AI Chat Image Generator Free

AI Chat Image Generator Free — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

BERT (language model)

Bidirectional encoder representations from transformers (BERT) is a language model introduced in October 2018 by researchers at Google. It learns to represent text as a sequence of vectors using self-supervised learning. It uses the encoder-only transformer architecture. BERT dramatically improved the state of the art for large language models. As of 2020, BERT is a ubiquitous baseline in natural language processing (NLP) experiments. BERT is trained by masked token prediction and next sentence prediction. With this training, BERT learns contextual, latent representations of tokens in their context, similar to ELMo and GPT-2. It found applications for many natural language processing tasks, such as coreference resolution and polysemy resolution. It improved on ELMo and spawned the study of "BERTology", which attempts to interpret what is learned by BERT. BERT was originally implemented in the English language at two model sizes, BERTBASE (110 million parameters) and BERTLARGE (340 million parameters). Both were trained on the Toronto BookCorpus (800M words) and English Wikipedia (2,500M words). The weights were released on GitHub. On March 11, 2020, 24 smaller models were released, the smallest being BERTTINY with just 4 million parameters. == Architecture == BERT is an "encoder-only" transformer architecture. At a high level, BERT consists of 4 modules: Tokenizer: This module converts a piece of English text into a sequence of integers ("tokens"). Embedding: This module converts the sequence of tokens into an array of real-valued vectors representing the tokens. It represents the conversion of discrete token types into a lower-dimensional Euclidean space. Encoder: a stack of Transformer blocks with self-attention, but without causal masking. Task head: This module converts the final representation vectors into one-shot encoded tokens again by producing a predicted probability distribution over the token types. It can be viewed as a simple decoder, decoding the latent representation into token types, or as an "un-embedding layer". The task head is necessary for pre-training, but it is often unnecessary for so-called "downstream tasks," such as question answering or sentiment classification. Instead, one removes the task head and replaces it with a newly initialized module suited for the task, and finetune the new module. The latent vector representation of the model is directly fed into this new module, allowing for sample-efficient transfer learning. === Embedding === This section describes the embedding used by BERTBASE. The other one, BERTLARGE, is similar, just larger. The tokenizer of BERT is WordPiece, which is a sub-word strategy like byte-pair encoding. Its vocabulary size is 30,000, and any token not appearing in its vocabulary is replaced by [UNK] ("unknown"). The first layer is the embedding layer, which contains three components: token type embeddings, position embeddings, and segment type embeddings. Token type: The token type is a standard embedding layer, translating a one-hot vector into a dense vector based on its token type. Position: The position embeddings are based on a token's position in the sequence. BERT uses absolute position embeddings, where each position in a sequence is mapped to a real-valued vector. Each dimension of the vector consists of a sinusoidal function that takes the position in the sequence as input. Segment type: Using a vocabulary of just 0 or 1, this embedding layer produces a dense vector based on whether the token belongs to the first or second text segment in that input. In other words, type-1 tokens are all tokens that appear after the [SEP] special token. All prior tokens are type-0. The three embedding vectors are added together representing the initial token representation as a function of these three pieces of information. After embedding, the vector representation is normalized using a LayerNorm operation, outputting a 768-dimensional vector for each input token. After this, the representation vectors are passed forward through 12 Transformer encoder blocks, and are decoded back to 30,000-dimensional vocabulary space using a basic affine transformation layer. === Architectural family === The encoder stack of BERT has 2 free parameters: L {\displaystyle L} , the number of layers, and H {\displaystyle H} , the hidden size. There are always H / 64 {\displaystyle H/64} self-attention heads, and the feed-forward/filter size is always 4 H {\displaystyle 4H} . By varying these two numbers, one obtains an entire family of BERT models. For BERT: the feed-forward size and filter size are synonymous. Both of them denote the number of dimensions in the middle layer of the feed-forward network. the hidden size and embedding size are synonymous. Both of them denote the number of real numbers used to represent a token. The notation for encoder stack is written as L/H. For example, BERTBASE is written as 12L/768H, BERTLARGE as 24L/1024H, and BERTTINY as 2L/128H. == Training == === Pre-training === BERT was pre-trained simultaneously on two tasks: Masked language modeling (MLM): In this task, BERT ingests a sequence of words, where one word may be randomly changed ("masked"), and BERT tries to predict the original words that had been changed. For example, in the sentence "The cat sat on the [MASK]," BERT would need to predict "mat." This helps BERT learn bidirectional context, meaning it understands the relationships between words not just from left to right or right to left but from both directions at the same time. Next sentence prediction (NSP): In this task, BERT is trained to predict whether one sentence logically follows another. For example, given two sentences, "The cat sat on the mat" and "It