set cover x ′ {\displaystyle x'} of cost at most 2 ln ⁡ ( 2 | U | ) c ⋅ x ∗ {\displaystyle 2\ln(2|{\mathcal {U}}|)c\cdot x^{}} (and thus of cost O ( log ⁡ | U | ) {\displaystyle O(\log |{\mathcal {U}}|)} times the cost of the optimal set cover). (Note: with care the O ( log ⁡ | U | ) {\displaystyle O(\log |{\mathcal {U}}|)} can be reduced to ln ⁡ ( | U | ) + O ( log ⁡ log ⁡ | U | ) {\displaystyle \ln(|{\mathcal {U}}|)+O(\log \log |{\mathcal {U}}|)} .) ==== Proof ==== The output x ′ {\displaystyle x'} of the random rounding scheme has the desired properties as long as none of the following "bad" events occur: the cost c ⋅ x ′ {\displaystyle c\cdot x'} of x ′ {\displaystyle x'} exceeds 2 λ c ⋅ x ∗ {\displaystyle 2\lambda c\cdot x^{}} , or for some element e {\displaystyle e} , x ′ {\displaystyle x'} fails to cover e {\displaystyle e} . The expectation of each x s ′ {\displaystyle x'_{s}} is at most λ x s ∗ {\displaystyle \lambda x_{s

  Read more →
• 

  ArchiMate

  ArchiMate ( AR-ki-mayt) is an open and independent enterprise architecture modeling language to support the description, analysis and visualization of architecture within and across business domains in an unambiguous way. ArchiMate is a technical standard from The Open Group and is based on concepts from the now superseded IEEE 1471 standard. It is supported by various tool vendors and consulting firms. ArchiMate is also a registered trademark of The Open Group. The Open Group has a certification program for ArchiMate users, software tools and courses. ArchiMate distinguishes itself from other languages such as Unified Modeling Language (UML) and Business Process Modeling and Notation (BPMN) by its enterprise modelling scope. Also, UML and BPMN are meant for a specific use and they are quite heavy – containing about 150 (UML) and 250 (BPMN) modeling concepts whereas ArchiMate works with just about 50 (in version 2.0). The goal of ArchiMate is to be ”as small as possible”, not to cover every edge scenario imaginable. To be easy to learn and apply, ArchiMate was intentionally restricted “to the concepts that suffice for modeling the proverbial 80% of practical cases". == Overview == ArchiMate offers a common language for describing the construction and operation of business processes, organizational structures, information flows, IT systems, and technical infrastructure. This insight helps the different stakeholders to design, assess, and communicate the consequences of decisions and changes within and between these business domains. The main concepts and relationships of the ArchiMate language can be seen as a framework, the so-called Archimate Framework: It divides the enterprise architecture into a business, application and technology layer. In each layer, three aspects are considered: active elements, an internal structure and elements that define use or communicate information. One of the objectives of the ArchiMate language is to define the relationships between concepts in different architecture domains. The concepts of this language therefore hold the middle between the detailed concepts, which are used for modeling individual domains (for example, the Unified Modeling Language (UML) for modeling software products), and Business Process Model and Notation (BPMN), which is used for business process modeling. == History == ArchiMate is partly based on the now superseded IEEE 1471 standard. It was developed in the Netherlands by a project team from the Telematica Instituut in cooperation with several Dutch partners from government, industry and academia. Among the partners were Ordina NV, Radboud Universiteit Nijmegen, the Leiden Institute for Advanced Computer Science (LIACS) and the Centrum Wiskunde & Informatica (CWI). Later, tests were performed in organizations such as ABN AMRO, the Dutch Tax and Customs Administration and the ABP. The development process lasted from July 2002 to December 2004, and took about 35 person years and approximately 4 million euros. The development was funded by the Dutch government (Dutch Tax and Customs Administration), and business partners, including ABN AMRO and the ABP Pension Fund. In 2008 the ownership and stewardship of ArchiMate was transferred to The Open Group. It is now managed by the ArchiMate Forum within The Open Group. In February 2009 The Open Group published the ArchiMate 1.0 standard as a formal technical standard. In January 2012 the ArchiMate 2.0 standard, and in 2013 the ArchiMate 2.1 standard was released. In June 2016, the Open Group released version 3.0 of the ArchiMate Specification. An update to Archimate 3.0.1 came out in August 2017. Archimate 3.1 was published 5 November 2019. The latest version of the ArchiMate Specification is version 3.2 released October 2022. Version 3.0 adds enhanced support for capability-oriented strategic modelling, new entities representing physical resources (for modelling the ingredients, equipment and transport resources used in the physical world) and a generic metamodel showing the entity types and the relationships between them. == ArchiMate framework == === Core framework === The main concepts and elements of the ArchiMate language are being presented as ArchiMate core framework. It consists of three layers and three aspects. This creates a matrix of combinations. Every layer has its passive structure, behavior and active structure aspects. ==== Layers ==== ArchiMate has a layered and service-oriented look on architectural models. The higher layers make use of services that are provided by the lower layers. Although, at an abstract level, the concepts that are used within each layer are similar, we define more concrete concepts that are specific for a certain layer. In this context, we distinguish three main layers: The business layer is about business processes, services, functions and events of business units. This layer "offers products and services to external customers, which are realized in the organization by business processes performed by business actors and roles". The application layer is about software applications that "support the components in the business with application services". The technology layer deals "with the hardware and communication infrastructure to support the application layer. This layer offers infrastructural services needed to run applications, realized by computer and communication hardware and system software". Each of these main layers can be further divided in sub-layers. For example, in the business layer, the primary business processes realising the products of a company may make use of a layer of secondary (supporting) business processes; in the application layer, the end-user applications may make use of generic services offered by supporting applications. On top of the business layer, a separate environment layer may be added, modelling the external customers that make use of the services of the organisation (although these may also be considered part of the business layer). In line with service orientation, the most important relation between layers is formed by use relations, which show how the higher layers make use of the services of lower layers. However, a second type of link is formed by realisation relations: elements in lower layers may realise comparable elements in higher layers; e.g., a ‘data object’ (application layer) may realise a ‘business object’ (business layer); or an ‘artifact’ (technology layer) may realise either a ‘data object’ or an ‘application component’ (application layer). ==== Aspects ==== Passive structure is the set of entities on which actions are conducted. In the business layer the example would be information objects, in the application layer data objects and in the technology layer, they could include physical objects. Behavior refers to the processes and functions performed by the actors. "Structural elements are assigned to behavioral elements, to show who or what displays the behavior". Active structure is the set of entities that display some behavior, e.g. business actors, devices, or application components. === Full framework === The Full ArchiMate framework is enriched by the physical layer, which was added to allow modeling of “physical equipment, materials, and distribution networks” and was not present in the previous version. The implementation and migration layer adds elements that allow architects to model a state of transition, to mark parts of the architecture that are temporary for the purpose, as the name says, of implementation and migration. Strategy layer adds three elements: resource, capability and course of action. These elements help to incorporate strategic dimension to the ArchiMate language by allowing it to depict the usage of resources and capabilities in order to achieve some strategic goals. Finally, there is a motivation aspect that allows different stakeholders to describe the motivation of specific actors or domains, which can be quite important when looking at one thing from several different angles. It adds several elements like stakeholder, value, driver, goal, meaning etc. == ArchiMate language == The ArchiMate language is formed as a top-level and is hierarchical. On the top, there is a model. A model is a collection of concepts. A concept can be either an element or a relationship. An element can be either of behavior type, structure, motivation or a so-called composite element (which means that it does not fit just one aspect of the framework, but two or more). The functionality of all concepts without a dependency on a specific layer is described by the generic metamodel. This layer-independent description of concepts is useful when trying to understand the mechanics of the Archimate language. === Concepts === ==== Elements ==== The generic elements are distributed into the same categories as the layers: Active structure elements Behavior elements Passive structure elements Motivation elements Active structure e