was a sunny day", BERT has to decide if the second sentence is a valid continuation of the first one. This helps BERT understand relationships between sentences, which is important for tasks like question answering or document classification. ==== Masked language modeling ==== In masked language modeling, 15% of tokens would be randomly selected for masked-prediction task, and the training objective was to predict the masked token given its context. In more detail, the selected token is: replaced with a [MASK] token with probability 80%, replaced with a random word token with probability 10%, not replaced with probability 10%. The reason not all selected tokens are masked is to avoid the dataset shift problem. The dataset shift problem arises when the distribution of inputs seen during training differs significantly from the distribution encountered during inference. A trained BERT model might be applied to word representation (like Word2Vec), where it would be run over sentences not containing any [MASK] tokens. It is later found that more diverse training objectives are generally better. As an illustrative example, consider the sentence "my dog is cute". It would first be divided into tokens like "my1 dog2 is3 cute4". Then a random token in the sentence would be picked. Let it be the 4th one "cute4". Next, there would be three possibilities: with probability 80%, the chosen token is masked, resulting in "my1 dog2 is3 [MASK]4"; with probability 10%, the chosen token is replaced by a uniformly sampled random token, such as "happy", resulting in "my1 dog2 is3 happy4"; with probability 10%, nothing is done, resulting in "my1 dog2 is3 cute4". After processing the input text, the model's 4th output vector is passed to its decoder layer, which outputs a probability distribution over its 30,000-dimensional vocabulary space. ==== Next sentence prediction ==== Given two sentences, the model predicts if they appear sequentially in the training corpus, outputting either [IsNext] or [NotNext]. During training, the algorithm sometimes samples two sentences from a single continuous span in the training corpus, while at other times, it samples two sentences from two discontinuous spans. The first sentence starts with a special token, [CLS] (for "classify"). The two sentences are separated by another special token, [SEP] (for "separate"). After processing the two sentences, the final vector for the [CLS] token is passed to a linear layer for binary classification into [IsNext] and [NotNext]. For example: Given "[CLS] my dog is cute [SEP] he likes playing [SEP]", the model should predict [IsNext]. Given "[CLS] my dog is cute [SEP] how do magnets work [SEP]", the model should predict [NotNext]. === Fine-tuning === BERT is meant as a general pretrained model for various applications in natural language processing. That is, after pre-training, BERT can be fine-tuned with fewer resources on smaller datasets to optimize its performance on specific tasks such as natural language inference and text classification, and sequence-to-sequence-based language generation tasks such as question answering and conversational response generation. The original BERT paper published results demonstrating that a small amount of fine
Read more →
AI Photo Editors Reviews: What Actually Works in 2026

Curious about the best AI photo editor? An AI photo editor is software that uses machine learning to help you get more done — it combines speed, accuracy, and an interface that just works. Hands-on testing shows real-world results vary, so a short free trial is the smartest way to decide. Whether you are a beginner or a pro, the right AI photo editor slots into your workflow and pays for itself fast. This guide breaks down the top picks, their pros and cons, and who each one is best for.
Read more →
Markov chain

In probability theory and statistics, a Markov chain or Markov process is a stochastic process describing a sequence of possible events in which the probability of each event depends only on the state attained in the previous event. Informally, this may be thought of as, "What happens next depends only on the state of affairs now." A countably infinite sequence, in which the chain moves state at discrete time steps, gives a discrete-time Markov chain (DTMC). A continuous-time process is called a continuous-time Markov chain (CTMC). Markov processes are named in honor of the Russian mathematician Andrey Markov. Markov chains have many applications as statistical models of real-world processes. They provide the basis for general stochastic simulation methods known as Markov chain Monte Carlo, which are used for simulating sampling from complex probability distributions, and have found application in areas including Bayesian statistics, biology, chemistry, economics, finance, information theory, physics, signal processing, and speech processing. The adjectives Markovian and Markov are used to describe something that is related to a Markov process. == Principles == === Definition === A Markov process is a stochastic process that satisfies the Markov property (sometimes characterized as "memorylessness"). In simpler terms, it is a process for which predictions can be made regarding future outcomes based solely on its present state and—most importantly—such predictions are just as good as the ones that could be made knowing the process's full history. In other words, conditional on the present state of the system, its future and past states are independent. A Markov chain is a type of Markov process that has either a discrete state space or a discrete index set (often representing time), but the precise definition of a Markov chain varies. For example, it is common to define a Markov chain as a Markov process in either discrete or continuous time with a countable state space (thus regardless of the nature of time), but it is also common to define a Markov chain as having discrete time in either countable or continuous state space (thus regardless of the state space). === Types of Markov chains === The system's state space and time parameter index need to be specified. The following table gives an overview of the different instances of Markov processes for different levels of state space generality for both discrete and continuous time: Note that there is no definitive agreement in the literature on the use of some of the terms that signify special cases of Markov processes. Usually the term "Markov chain" is reserved for a process with a discrete set of times, that is, a discrete-time Markov chain (DTMC), but a few authors use the term "Markov process" to refer to a continuous-time Markov chain (CTMC) without explicit mention. In addition, there are other extensions of Markov processes that are referred to as such but do not necessarily fall within any of these four categories (see Markov model). Moreover, the time index need not necessarily be real-valued; like with the state space, there are conceivable processes that move through index sets with other mathematical constructs. Notice that the general state space continuous-time Markov chain is general to such a degree that it has no designated term. While the time parameter is usually discrete, the state space of a Markov chain does not have any generally agreed-on restrictions: the term may refer to a process on an arbitrary state space. However, many applications of Markov chains employ finite or countably infinite state spaces, which have a more straightforward statistical analysis. Besides time-index and state-space parameters, there are many other variations, extensions and generalizations (see Variations). For simplicity, most of this article concentrates on the discrete-time, discrete state-space case, unless mentioned otherwise. === Transitions === The changes of state of the system are called transitions. The probabilities associated with various state changes are called transition probabilities. The process is characterized by a state space, a transition matrix describing the probabilities of particular transitions, and an initial state (or initial distribution) across the state space. By convention, we assume all possible states and transitions have been included in the definition of the process, so there is always a next state, and the process does not terminate. A discrete-time random process involves a system which is in a certain state at each step, with the state changing randomly between steps. The steps are often thought of as moments in time, but they can equally well refer to physical distance or any other discrete measurement. Formally, the steps are the integers or natural numbers, and the random process is a mapping of these to states. The Markov property states that the conditional probability distribution for the system at the next step (and in fact at all future steps) depends only on the current state of the system, and not additionally on the state of the system at previous steps. Since the system changes randomly, it is generally impossible to predict with certainty the state of a Markov chain at a given point in the future. However, the statistical properties of the system's future can be predicted. In many applications, it is these statistical properties that are important. == History == Andrey Markov studied Markov processes in the early 20th century, publishing his first paper on the topic in 1906. Markov processes in continuous time were discovered long before his work in the early 20th century in the form of the Poisson process. Markov was interested in studying an extension of independent random sequences, motivated by a disagreement with Pavel Nekrasov who claimed independence was necessary for the weak law of large numbers to hold. In his first paper on Markov chains, published in 1906, Markov showed that under certain conditions the average outcomes of the Markov chain would converge to a fixed vector of values, so proving a weak law of large numbers without the independence assumption, which had been commonly regarded as a requirement for such mathematical laws to hold. Markov later used Markov chains to study the distribution of vowels in Eugene Onegin, written by Alexander Pushkin, and proved a central limit theorem for such chains. In 1912 Henri Poincaré studied Markov chains on finite groups with an aim to study card shuffling. Other early uses of Markov chains include a diffusion model, introduced by Paul and Tatyana Ehrenfest in 1907, and a branching process, introduced by Francis Galton and Henry William Watson in 1873, preceding the work of Markov. After the work of Galton and Watson, it was later revealed that their branching process had been independently discovered and studied around three decades earlier by Irénée-Jules Bienaymé. Starting in 1928, Maurice Fréchet became interested in Markov chains, eventually resulting in him publishing in 1938 a detailed study on Markov chains. Andrey Kolmogorov developed in a 1931 paper a large part of the early theory of continuous-time Markov processes. Kolmogorov was partly inspired by Louis Bachelier's 1900 work on fluctuations in the stock market as well as Norbert Wiener's work on Einstein's model of Brownian movement. He introduced and studied a particular set of Markov processes known as diffusion processes, where he derived a set of differential equations describing the processes. Independent of Kolmogorov's work, Sydney Chapman derived in a 1928 paper an equation, now called the Chapman–Kolmogorov equation, in a less mathematically rigorous way than Kolmogorov, while studying Brownian movement. The differential equations are now called the Kolmogorov equations or the Kolmogorov–Chapman equations. Other mathematicians who contributed