  Read more →
• 

  EdgeRank

  EdgeRank is the name commonly given to the algorithm that Facebook uses to determine what articles should be displayed in a user's News Feed. As of 2011, Facebook has stopped using the EdgeRank system and uses a machine learning algorithm that, as of 2013, takes more than 100,000 factors into account. EdgeRank was developed and implemented by Serkan Piantino. == Formula and factors == In 2010, a simplified version of the EdgeRank algorithm was presented as: ∑ e d g e s e u e w e d e {\displaystyle \sum _{\mathrm {edges\,} e}u_{e}w_{e}d_{e}} where: u e {\displaystyle u_{e}} is user affinity. w e {\displaystyle w_{e}} is how the content is weighted. d e {\displaystyle d_{e}} is a time-based decay parameter. User Affinity: The User Affinity part of the algorithm in Facebook's EdgeRank looks at the relationship and proximity of the user and the content (post/status update). Content Weight: What action was taken by the user on the content. Time-Based Decay Parameter: New or old. Newer posts tend to hold a higher place than older posts. Some of the methods that Facebook uses to adjust the parameters are proprietary and not available to the public. A study has shown that it is possible to hypothesize a disadvantage of the "like" reaction and advantages of other interactions (e.g., the "haha" reaction or "comments") in content algorithmic ranking on Facebook. The "like" button can decrease the organic reach as a "brake effect of viral reach". The "haha" reaction, "comments" and the "love" reaction could achieve the highest increase in total organic reach. == Impact == EdgeRank and its successors have a broad impact on what users actually see out of what they ostensibly follow: for instance, the selection can produce a filter bubble (if users are exposed to updates which confirm their opinions etc.) or alter people's mood (if users are shown a disproportionate amount of positive or negative updates). As a result, for Facebook pages, the typical engagement rate is less than 1% (or less than 0.1% for the bigger ones), and organic reach 10% or less for most non-profits. As a consequence, for pages, it may be nearly impossible to reach any significant audience without paying to promote their content.

  Read more →
• 

  Shepp–Logan phantom

  The Shepp–Logan phantom is a standard test image created by Larry Shepp and Benjamin F. Logan for their 1974 paper "The Fourier Reconstruction of a Head Section". It serves as the model of a human head in the development and testing of image reconstruction algorithms. == Definition == The function describing the phantom is defined as the sum of 10 ellipses inside a 2×2 square:

  Read more →
• 

  Time Warp Edit Distance

  In the data analysis of time series, Time Warp Edit Distance (TWED) is a measure of similarity (or dissimilarity) between pairs of discrete time series, controlling the relative distortion of the time units of the two series using the physical notion of elasticity. In comparison to other distance measures, (e.g. DTW (dynamic time warping) or LCS (longest common subsequence problem)), TWED is a metric. Its computational time complexity is O ( n 2 ) {\displaystyle O(n^{2})} , but can be drastically reduced in some specific situations by using a corridor to reduce the search space. Its memory space complexity can be reduced to O ( n ) {\displaystyle O(n)} . It was first proposed in 2009 by P.-F. Marteau. == Definition == δ λ , ν ( A 1 p , B 1 q ) = M i n { δ λ , ν ( A 1 p − 1 , B 1 q ) + Γ ( a p ′ → Λ ) d e l e t e i n A δ λ , ν ( A 1 p − 1 , B 1 q − 1 ) + Γ ( a p ′ → b q ′ ) m a t c h o r s u b s t i t u t i o n δ λ , ν ( A 1 p , B 1 q − 1 ) + Γ ( Λ → b q ′ ) d e l e t e i n B {\displaystyle \delta _{\lambda ,\nu }(A_{1}^{p},B_{1}^{q})=Min{\begin{cases}\delta _{\lambda ,\nu }(A_{1}^{p-1},B_{1}^{q})+\Gamma (a_{p}^{'}\to \Lambda )&{\rm {delete\ in\ A}}\\\delta _{\lambda ,\nu }(A_{1}^{p-1},B_{1}^{q-1})+\Gamma (a_{p}^{'}\to b_{q}^{'})&{\rm {match\ or\ substitution}}\\\delta _{\lambda ,\nu }(A_{1}^{p},B_{1}^{q-1})+\Gamma (\Lambda \to b_{q}^{'})&{\rm {delete\ in\ B}}\end{cases}}} whereas Γ ( α p ′ → Λ ) = d L P ( a p ′ , a p − 1 ′ ) + ν ⋅ ( t a p − t a p − 1 ) + λ {\displaystyle \Gamma (\alpha _{p}^{'}\to \Lambda )=d_{LP}(a_{p}^{'},a_{p-1}^{'})+\nu \cdot (t_{a_{p}}-t_{a_{p-1}})+\lambda } Γ ( α p ′ → b q ′ ) = d L P ( a p ′ , b q ′ ) + d L P ( a p − 1 ′ , b q − 1 ′ ) + ν ⋅ ( | t a p − t b q | + | t a p − 1 − t b q − 1 | ) {\displaystyle \Gamma (\alpha _{p}^{'}\to b_{q}^{'})=d_{LP}(a_{p}^{'},b_{q}^{'})+d_{LP}(a_{p-1}^{'},b_{q-1}^{'})+\nu \cdot (|t_{a_{p}}-t_{b_{q}}|+|t_{a_{p-1}}-t_{b_{q-1}}|)} Γ ( Λ → b q ′ ) = d L P ( b p ′ , b p − 1 ′ ) + ν ⋅ ( t b q − t b q − 1 ) + λ {\displaystyle \Gamma (\Lambda \to b_{q}^{'})=d_{LP}(b_{p}^{'},b_{p-1}^{'})+\nu \cdot (t_{b_{q}}-t_{b_{q-1}})+\lambda } Whereas the recursion δ λ , ν {\displaystyle \delta _{\lambda ,\nu }} is initialized as: δ λ , ν ( A 1 0 , B 1 0 ) = 0 , {\displaystyle \delta _{\lambda ,\nu }(A_{1}^{0},B_{1}^{0})=0,} δ λ , ν ( A 1 0 , B 1 j ) = ∞ f o r j ≥ 1 {\displaystyle \delta _{\lambda ,\nu }(A_{1}^{0},B_{1}^{j})=\infty \ {\rm {{for\ }j\geq 1}}} δ λ , ν ( A 1 i , B 1 0 ) = ∞ f o r i ≥ 1 {\displaystyle \delta _{\lambda ,\nu }(A_{1}^{i},B_{1}^{0})=\infty \ {\rm {{for\ }i\geq 1}}} with a 0 ′ = b 0 ′ = 0 {\displaystyle a'_{0}=b'_{0}=0} === Implementations === An implementation of the TWED algorithm in C with a Python wrapper is available at TWED is also implemented into the Time Series Subsequence Search Python package (TSSEARCH for short) available at [1]. An R implementation of TWED has been integrated into the TraMineR, a R package for mining, describing and visualizing sequences of states or events, and more generally discrete sequence data. Additionally, cuTWED is a CUDA- accelerated implementation of TWED which uses an improved algorithm due to G. Wright (2020). This method is linear in memory and massively parallelized. cuTWED is written in CUDA C/C++, comes with Python bindings, and also includes Python bindings for Marteau's reference C implementation. ==== Python ==== Backtracking, to find the most cost-efficient path: ==== MATLAB ==== Backtracking, to find the most cost-efficient path:

  Read more →
• 

  Outline of artificial intelligence

  The following outline is provided as an overview of and topical guide to artificial intelligence: Artificial intelligence (AI) is intelligence exhibited by machines or software. It is also the name of the scientific field which studies how to create computers and computer software that are capable of intelligent behavior. == AI terminology == Glossary of artificial intelligence == Goals and applications == === General intelligence === Artificial general intelligence AI-complete === Reasoning and problem solving === Automated reasoning Mathematics Automated theorem prover Computer-assisted proof – Computer algebra General Problem Solver Expert system – Decision support system – Clinical decision support system – === Knowledge representation === Knowledge representation Knowledge management Cyc === Planning === Automated planning and scheduling Strategic planning Sussman anomaly – === Learning === Machine learning – Constrained Conditional Models – Deep learning – Neural modeling fields – Supervised learning – Weak supervision (semi-supervised learning) – Unsupervised learning – === Natural language processing === Natural language processing (outline) – Chatterbots – Language identification – Large language model – Retrieval-augmented generation – Natural language user interface – Natural language understanding – Machine translation – Statistical semantics – Question answering – Semantic translation – Concept mining – Data mining – Text mining – Process mining – E-mail spam filtering – Information extraction – Named-entity extraction – Coreference resolution – Named-entity recognition – Relationship extraction – Terminology extraction – === Perception === Machine perception Pattern recognition – Computer Audition – Speech recognition – Speaker recognition – Computer vision (outline) – Image processing Intelligent word recognition – Object recognition – Optical mark recognition – Handwriting recognition – Optical character recognition – Automatic number plate recognition – Information extraction – Image retrieval – Automatic image annotation – Facial recognition systems – Silent speech interface – Activity recognition – Percept (artificial intelligence) === Robotics === Robotics – Behavior-based robotics – Cognitive – Cybernetics – Developmental robotics – Evolutionary robotics – === Control === Intelligent control Self-management (computer science) – Autonomic Computing – Autonomic Networking – === Social intelligence === Affective computing Kismet === Game playing === Game artificial intelligence – Computer game bot – computer replacement for human players. Video game AI – Computer chess – Computer Go – General game playing – General video game playing – === Creativity, art and entertainment === Artificial creativity Artificial life Artificial intelligence art AI anthropomorphism AI agent AI web browser AI boom AI slop Creative computing Generative artificial intelligence Generative pre trained transformer Uncanny valley Music and artificial intelligence Computational humor Chatbot === Integrated AI systems === AIBO – Sony's robot dog. It integrates vision, hearing and motorskills. Asimo (2000 to present) – humanoid robot developed by Honda, capable of walking, running, negotiating through pedestrian traffic, climbing and descending stairs, recognizing speech commands and the faces of specific individuals, among a growing set of capabilities. MIRAGE – A.I. embodied humanoid in an augmented reality environment. Cog – M.I.T. humanoid robot project under the direction of Rodney Brooks. QRIO – Sony's version of a humanoid robot. TOPIO, TOSY's humanoid robot that can play ping-pong with humans. Watson (2011) – computer developed by IBM that played and won the game show Jeopardy! It is now being used to guide nurses in medical procedures. Purpose: Open domain question answering Technologies employed: Natural language processing Information retrieval Knowledge representation Automated reasoning Machine learning Project Debater (2018) – artificially intelligent computer system, designed to make coherent arguments, developed at IBM's lab in Haifa, Israel. === Intelligent personal assistants === Intelligent personal assistant – Amazon Alexa – Assistant – Braina – Cortana – Google Assistant – Google Now – Mycroft – Siri – Viv – === Other applications === Artificial life – simulation of natural life through the means of computers, robotics, or biochemistry. Automatic target recognition – Diagnosis (artificial intelligence) – Speech generating device – Vehicle infrastructure integration – Virtual Intelligence – == History == History of artificial intelligence Progress in artificial intelligence Timeline of artificial intelligence AI effect – as soon as AI successfully solves a problem, the problem is no longer considered by the public to be a part of AI. This phenomenon has occurred in relation to every AI application produced, so far, throughout the history of development of AI. AI winter – a period of disappointment and funding reductions occurring after a wave of high expectations and funding in AI. Such funding cuts occurred in the 1970s, for instance. Moore's law === History by period === 2017 in artificial intelligence 2018 in artificial intelligence 2019 in artificial intelligence 2020 in artificial intelligence 2021 in artificial intelligence 2022 in artificial intelligence 2023 in artificial intelligence 2024 in artificial intelligence 2025 in artificial intelligence 2026 in artificial intelligence 2027 in artificial intelligence 2028 in artificial intelligence 2029 in artificial intelligence === History by subject === History of logic (formal reasoning is an important precursor of AI) History of machine learning (timeline) History of machine translation (timeline) History of natural language processing History of optical character recognition (timeline) == AI algorithms and techniques == === Search === Discrete search algorithms Uninformed search Brute force search – Problem-solving technique and algorithmic paradigmPages displaying short descriptions of redirect targets Search tree – Data structure in tree form sorted for fast lookup Breadth-first search – Algorithm to search the nodes of a graph Depth-first search – Algorithm to search the nodes of a graph State space search – Class of search algorithmsPages displaying short descriptions of redirect targets Informed search Best-first search – Graph exploring search algorithm A search algorithm – Algorithm used for pathfinding and graph traversal Heuristics – Problem-solving methodPages displaying short descriptions of redirect targets Pruning (algorithm) – Data compression techniquePages displaying short descriptions of redirect targets Adversarial search Minmax algorithm – Decision rule used for minimizing the possible loss for a worst-case scenarioPages displaying short descriptions of redirect targets Logic as search Production system (computer science) – Computer program used to provide artificial intelligence Rule based system – Type of computer systemPages displaying short descriptions of redirect targets Production rule – Computer program used to provide artificial intelligence Inference rule – Method of deriving conclusionsPages displaying short descriptions of redirect targets Horn clause – Type of logical formula Forward chaining – Inference engine in an expert system Backward chaining – Method of forming inferences Planning as search State space search – Class of search algorithmsPages displaying short descriptions of redirect targets Means–ends analysis – Problem solving technique === Optimization search === Optimization (mathematics) algorithms Hill climbing – Optimization algorithm Simulated annealing – Probabilistic optimization technique and metaheuristic Beam search – Heuristic search algorithm Random optimization – Optimization technique in mathematics Evolutionary computation Genetic algorithms – Competitive algorithm for searching a problem spacePages displaying short descriptions of redirect targets Gene expression programming – Evolutionary algorithm Genetic programming – Evolving computer programs with techniques analogous to natural genetic processes Differential evolution – Method of mathematical optimization Society based learning algorithms. Swarm intelligence – Collective behavior of decentralized, self-organized systems Particle swarm optimization – Iterative simulation method Ant colony optimization – Optimization algorithmPages displaying short descriptions of redirect targets Metaheuristic – Optimization technique === Logic === Logic and automated reasoning Programming using logic Logic programming – Programming paradigm based on formal logic See "Logic as search" above. Forms of Logic Propositional logic First-order logic First-order logic with equality Constraint satisfaction – Process in artificial intelligence and operations research Fuzzy logic Fuzzy set theory – Sets whose elements have degrees of membershipPages displaying short descriptions