significantly to the foundations of Markov processes include William Feller, starting in 1930s, and then later Eugene Dynkin, starting in the 1950s. == Examples == Mark V. Shaney is a third-order Markov chain program, and a Markov text generator. It ingests the sample text (the Tao Te Ching, or the posts of a Usenet group) and creates a massive list of every sequence of three successive words (triplet) which occurs in the text. It then chooses two words at random, and looks for a word which follows those two in one of the triplets in its massive list. If there is more than one, it picks at random (identical triplets count separately, so a sequence which occurs twice is twice as likely to be picked as one which only occurs once). It then adds that word to the generated text. Then, in the same way, it picks a triplet that starts with the second and third words in the generated text, and that gives a fourth word. It adds the fourth word, then repeats with the third and fourth words, and so on. Random walks based on integers and the gambler's ruin problem are ex
Read more →
Frederick Jelinek

Frederick Jelinek (18 November 1932 – 14 September 2010) was a Czech-American researcher in information theory, automatic speech recognition, and natural language processing. He is well known for his oft-quoted statement, "Every time I fire a linguist, the performance of the speech recognizer goes up". Jelinek was born in Czechoslovakia before World War II and emigrated with his family to the United States in the early years of the communist regime. He studied engineering at the Massachusetts Institute of Technology and taught for 10 years at Cornell University before accepting a job at IBM Research. In 1961, he married Czech screenwriter Milena Jelinek. At IBM, his team advanced approaches to computer speech recognition and machine translation. After IBM, he went to head the Center for Language and Speech Processing at Johns Hopkins University for 17 years, where he was still working on the day he died. == Personal life == Jelinek was born on November 18, 1932, as Bedřich Jelínek in Kladno to Vilém and Trude Jelínek. His father was Jewish; his mother was born in Switzerland to Czech Catholic parents and had converted to Judaism. Jelínek senior, a dentist, had planned early to escape Nazi occupation and flee to England; he arranged for a passport, visa, and the shipping of his dentistry materials. The couple planned to send their son to an English private school. However, Vilém decided to stay at the last minute and was eventually sent to the Theresienstadt concentration camp, where he died in 1945. The family was forced to move to Prague in 1941, but Frederick, his sister and mother—thanks to the latter's background—escaped the concentration camps. After the war, Jelinek entered in the gymnasium, despite having missed several years of schooling because education of Jewish children had been forbidden since 1942. His mother, anxious that her son should get a good education, made great efforts for their emigration, especially when it became clear he would not be allowed to even attempt the graduation examination. His mother hoped her son would become a physician, but Jelinek dreamed of being a lawyer. He studied engineering in evening classes at the City College of New York and received stipends from the National Committee for a Free Europe that allowed him to study at the Massachusetts Institute of Technology. About his choice of specialty, he said: "Fortunately, to electrical engineering there belonged a discipline whose aim was not the construction of physical systems: the theory of information". He obtained his Ph.D. in 1962, with Robert Fano as his adviser. In 1957, Jelinek paid an unexpected visit to Prague. He had been in Vienna and applied for a visa, hoping to see his former acquaintances again. He met with his old friend Miloš Forman, who introduced him to film student Milena Tobolová—whose screenplay had been the basis for the movie Easy Life (Snadný život). His flight back to the U.S. had a stopover in Munich, during which he called her to propose. Tobolová was considered a dissident and the authorities were not happy with her film. Jelinek asked for help from Jerome Wiesner and Cyrus Eaton, the latter who lobbied Nikita Khrushchev. Following the inauguration of John F. Kennedy, a group of Czech dissidents were allowed to emigrate in January 1961. Thanks to the lobbying, the future Milena Jelinek was one of them. After completing his graduate studies, Jelinek, who had developed an interest in linguistics, had plans to work with Charles F. Hockett at Cornell University. However these fell through and during the next ten years he continued to study information theory. Having previously worked at IBM during a sabbatical, he began full-time work there in 1972—at first on leave for Cornell, but permanently from 1974. He remained there for over twenty years. Although at first he had been offered a regular research job, upon his arrival he learned that Josef Raviv had recently been promoted to head of the newly opened IBM Haifa Research Laboratory, and became head of the Continuous Speech Recognition group at the Thomas J. Watson Research Center. Despite his team's successes in this area, Jelinek's work remained little known in his home country because Czech scientists were not allowed to participate in key conferences. After the 1989 fall of communism, Jelinek helped establish scientific relationships, regularly visiting to lecture and helping to persuade IBM to establish a computing centre at Charles University. In 1993, he retired from IBM and went to Johns Hopkins University's Center for Language and Speech Processing, where he was director and Julian Sinclair Smith Professor of Electrical and Computer Engineering. He was still working there at the time of his death; Jelinek died of a heart attack at the close of an otherwise normal workday in mid-September 2010. He was survived by his wife, daughter and son, sister, stepsister, and three grandchildren, including Sophie Gold Jelinek. == Research and legacy == Information theory was a fashionable scientific approach in the mid '50s. However, pioneer Claude Shannon wrote in 1956 that this trendiness was dangerous. He said, "Our fellow scientists in many different fields, attracted by the fanfare and by the new avenues opened to scientific analysis, are using these ideas in their own problems ... It will be all too easy for our somewhat artificial prosperity to collapse overnight when it is realized that the use of a few exciting words like information, entropy, redundancy, do not solve all our problems." During the next decade, a combination of factors shut down the application of information theory to natural language processing (NLP) problems—in particular machine translation. One factor was the 1957 publication of Noam Chomsky's Syntactic Structures, which stated, "probabilistic models give no insight into the basic problems of syntactic structure". This accorded well with the philosophy of the artificial intelligence research of the time, which promoted rule-based approaches. The other factor was the 1966 ALPAC report, which recommended that the government should stop funding research into machine translation. ALPAC chairman John Pierce later said that the field was filled with "mad inventors or untrustworthy engineers". He said that the underlying linguistic problems must be solved before attempts at NLP could be reasonably made. These elements essentially halted research in the field. Jelinek had begun to develop an interest in linguistics after the immigration of his wife, who initially enrolled in the MIT linguistics program with the help of Roman Jakobson. Jelinek often accompanied her to Chomsky's lectures, and even discussed the possibility of changing orientation with his adviser. Fano was "really upset", and after the failure of his project with Hockett at Cornell, he did not return to this field of research until starting work at IBM. The scope of research at IBM was considerably different from that of most other teams. According to Mark Liberman, "While [Jelinek] was leading IBM's effort to solve the general dictation problem during the decade or so following 1972, most other U.S. companies and academic researchers were working on very limited problems ... or were staying out of the field entirely". Jelinek regarded speech recognition as an information theory problem—a noisy channel, in this case the acoustic signal—which some observers considered a daring approach. The concept of perplexity was introduced in their first model, New Raleigh Grammar, which was published in 1976 as the paper "Continuous Speech Recognition by Statistical Methods" in the journal Proceedings of the IEEE. According to Young, the basic noisy channel approach "reduced the speech recognition problem to one of producing two statistical models". Whereas New Raleigh Grammar was a hidden Markov model, their next model, called Tangora, was broader and involved n-grams, specifically trigrams. Even though "it was obvious to everyone that this model was hopelessly impoverished", it was not improved upon until Jelinek presented another paper in 1999. The same trigram approach was applied to phones in single words. Although the identification of parts of speech turned out not to be very useful for speech recognition, tagging methods developed during these projects are now used in various NLP applications. The incremental research techniques developed at IBM eventually became dominant in the field after DARPA, in the mid-80s, returned to NLP research and imposed that methodology to participating teams, shared common goals, data, and precise evaluation metrics. The Continuous Speech Recognition Group's research, which required large amounts of data to train the algorithms, eventually led to the creation of the Linguistic Data Consortium. In the 1980s, although the broader problem of speech recognition remained unsolved, they sought to apply the methods developed to other problems; machine translat
Read more →
XRX (web application architecture)

In software development XRX is a web application architecture based on XForms, REST and XQuery. XRX applications store data on both the web client and on the web server in XML format and do not require a translation between data formats. XRX is considered a simple and elegant application architecture due to the minimal number of translations needed to transport data between client and server systems. The XRX architecture is also tightly coupled to W3C standards (CSS, XHTML 2.0, XPath, XML Schema) to ensure XRX applications will be robust in the future. Because XRX applications leverage modern declarative languages on the client and functional languages on the server they are designed to empower non-developers who are not familiar with traditional imperative languages such as JavaScript, Java or .Net. == Overview of XRX == XRX is a zero translation application architecture that uses XML to store data in the client web browser, on the application server and in the database server. It is because each of these layers uses XML as the same structural data model that XRX applications do not have to translate data structures to and from both object and relational data structures. Because of the lack of need for translation, XRX is considered to have a clean and elegant design. The XRX web application architecture allows developers to focus on the business problem and not the translation problem. XRX benefits from several advances in software technology: === Client Architectural Features === A model–view–controller (MVC) architecture that separates the data from its presentation and business logic. A