  Read more →
• 

  Conceptions of Library and Information Science

  Conceptions of Library and Information Science (CoLIS) is a series of conferences about historical, empirical and theoretical perspectives in Library and Information Science. == CoLIS conferences == CoLIS 1 1991 in Tampere, Finland CoLIS 2 1996 in Copenhagen, Denmark CoLIS 3 1999 in Dubrovnik, Croatia CoLIS 4 2002 in Seattle, US CoLIS 5 2005 in Glasgow, Scotland CoLIS 6 2007 in Borås, Sweden CoLIS 7 June 2010 in London, at City University London. CoLIS 8 August 19–22, 2013, in Copenhagen, Denmark, at The Royal School of Library and Information Science. CoLIS 9 June 27–29, 2016, in Uppsala, Sweden, at Uppsala University. CoLIS 10 June 16–19, 2019, in Ljubljana, Slovenia, Faculty of Arts CoLIS 11 May 29–June 1, 2022, in Oslo, Norway, Oslo Metropolitan University.

  Read more →
• 

  EffectsLab Pro

  EffectsLab Pro is a discontinued visual effects software product developed by FXhome. It has since been superseded by the FXhome HitFilm range. The company also produced a limited functionality version, EffectsLab Lite, containing just the Particle engine. A more extensive product, VisionLab Studio, combined the functionality of EffectsLab Pro and the company's CompositeLab Pro product with enhancements to both. == Effects Engines == The effects are generated by the program's effect engines: The Neon Light engine allows light beams to be drawn onto the video, allowing the generation of lightsaber-like weapons, neon lighting, fantasy glow effects and laser blasts. The Particle engine is used for particle effects, such as smoke, fire, explosions, and weather effects. The Muzzle Flash engine is designed for creating and animating muzzle flashes such as machine gun firing, tank blasts, etc. It's possible to rotate the created muzzle flash in 3D, making it the only engine with 3D use. The Optics engine is designed for creating artificial lens flares and light sources. It is useful for enhancing other light-based effects, and mimicking the distinctive flashes of light that accompany Star Wars' lightsaber battles. The Laser engine (introduced in EffectsLab Pro in late 2007) is designed as a simplified method of creating laser weapon effects, including the ability to add simulated perspective to the effect. == Presets == EffectsLab Pro allows the user to save the effects using presets. Since all effects are generated from settings in the different engines, it is fairly easy to generate an XML style description of the effect. It is also possible to share presets on FXhome's website.

  Read more →
• 

  Vector-field consistency

  Vector-Field Consistency is a consistency model for replicated data (for example, objects), initially described in a paper which was awarded the best-paper prize in the ACM/IFIP/Usenix Middleware Conference 2007. It has since been enhanced for increased scalability and fault-tolerance in a recent paper. == Description == This consistency model was initially designed for replicated data management in ad hoc gaming in order to minimize bandwidth usage without sacrificing playability. Intuitively, it captures the notion that although players require, wish, and take advantage of information regarding the whole of the game world (as opposed to a restricted view to rooms, arenas, etc. of limited size employed in many multiplayer video games), they need to know information with greater freshness, frequency, and accuracy as other game entities are located closer and closer to the player's position. It prescribes a multidimensional divergence bounding scheme, based on a vector field that employs consistency vectors k=(θ,σ,ν), standing for maximum allowed time - or replica staleness, sequence - or missing updates, and value - or user-defined measured replica divergence, applied to all space coordinates in game scenario or world. The consistency vector-fields emanate from field-generators designated as pivots (for example, players) and field intensity attenuates as distance grows from these pivots in concentric or square-like regions. This consistency model unifies locality-awareness techniques employed in message routing and consistency enforcement for multiplayer games, with divergence bounding techniques traditionally employed in replicated database and web scenarios.