single element (xf:submission) for all server submissions. This replaces much of the JavaScript code required in most AJAX applications. An advanced event model (XML Events) consistent with W3C standards that frees applications from having to deal with vendor-specific and browser-specific event handling. A Dependency graph that is used to store the dependency structure of the client controllers. This frees the developer from having to manually update either the model or the views when data changes in an application. This allows spreadsheet-like applications to be created on the client with very little effort. A declarative programming style that allows most client XForms applications to be created using a small set of approximately 20 elements. This allows rich client applications to be created without knowledge of JavaScript or other procedural scripting languages. An easy-to-extend system for creating new user interface controls using the EXtensible Bindings Language. This allows developers to add new controls at any time without fear of incompatibilities with W3C standards. === Server Architecture Features === Many native XML databases have built-in REST interfaces making each XQuery inherently a RESTful web service. A functional programming model that promotes side-effect free systems that are easier to debug and easier to run on multiple processors. An easy-to-extend system using XQuery function and modules. === Both Client and Server === Both XRX client and server components support a wide range of XML related standards such as XPath, XML Schema and XML Namespaces. Consistent use of REST interfaces to exchange data between the client and server for all transfers of data including as-you-type data checking and suggest functions. Consistent integration of W3C standards including use of XPath and XML Schema data types. A large library of standard of functions used on both the client and server. == Overall Benefits of XRX == One of the principal benefits of the XRX architecture is that it avoids the requirement to "shred" complex data structures into relational structures and then reconstitute the data back into structures when a record is edited on the client. Another benefits of the XRX Web application architecture is that it avoids most of the problems around the object-relational impedance mismatch. Another advantage is that the client developer does not have to learn JavaScript on the client. == Comparison with Traditional Object/Relational Web Application Architectures == Many traditional web application architectures created in the late 1990 were based on middle object tiers and persistence layers that used tabular data streams and relational database systems. Because each of these layers used different structures to store the models the systems required much additional complexity to translate between layers. == History of XRX == Early examples of using a zero-translation architecture in multi-tier systems can be traced back to the rise of object-oriented databases in the 1990s. See OODBMS History Mark Birbeck suggested that the combination of XForms, XQuery with REST interfaces between the two had many advantages in a meeting to the UK XML User Group in September 2006 . His presentation was one of the first to specifically suggest that the combination of three technologies: XForms and XQuery with REST interfaces would have surprisingly beneficial effects. Mark termed this process "Skimming" but that term did not seem to be contagious. Erik Bruchez of Orbeon spoke at the XML 2007 conference on Boston in December 2007. In his presentation "XForms and the eXist XML database: a perfect couple", Bruchez showed that many people were discovering synergistic benefits of XForms on the client and XQuery on the server. The label for XRX was suggested by a blog posting by Dan McCreary on December 14, 2007. It was in this article that Dan suggested the need for a contagious meme for the ideas behind the XRX architecture. == Generalizations of XRX == Although XRX was originally intended to connote the use of XForms on the client, REST as an interface and XQuery on the server, other proponents of the symmetrical use of XML on the client and server have generalized the term to encompass any XML-centric web client and any server that can store and query XML documents. This use of XRX is generally referred to as "shallow XRX". These generalizations do benefit from a simplified zero-translation architecture but many do not benefit from REST interfaces, XPath for consistent data selection, declarative systems in the client, and functional languages on the server (one of the key aspects of XRX). Use of all three technologies (XForms, REST and XQuery) is referred to as "deep XRX". Although XRX architecture is centred on XForms and XQuery, it does not preclude the use of other technologies that manipulate XML natively, such as XSLT, XProc, and XSL-FO.
Read more →
Structured support vector machine

The structured supportvector machine is a machine learning algorithm that generalizes the support vector machine (SVM) classifier. Whereas the SVM classifier supports binary classification, multiclass classification and regression, the structured SVM allows training of a classifier for general structured output labels. As an example, a sample instance might be a natural language sentence, and the output label is an annotated parse tree. Training a classifier consists of showing pairs of correct sample and output label pairs. After training, the structured SVM model allows one to predict for new sample instances the corresponding output label; that is, given a natural language sentence, the classifier can produce the most likely parse tree. == Training == For a set of n {\displaystyle n} training instances ( x i , y i ) ∈ X × Y {\displaystyle ({\boldsymbol {x}}_{i},y_{i})\in {\mathcal {X}}\times {\mathcal {Y}}} , i = 1 , … , n {\displaystyle i=1,\dots ,n} from a sample space X {\displaystyle {\mathcal {X}}} and label space Y {\displaystyle {\mathcal {Y}}} , the structured SVM minimizes the following regularized risk function. min w ‖ w ‖ 2 + C ∑ i = 1 n max y ∈ Y ( 0 , Δ ( y i , y ) + ⟨ w , Ψ ( x i , y ) ⟩ − ⟨ w , Ψ ( x i , y i ) ⟩ ) {\displaystyle {\underset {\boldsymbol {w}}{\min }}\quad \|{\boldsymbol {w}}\|^{2}+C\sum _{i=1}^{n}{\underset {y\in {\mathcal {Y}}}{\max }}\left(0,\Delta (y_{i},y)+\langle {\boldsymbol {w}},\Psi ({\boldsymbol {x}}_{i},y)\rangle -\langle {\boldsymbol {w}},\Psi ({\boldsymbol {x}}_{i},y_{i})\rangle \right)} The function is convex in w {\displaystyle {\boldsymbol {w}}} because the maximum of a set of affine functions is convex. The function Δ : Y × Y → R + {\displaystyle \Delta :{\mathcal {Y}}\times {\mathcal {Y}}\to \mathbb {R} _{+}} measures a distance in label space and is an arbitrary function (not necessarily a metric) satisfying Δ ( y , z ) ≥ 0 {\displaystyle \Delta (y,z)\geq 0} and Δ ( y , y ) = 0 ∀ y , z ∈ Y {\displaystyle \Delta (y,y)=0\;\;\forall y,z\in {\mathcal {Y}}} . The function Ψ : X × Y → R d {\displaystyle \Psi :{\mathcal {X}}\times {\mathcal {Y}}\to \mathbb {R} ^{d}} is a feature function, extracting some feature vector from a given sample and label. The design of this function depends very much on the application. Because the regularized risk function above is non-differentiable, it is often reformulated in terms of a quadratic program by introducing one slack variable ξ i {\displaystyle \xi _{i}} for each sample, each representing the value of the maximum. The standard structured SVM primal formulation is given as follows. min w , ξ ‖ w ‖ 2 + C ∑ i = 1 n ξ i s.t. ⟨ w , Ψ ( x i , y i ) ⟩ − ⟨ w , Ψ ( x i , y ) ⟩ + ξ i ≥ Δ ( y i , y ) , i = 1 , … , n , ∀ y ∈ Y {\displaystyle {\begin{array}{cl}{\underset {{\boldsymbol {w}},{\boldsymbol {\xi }}}{\min }}&\|{\boldsymbol {w}}\|^{2}+C\sum _{i=1}^{n}\xi _{i}\\{\textrm {s.t.}}&\langle {\boldsymbol {w}},\Psi ({\boldsymbol {x}}_{i},y_{i})\rangle -\langle {\boldsymbol {w}},\Psi ({\boldsymbol {x}}_{i},y)\rangle +\xi _{i}\geq \Delta (y_{i},y),\qquad i=1,\dots ,n,\quad \forall y\in {\mathcal {Y}}\end{array}}} == Inference == At test time, only a sample x ∈ X {\displaystyle {\boldsymbol {x}}\in {\mathcal {X}}} is known, and a prediction function f : X → Y {\displaystyle f:{\mathcal {X}}\to {\mathcal {Y}}} maps it to a predicted label from the label space Y {\displaystyle {\mathcal {Y}}} . For structured SVMs, given the vector w {\displaystyle {\boldsymbol {w}}} obtained from training, the prediction function is the following. f ( x ) = argmax y ∈ Y ⟨ w , Ψ ( x , y ) ⟩ {\displaystyle f({\boldsymbol {x}})={\underset {y\in {\mathcal {Y}}}{\textrm {argmax}}}\quad \langle {\boldsymbol {w}},\Psi ({\boldsymbol {x}},y)\rangle } Therefore, the maximizer over the label space is the predicted label. Solving for this maximizer is the so-called inference problem and similar to making a maximum a-posteriori (MAP) prediction in probabilistic models. Depending on the structure of the function Ψ {\displaystyle \Psi } , solving for the maximizer can be a hard problem. == Separation == The above quadratic program involves a very large, possibly infinite number of linear inequality constraints. In general, the number of inequalities is too large to be optimized over explicitly. Instead the problem is solved by using delayed constraint generation where only a finite and small subset of the constraints is used. Optimizing over a subset of the constraints enlarges the feasible set and will yield a solution that provides a lower bound on the objective. To test whether the solution w {\displaystyle {\boldsymbol {w}}} violates constraints of the complete set inequalities, a separation problem needs to be solved. As the inequalities decompose over the samples, for each sample ( x i , y i ) {\displaystyle ({\boldsymbol {x}}_{i},y_{i})} the following problem needs to be solved. y n ∗ = argmax y ∈ Y ( Δ ( y i , y ) + ⟨ w , Ψ ( x i , y ) ⟩ − ⟨ w , Ψ ( x i , y i ) ⟩ − ξ i ) {\displaystyle y_{n}^{}={\underset {y\in {\mathcal {Y}}}{\textrm {argmax}}}\left(\Delta (y_{i},y)+\langle {\boldsymbol {w}},\Psi ({\boldsymbol {x}}_{i},y)\rangle -\langle {\boldsymbol {w}},\Psi ({\boldsymbol {x}}_{i},y_{i})\rangle -\xi _{i}\right)} The right hand side objective to be maximized is composed of the constant − ⟨ w , Ψ ( x i , y i ) ⟩ − ξ i {\displaystyle -\langle {\boldsymbol {w}},\Psi ({\boldsymbol {x}}_{i},y_{i})\rangle -\xi _{i}} and a term dependent on the variables optimized over, namely Δ ( y i , y ) + ⟨ w , Ψ ( x i , y ) ⟩ {\displaystyle \Delta (y_{i},y)+\langle {\boldsymbol {w}},\Psi ({\boldsymbol {x}}_{i},y)\rangle } . If the achieved right hand side objective is smaller or equal to zero, no violated constraints for this sample exist. If it is strictly larger than zero, the most violated constraint with respect to this sample has been identified. The problem is enlarged by this constraint and resolved. The process continues until no violated inequalities can be identified. If the constants are dropped from the above problem, we obtain the following problem to be solved. y i ∗ = argmax y ∈ Y ( Δ ( y i , y ) + ⟨ w , Ψ ( x i , y ) ⟩ ) {\displaystyle y_{i}^{}={\underset {y\in {\mathcal {Y}}}{\textrm {argmax}}}\left(\Delta (y_{i},y)+\langle {\boldsymbol {w}},\Psi ({\boldsymbol {x}}_{i},y)\rangle \right)} This problem looks very similar to the inference problem. The only difference is the addition of the term Δ ( y i , y ) {\displaystyle \Delta (y_{i},y)} . Most often, it is chosen such that it has a natural decomposition in label space. In that case, the influence of Δ {\displaystyle \Delta } can be encoded into the inference problem and solving for the most violating constraint is equivalent to solving the inference problem.