  Read more →
• 

  Wearable computer

  A wearable computer, also known as a body-borne computer or wearable, is a computing device worn on the body. The definition of 'wearable computer' may be narrow or broad, extending to smartphones or even ordinary wristwatches. Wearables may be for general use, in which case they are just a particularly small example of mobile computing. Alternatively, they may be for specialized purposes such as fitness trackers. They may incorporate special sensors such as accelerometers, heart rate monitors, or on the more advanced side, electrocardiogram (ECG) and blood oxygen saturation (SpO2) monitors. Under the definition of wearable computers, we also include novel user interfaces such as Google Glass, an optical head-mounted display controlled by gestures. It may be that specialized wearables will evolve into general all-in-one devices, as happened with the convergence of PDAs and mobile phones into smartphones. Wearables are typically worn on the wrist (e.g. fitness trackers), hung from the neck (like a necklace), strapped to the arm or leg (electronic tagging), or on the head (as glasses or a helmet), though some have been located elsewhere (e.g. on a finger or in a shoe). Devices carried in a pocket or bag – such as smartphones and before them, pocket calculators and PDAs, may or may not be regarded as 'worn'. Wearable computers have various technical issues common to other mobile computing, such as batteries, heat dissipation, software architectures, wireless and personal area networks, and data management. Many wearable computers are active all the time, e.g. processing or recording data continuously. == Applications == Wearable computers are not only limited to computers such as fitness trackers that are worn on wrists; they also include wearables such as heart pacemakers and other prosthetics. They are used most often in research that focuses on behavioral modeling, health monitoring systems, IT and media development, where the person wearing the computer actually moves or is otherwise engaged with his or her surroundings. Wearable computers have been used for the following: general-purpose computing (e.g. smartphones and smartwatches) sensory integration, e.g. to help people see better or understand the world better (whether in task-specific applications like camera-based welding helmets or for everyday use like Google Glass) behavioral modeling health care monitoring systems service management electronic textiles and fashion design, e.g. Microsoft's 2011 prototype "The Printing Dress". Wearable computing is the subject of active research, especially the form-factor and location on the body, with areas of study including user interface design, augmented reality, and pattern recognition. The use of wearables for specific applications, for compensating disabilities or supporting elderly people steadily increases. == Operating systems == The dominant operating systems for wearable computing are: FreeRTOS is a real-time operating system kernel for embedded devices; most of the Smartbands that are currently available in the market are based on FreeRTOS, which include Huawei, Honor, Lenovo, realme, TCL and Xiaomi smartbands. LiteOS is a lightweight open source real-time operating system that is part of Huawei's "1+8+N" Internet of Things solution. Tizen OS from Samsung (there was an announcement in May 2021 that Wear OS and Tizen OS will merge and will be called simply Wear.) watchOS watchOS is a proprietary mobile operating system developed by Apple Inc. to run on the Apple Watch. Wear OS Wear OS (previously known as Android Wear) is a smartwatch operating system developed by Google Inc. == History == Due to the varied definitions of wearable and computer, the first wearable computer could be as early as the first abacus on a necklace, a 16th-century abacus ring, a wristwatch and 'finger-watch' owned by Queen Elizabeth I of England, or the covert timing devices hidden in shoes to cheat at roulette by Thorp and Shannon in the 1960s and 1970s. However, a general-purpose computer is not merely a time-keeping or calculating device, but rather a user-programmable item for arbitrary complex algorithms, interfacing, and data management. By this definition, the wearable computer was invented by Steve Mann, in the late 1970s: Steve Mann, a professor at the University of Toronto, was hailed as the father of the wearable computer and the ISSCC's first virtual panelist, by moderator Woodward Yang of Harvard University (Cambridge Mass.). The development of wearable items has taken several steps of miniaturization from discrete electronics over hybrid designs to fully integrated designs, where just one processor chip, a battery, and some interface conditioning items make the whole unit. === 1500s === Queen Elizabeth I of England received a watch from Robert Dudley in 1571, as a New Year's present; it may have been worn on the forearm rather than the wrist. She also possessed a 'finger-watch' set in a ring, with an alarm that prodded her finger. === 1600s === The Qing dynasty saw the introduction of a fully functional abacus on a ring, which could be used while it was being worn. === 1960s === In 1961, mathematicians Edward O. Thorp and Claude Shannon built some computerized timing devices to help them win a game of roulette. One such timer was concealed in a shoe and another in a pack of cigarettes. Various versions of this apparatus were built in the 1960s and 1970s. Thorp refers to himself as the inventor of the first "wearable computer". In other variations, the system was a concealed cigarette-pack-sized analog computer designed to predict the motion of roulette wheels. A data-taker would use microswitches hidden in his shoes to indicate the speed of the roulette wheel, and the computer would indicate an octant of the roulette wheel to bet on by sending musical tones via radio to a miniature speaker hidden in a collaborator's ear canal. The system was successfully tested in Las Vegas in June 1961, but hardware issues with the speaker wires prevented it from being used beyond test runs. This was not a wearable computer because it could not be re-purposed during use; rather it was an example of task-specific hardware. This work was kept secret until it was first mentioned in Thorp's book Beat the Dealer (revised ed.) in 1966 and later published in detail in 1969. === 1970s === Pocket calculators became mass-market devices in 1970, starting in Japan. Programmable calculators followed in the late 1970s, being somewhat more general-purpose computers. The HP-01 algebraic calculator watch by Hewlett-Packard was released in 1977. A camera-to-tactile vest for the blind, launched by C.C. Collins in 1977, converted images into a 1024-point, ten-inch square tactile grid on a vest. === 1980s === The 1980s saw the rise of more general-purpose wearable computers. In 1981, Steve Mann designed and built a backpack-mounted 6502-based wearable multimedia computer with text, graphics, and multimedia capability, as well as video capability (cameras and other photographic systems). Mann went on to be an early and active researcher in the wearables field, especially known for his 1994 creation of the Wearable Wireless Webcam, the first example of lifelogging. Seiko Epson released the RC-20 Wrist Computer in 1984. It was an early smartwatch, powered by a computer on a chip. In 1989, Reflection Technology marketed the Private Eye head-mounted display, which scans a vertical array of LEDs across the visual field using a vibrating mirror. This display gave rise to several hobbyist and research wearables, including Gerald "Chip" Maguire's IBM/Columbia University Student Electronic Notebook, Doug Platt's Hip-PC, and Carnegie Mellon University's VuMan 1 in 1991. The Student Electronic Notebook consisted of the Private Eye, Toshiba diskless AIX notebook computers (prototypes), a stylus based input system and a virtual keyboard. It used direct-sequence spread spectrum radio links to provide all the usual TCP/IP based services, including NFS mounted file systems and X11, which all ran in the Andrew Project environment. The Hip-PC included an Agenda palmtop used as a chording keyboard attached to the belt and a 1.44 megabyte floppy drive. Later versions incorporated additional equipment from Park Engineering. The system debuted at "The Lap and Palmtop Expo" on 16 April 1991. VuMan 1 was developed as part of a Summer-term course at Carnegie Mellon's Engineering Design Research Center, and was intended for viewing house blueprints. Input was through a three-button unit worn on the belt, and output was through Reflection Tech's Private Eye. The CPU was an 8 MHz 80188 processor with 0.5 MB ROM. === 1990s === In the 1990s PDAs became widely used, and in 1999 were combined with mobile phones in Japan to produce the first mass-market smartphone. In 1993, the Private Eye was used in Thad Starner's wearable, based on Doug Platt's system and built from a kit from Park Enterprises, a Pri

  Read more →
• 

  Small Data

  Small Data: the Tiny Clues that Uncover Huge Trends is Martin Lindstrom's seventh book. It chronicles his work as a branding expert, working with consumers across the world to better understand their behavior. The theory behind the book is that businesses can better create products and services based on observing consumer behavior in their homes, as opposed to relying solely on big data. == Content == The book is based on a several year period of consumer studies for major corporations across the globe. It features case studies of the author's work interviewing consumers in their homes and using his observations to create hypotheses as to why they use products the way that they do. == Public reception == The book was a New York Times Bestseller upon release and was positively reviewed on several websites, Including Entrepreneur and Forbes. In 2016, it was named a Best Business Book by strategy+business and one of Inc. Magazine's Best Sales and Marketing books.

  Read more →
• 

  Neural network Gaussian process

  A Neural Network Gaussian Process (NNGP) is a Gaussian process (GP) obtained as the limit of a certain type of sequence of neural networks. Specifically, a wide variety of network architectures converges to a GP in the infinitely wide limit, in the sense of distribution. The concept constitutes an intensional definition, i.e., a NNGP is just a GP, but distinguished by how it is obtained. == Motivation == Bayesian networks are a modeling tool for assigning probabilities to events, and thereby characterizing the uncertainty in a model's predictions. Deep learning and artificial neural networks are approaches used in machine learning to build computational models which learn from training examples. Bayesian neural networks merge these fields. They are a type of neural network whose parameters and predictions are both probabilistic. While standard neural networks often assign high confidence even to incorrect predictions, Bayesian neural networks can more accurately evaluate how likely their predictions are to be correct. Computation in artificial neural networks is usually organized into sequential layers of artificial neurons. The number of neurons in a layer is called the layer width. When we consider a sequence of Bayesian neural networks with increasingly wide layers (see figure), they converge in distribution to a NNGP. This large width limit is of practical interest, since the networks often improve as layers get wider. And the process may give a closed form way to evaluate networks. NNGPs also appears in several other contexts: It describes the distribution over predictions made by wide non-Bayesian artificial neural networks after random initialization of their parameters, but before training; it appears as a term in neural tangent kernel prediction equations; it is used in deep information propagation to characterize whether hyperparameters and architectures will be trainable. It is related to other large width limits of neural networks. === Scope === The first correspondence result had been established in the 1995 PhD thesis of Radford M. Neal, then supervised by Geoffrey Hinton at University of Toronto. Neal cites David J. C. MacKay as inspiration, who worked in Bayesian learning. Today the correspondence is proven for: Single hidden layer Bayesian neural networks; deep fully connected networks as the number of units per layer is taken to infinity; convolutional neural networks as the number of channels is taken to infinity; transformer networks as the number of attention heads is taken to infinity; recurrent networks as the number of units is taken to infinity. In fact, this NNGP correspondence holds for almost any architecture: Generally, if an architecture can be expressed solely via matrix multiplication and coordinatewise nonlinearities (i.e., a tensor program), then it has an infinite-width GP. This in particular includes all feedforward or recurrent neural networks composed of multilayer perceptron, recurrent neural networks (e.g., LSTMs, GRUs), (nD or graph) convolution, pooling, skip connection, attention, batch normalization, and/or layer normalization. === Illustration === Every setting of a neural network's parameters θ {\displaystyle \theta } corresponds to a specific function computed by the neural network. A prior distribution p ( θ ) {\displaystyle p(\theta )} over neural network parameters therefore corresponds to a prior distribution over functions computed by the network. As neural networks are made infinitely wide, this distribution over functions converges to a Gaussian process for many architectures. The notation used in this section is the same as the notation used below to derive the correspondence between NNGPs and fully connected networks, and more details can be found there. The figure to the right plots the one-dimensional outputs z L ( ⋅ ; θ ) {\displaystyle z^{L}(\cdot ;\theta )} of a neural network for two inputs x {\displaystyle x} and x ∗ {\displaystyle x^{}} against each other. The black dots show the function computed by the neural network on these inputs for random draws of the parameters from p ( θ ) {\displaystyle p(\theta )} . The red lines are iso-probability contours for the joint distribution over network outputs z L ( x ; θ ) {\displaystyle z^{L}(x;\theta )} and z L ( x ∗ ; θ ) {\displaystyle z^{L}(x^{};\theta )} induced by p ( θ ) {\displaystyle p(\theta )} . This is the distribution in function space corresponding to the distribution p ( θ ) {\displaystyle p(\theta )} in parameter space, and the black dots are samples from this distribution. For infinitely wide neural networks, since the distribution over functions computed by the neural network is a Gaussian process, the joint distribution over network outputs is a multivariate Gaussian for any finite set of network inputs. == Discussion == === Infinitely wide fully connected network === This section expands on the correspondence between infinitely wide neural networks and Gaussian processes for the specific case of a fully connected architecture. It provides a proof sketch outlining why the correspondence holds, and introduces the specific functional form of the NNGP for fully connected networks. The proof sketch closely follows the approach by Novak and coauthors. ==== Network architecture specification ==== Consider a fully connected artificial neural network with inputs x {\displaystyle x} , parameters θ {\displaystyle \theta } consisting of weights W l {\displaystyle W^{l}} and biases b l {\displaystyle b^{l}} for each layer l {\displaystyle l} in the network, pre-activations (pre-nonlinearity) z l {\displaystyle z^{l}} , activations (post-nonlinearity) y l {\displaystyle y^{l}} , pointwise nonlinearity ϕ ( ⋅ ) {\displaystyle \phi (\cdot )} , and layer widths n l {\displaystyle n^{l}} . For simplicity, the width n L + 1 {\displaystyle n^{L+1}} of the readout vector z L {\displaystyle z^{L}} is taken to be 1. The parameters of this network have a prior distribution p ( θ ) {\displaystyle p(\theta )} , which consists of an isotropic Gaussian for each weight and bias, with the variance of the weights scaled inversely with layer width. This network is illustrated in the figure to the right, and described by the following set of equations: x ≡ input y l ( x ) = { x l = 0 ϕ ( z l − 1 ( x ) ) l > 0 z i l ( x ) = ∑ j W i j l y j l ( x ) + b i l W i j l ∼ N ( 0 , σ w 2 n l ) b i l ∼ N ( 0 , σ b 2 ) ϕ ( ⋅ ) ≡ nonlinearity y l ( x ) , z l − 1 ( x ) ∈ R n l × 1 n L + 1 = 1 θ = { W 0 , b 0 , … , W L , b L } {\displaystyle {\begin{aligned}x&\equiv {\text{input}}\\y^{l}(x)&=\left\{{\begin{array}{lcl}x&&l=0\\\phi \left(z^{l-1}(x)\right)&&l>0\end{array}}\right.\\z_{i}^{l}(x)&=\sum _{j}W_{ij}^{l}y_{j}^{l}(x)+b_{i}^{l}\\W_{ij}^{l}&\sim {\mathcal {N}}\left(0,{\frac {\sigma _{w}^{2}}{n^{l}}}\right)\\b_{i}^{l}&\sim {\mathcal {N}}\left(0,\sigma _{b}^{2}\right)\\\phi (\cdot )&\equiv {\text{nonlinearity}}\\y^{l}(x),z^{l-1}(x)&\in \mathbb {R} ^{n^{l}\times 1}\\n^{L+1}&=1\\\theta &=\left\{W^{0},b^{0},\dots ,W^{L},b^{L}\right\}\end{aligned}}} ==== ==== z l | y l {\displaystyle z^{l}|y^{l}} is a Gaussian process We first observe that the pre-activations z l {\displaystyle z^{l}} are described by a Gaussian process conditioned on the preceding activations y l {\displaystyle y^{l}} . This result holds even at finite width. Each pre-activation z i l {\displaystyle z_{i}^{l}} is a weighted sum of Gaussian random variables, corresponding to the weights W i j l {\displaystyle W_{ij}^{l}} and biases b i l {\displaystyle b_{i}^{l}} , where the coefficients for each of those Gaussian variables are the preceding activations y j l {\displaystyle y_{j}^{l}} . Because they are a weighted sum of zero-mean Gaussians, the z i l {\displaystyle z_{i}^{l}} are themselves zero-mean Gaussians (conditioned on the coefficients y j l {\displaystyle y_{j}^{l}} ). Since the z l {\displaystyle z^{l}} are jointly Gaussian for any set of y l {\displaystyle y^{l}} , they are described by a Gaussian process conditioned on the preceding activations y l {\displaystyle y^{l}} . The covariance or kernel of this Gaussian process depends on the weight and bias variances σ w 2 {\displaystyle \sigma _{w}^{2}} and σ b 2 {\displaystyle \sigma _{b}^{2}} , as well as the second moment matrix K l {\displaystyle K^{l}} of the preceding activations y l {\displaystyle y^{l}} , z i l ∣ y l ∼ G P ( 0 , σ w 2 K l + σ b 2 ) K l ( x , x ′ ) = 1 n l ∑ i y i l ( x ) y i l ( x ′ ) {\displaystyle {\begin{aligned}z_{i}^{l}\mid y^{l}&\sim {\mathcal {GP}}\left(0,\sigma _{w}^{2}K^{l}+\sigma _{b}^{2}\right)\\K^{l}(x,x')&={\frac {1}{n^{l}}}\sum _{i}y_{i}^{l}(x)y_{i}^{l}(x')\end{aligned}}} The effect of the weight scale σ w 2 {\displaystyle \sigma _{w}^{2}} is to rescale the contribution to the covariance matrix from K l {\displaystyle K^{l}} , while the bias is shared for all inputs, and so σ b 2 {\displaystyle \sigma _{b}^{2}} makes the z i l {\displaystyle z_{i}^{l}} for different datapoints more similar and

  Read more →
• 

  Information history

  Information history may refer to the history of each of the categories listed below (or to combinations of them). It should be recognized that the understanding of, for example, libraries as information systems only goes back to about 1950. The application of the term information for earlier systems or societies is a retronym. == Academic discipline == Information history is an emerging discipline related to, but broader than, library history. An important introduction and review was made by Alistair Black (2006). A prolific scholar in this field is also Toni Weller, for example, Weller (2007, 2008, 2010a and 2010b). As part of her work Toni Weller has argued that there are important links between the modern information age and its historical precedents. A description from Russia is Volodin (2000). Alistair Black (2006, p. 445) wrote: "This chapter explores issues of discipline definition and legitimacy by segmenting information history into its various components: The history of print and written culture, including relatively long-established areas such as the histories of libraries and librarianship, book history, publishing history, and the history of reading. The history of more recent information disciplines and practice, that is to say, the history of information management, information systems, and information science. The history of contiguous areas, such as the history of the information society and information infrastructure, necessarily enveloping communication history (including telecommunications history) and the history of information policy. The history of information as social history, with emphasis on the importance of informal information networks." "Bodies influential in the field include the American Library Association’s Round Table on Library History, the Library History Section of the International Federation of Library Associations and Institutions (IFLA), and, in the U.K., the Library and Information History Group of the Chartered Institute of Library and Information Professionals (CILIP). Each of these bodies has been busy in recent years, running conferences and seminars, and initiating scholarly projects. Active library history groups function in many other countries, including Germany (The Wolfenbuttel Round Table on Library History, the History of the Book and the History of Media, located at the Herzog August Bibliothek), Denmark (The Danish Society for Library History, located at the Royal School of Library and Information Science), Finland (The Library History Research Group, University of Tamepere), and Norway (The Norwegian Society for Book and Library History). Sweden has no official group dedicated to the subject, but interest is generated by the existence of a museum of librarianship in Bods, established by the Library Museum Society and directed by Magnus Torstensson. Activity in Argentina, where, as in Europe and the U.S., a "new library history" has developed, is described by Parada (2004)." (Black (2006, p. 447). === Journals === Information & Culture (previously Libraries & the Cultural Record, Libraries & Culture) Library & Information History (until 2008: Library History; until 1967: Library Association. Library History Group. Newsletter) == Information technology (IT) == The term IT is ambiguous although mostly synonym with computer technology. Haigh (2011, pp. 432-433) wrote "In fact, the great majority of references to information technology have always been concerned with computers, although the exact meaning has shifted over time (Kline, 2006). The phrase received its first prominent usage in a Harvard Business Review article (Haigh, 2001b; Leavitt & Whisler, 1958) intended to promote a technocratic vision for the future of business management. Its initial definition was at the conjunction of computers, operations research methods, and simulation techniques. Having failed initially to gain much traction (unlike related terms of a similar vintage such as information systems, information processing, and information science) it was revived in policy and economic circles in the 1970s with a new meaning. Information technology now described the expected convergence of the computing, media, and telecommunications industries (and their technologies), understood within the broader context of a wave of enthusiasm for the computer revolution, post-industrial society, information society (Webster, 1995), and other fashionable expressions of the belief that new electronic technologies were bringing a profound rupture with the past. As it spread broadly during the 1980s, IT increasingly lost its association with communications (and, alas, any vestigial connection to the idea of anybody actually being informed of anything) to become a new and more pretentious way of saying "computer". The final step in this process is the recent surge in references to "information and communication technologies" or ICTs, a coinage that makes sense only if one assumes that a technology can inform without communicating". Some people use the term information technology about technologies used before the development of the computer. This is however to use the term as a retronym. =

  Read more →
• 

  Sieve of Pritchard

  In mathematics, the sieve of Pritchard is an algorithm for finding all prime numbers up to a specified bound. Like the ancient sieve of Eratosthenes, it has a simple conceptual basis in number theory. It is especially suited to quick hand computation for small bounds. Whereas the sieve of Eratosthenes marks off each non-prime for each of its prime factors, the sieve of Pritchard avoids considering almost all non-prime numbers by building progressively larger wheels, which represent the pattern of numbers not divisible by any of the primes processed thus far. It thereby achieves a better asymptotic complexity, and was the first sieve with a running time sublinear in the specified bound. Its asymptotic running-time has not been improved on, and it deletes fewer composites than any other known sieve. It was created in 1979 by Paul Pritchard. Since Pritchard has created a number of other sieve algorithms for finding prime numbers, the sieve of Pritchard is sometimes singled out by being called the wheel sieve (by Pritchard himself) or the dynamic wheel sieve. == Overview == A prime number is a natural number that has no natural number divisors other than the number 1 and itself. To find all the prime numbers less than or equal to a given integer N, a sieve algorithm examines a set of candidates in the range 2, 3, …, N, and eliminates those that are not prime, leaving the primes at the end. The sieve of Eratosthenes examines all of the range, first removing all multiples of the first prime 2, then of the next prime 3, and so on. The sieve of Pritchard instead examines a subset of the range consisting of numbers that occur on successive wheels, which represent the pattern of numbers left after each successive prime is processed by the sieve of Eratosthenes. For i > 0, the ith wheel Wi represents this pattern. It is the set of numbers between 1 and the product Pi = p1 · p2 ⋯ pi of the first i prime numbers that are not divisible by any of these prime numbers (and is said to have an associated length Pi). This is because adding Pi to a number does not change whether it is divisible by one of the first i prime numbers, since the remainder on division by any one of these primes is unchanged. So W1 = {1} with length P1 = 2 represents the pattern of odd numbers; W2 = {1,5} with length P2 = 6 represents the pattern of numbers not divisible by 2 or 3; etc. Wheels are so-called because Wi can be usefully visualized as a circle of circumference Pi with its members marked at their corresponding distances from an origin. Then rolling the wheel along the number line marks points corresponding to successive numbers not divisible by one of the first i prime numbers. The animation shows W2 being rolled up to 30. It is useful to define Wi → n for n > 0 to be the result of rolling Wi up to n. Then the animation generates W2 → 30 = {1,5,7,11,13,17,19,23,25,29}. Note that up to 52 − 1 = 24, this consists only of 1 and the primes between 5 and 25. The sieve of Pritchard is derived from the observation that this holds generally: for all i > 0, the values in Wi → (p2i+1 − 1) are 1 and the primes between pi+1 and p2i+1. It even holds for i = 0, where the wheel has length 1 and contains just 1 (representing all the natural numbers). So the sieve of Pritchard starts with the trivial wheel W0 and builds successive wheels until the square of the wheel's first member after 1 is at least N. Wheels grow very quickly, but only their values up to N are needed and generated. It remains to find a method for generating the next wheel. Note in the animation that W3 = {1,5,7,11,13,17,19,23,25,29} − {5 · 1 , 5 · 5} can be obtained by rolling W2 up to 30 and then removing 5 times each member of W2.This also holds generally: for all i ≥ 0, Wi+1 = (Wi → Pi+1) − {pi+1 · w | w ∈ Wi}. Rolling Wi past Pi just adds values to Wi, so the current wheel is first extended by getting each successive member starting with w = 1, adding Pi to it, and inserting the result in the set. Then the multiples of pi+1 are deleted. Care must be taken to avoid a number being deleted that itself needs to be multiplied by pi+1. The sieve of Pritchard as originally presented does so by first skipping past successive members until finding the maximum one needed, and then doing the deletions in reverse order by working back through the set. This is the method used in the first animation above. A simpler approach is just to gather the multiples of pi+1 in a list, and then delete them. Another approach is given by Gries and Misra. If the main loop terminates with a wheel whose length is less than N, it is extended up to N to generate the remaining primes. The algorithm, for finding all primes up to N, is therefore as follows: Start with a set W = {1} and length = 1 representing wheel 0, and prime p = 2. As long as p2 ≤ N, do the following: if length < N, then extend W by repeatedly getting successive members w of W starting with 1 and inserting length + w into W as long as it does not exceed p · length or N; increase length to the minimum of p · length and N. repeatedly delete p times each member of W by first finding the largest ≤ length and then working backwards. note the prime p, then set p to the next member of W after 1 (or 3 if p was 2). if length < N, then extend W to N by repeatedly getting successive members w of W starting with 1 and inserting length + w into W as long as it does not exceed N; On termination, the rest of the primes up to N are the members of W after 1. === Example === To find all the prime numbers less than or equal to 150, proceed as follows. Start with wheel 0 with length 1, representing all natural numbers 1, 2, 3...: 1 The first number after 1 for wheel 0 (when rolled) is 2; note it as a prime. Now form wheel 1 with length 2 × 1 = 2 by first extending wheel 0 up to 2 and then deleting 2 times each number in wheel 0, to get: 1 2 The first number after 1 for wheel 1 (when rolled) is 3; note it as a prime. Now form wheel 2 with length 3 × 2 = 6 by first extending wheel 1 up to 6 and then deleting 3 times each number in wheel 1, to get 1 2 3 5 The first number after 1 for wheel 2 is 5; note it as a prime. Now form wheel 3 with length 5 × 6 = 30 by first extending wheel 2 up to 30 and then deleting 5 times each number in wheel 2 (in reverse order), to get 1 2 3 5 7 11 13 17 19 23 25 29 The first number after 1 for wheel 3 is 7; note it as a prime. Now wheel 4 has length 7 × 30 = 210, so we only extend wheel 3 up to our limit 150. (No further extending will be done now that the limit has been reached.) We then delete 7 times each number in wheel 3 until we exceed our limit 150, to get the elements in wheel 4 up to 150: 1 2 3 5 7 11 13 17 19 23 25 29 31 37 41 43 47 49 53 59 61 67 71 73 77 79 83 89 91 97 101 103 107 109 113 119 121 127 131 133 137 139 143 149 The first number after 1 for this partial wheel 4 is 11; note it as a prime. Since we have finished with rolling, we delete 11 times each number in the partial wheel 4 until we exceed our limit 150, to get the elements in wheel 5 up to 150: 1 2 3 5 7 11 13 17 19 23 25 29 31 37 41 43 47 49 53 59 61 67 71 73 77 79 83 89 91 97 101 103 107 109 113 119 121 127 131 133 137 139 143 149 The first number after 1 for this partial wheel 5 is 13. Since 13 squared is at least our limit 150, we stop. The remaining numbers (other than 1) are the rest of the primes up to our limit 150. Just 8 composite numbers are removed, once each. The rest of the numbers considered (other than 1) are prime. In comparison, the natural version of Eratosthenes sieve (stopping at the same point) removes composite numbers 184 times. == Pseudocode == The sieve of Pritchard can be expressed in pseudocode, as follows: algorithm Sieve of Pritchard is input: an integer N >= 2. output: the set of prime numbers in {1,2,...,N}. let W and Pr be sets of integer values, and all other variables integer values. k, W, length, p, Pr := 1, {1}, 2, 3, {2}; {invariant: p = pk+1 and W = Wk ∩ {\displaystyle \cap } {1,2,...,N} and length = minimum of Pk,N and Pr = the primes up to pk} while p2 <= N do if (length < N) then Extend W,length to minimum of plength,N; Delete multiples of p from W; Insert p into Pr; k, p := k+1, next(W, 1) if (length < N) then Extend W,length to N; return Pr ∪ {\displaystyle \cup } W - {1}; where next(W, w) is the next value in the ordered set W after w. procedure Extend W,length to n is {in: W = Wk and length = Pk and n > length} {out: W = Wk → {\displaystyle \rightarrow } n and length = n} integer w, x; w, x := 1, length+1; while x <= n do Insert x into W; w := next(W,w); x := length + w; length := n; procedure Delete multiples of p from W,length is integer w; w := p; while pw <= length do w := next(W,w); while w > 1 do w := prev(W,w); Remove pw from W; where prev(W, w) is the previous value in the ordered set W before w. The algorithm can be initialized with W0 instead of W1 at the minor complication of making next(W, 1) a special case when k = 0. This a

  Read more →