Read more →
How to Choose an Conversational AI Platform

Trying to pick the best conversational AI platform? An conversational AI platform is software that uses machine learning to help you get more done — it scales effortlessly from a single task to thousands. The best picks balance beginner-friendly simplicity with the depth power users need, and they ship updates often. Whether you are a beginner or a pro, the right conversational AI platform slots into your workflow and pays for itself fast. This guide breaks down the top picks, their pros and cons, and who each one is best for.
Read more →
DeepL Translator

DeepL is a German AI research company known for its language AI platform, which includes DeepL Translator and DeepL Voice, and for DeepL Agent, an AI agent capable of planning workflows and using office systems and tools autonomously, in response to natural language instructions. Its algorithm uses the transformer architecture. It offers a paid subscription for additional features and access to its translation application programming interface. DeepL was founded in 2017 by Jaroslaw Kutylowski and is a unicorn, valued at $2 billion after a Series C funding round raised $300 million in May 2024. Its more than 200,000 business customers include a large proportion of the Fortune 500. == History == The translating system was first developed within Linguee by a team led by Chief Technology Officer Jarosław Kutyłowski in 2016. It was launched as DeepL Translator on 28 August 2017 and offered translations between English, German, French, Spanish, Italian, Polish and Dutch. At its launch, it claimed to have surpassed its competitors in blind tests and BLEU scores, including Google Translate, Amazon Translate, Microsoft Translator and Facebook's translation feature. With the release of DeepL in 2017, Linguee's company name was changed to DeepL GmbH, and it is also financed by advertising on its sister site, linguee.com. Support for Portuguese and Russian was added on 5 December 2018. In July 2019, Jarosław Kutyłowski became the CEO of DeepL GmbH and restructured the company into a Societas Europaea in 2021. Translation software for Microsoft Windows and macOS was released in September 2019. Support for Chinese (simplified) and Japanese was added on 19 March 2020, which the company claimed to have surpassed the aforementioned competitors as well as Baidu and Youdao. Then, 13 more European languages were added in March 2021: Bulgarian, Czech, Danish, Estonian, Finnish, Greek, Hungarian, Latvian, Lithuanian, Romanian, Slovak, Slovenian, and Swedish, bringing the total number of supported languages to 24. On 25 May 2022, support for Indonesian and Turkish was added, and support for Ukrainian was added on 14 September 2022. In January 2023, the company reached a valuation of 1 billion euro and became the most valued startup company in Cologne. At the end of the month, support for Korean and Norwegian (Bokmål) was also added. In May 2024, the company announced an investment of US$300 million at AI. In January 2026, more languages were supported, including Luxembourgish and Irish. == Services == === Translation method === The service uses a proprietary algorithm with convolutional neural networks (CNNs) that have been trained with the Linguee database. According to the developers, the service uses a newer improved architecture of neural networks, resulting in a more natural sound of translations than by competing services. The translation is generated using a supercomputer that reaches 5.1 petaflops and is operated in Iceland with hydropower. DeepL's data centers are located at the EcoDataCenter in Falun, Sweden, which is a data center for sustainability. In general, CNNs are slightly more suitable for long coherent word sequences, but they have so far not been used by the competition because of their weaknesses compared to recurrent neural networks. The weaknesses of DeepL are compensated for by supplemental techniques, some of which are publicly known. === Translator and subscription === The translator can be used for free with a maximum limit of 1,500 characters per translation. Microsoft Word and PowerPoint files in Office Open XML file formats (.docx and .pptx) and PDF files up to 5MB in size can also be translated. It offers paid subscription DeepL Pro, which has been available since March 2018 and includes application programming interface access and a software plug-in for computer-assisted translation tools, including SDL Trados Studio. Unlike the free version, translated texts are stated to not be saved on the server; also, the character limit is removed. The monthly pricing model includes a set amount of text, with texts beyond that being calculated according to the number of characters. ==== Supported languages ==== As of May 2026, the translation service supports the following languages: Additionally, these languages are currently in beta, indicated by an asterisk after their name in the language picker: === DeepL Write === In November 2022, DeepL launched a tool to improve monolingual texts in English and German, called DeepL Write. In December, the company removed access and informed journalists that it was only for internal use and that DeepL Write would be relaunched in early 2023. The public beta version was then released on January 17, 2023. In the summer of 2024, DeepL announced the availability of two more languages in DeepL Write: French and Spanish. By January 2024, DeepL had added an additional two: Portuguese (European and Brazilian) and Italian. === DeepL Agent === In November 2025, DeepL launched an AI agent called DeepL Agent which is capable of operating business applications in a human-like manner. == Reception == The reception of DeepL has been generally positive. TechCrunch appreciates it for the accuracy of its translations and stating that it was more accurate and nuanced than Google Translate. Le Monde thanks its developers for translating French text into more "French-sounding" expressions. RTL Z stated that DeepL Translator "offers better translations […] when it comes to Dutch to English and vice versa". La Repubblica, and a Latin American website, "WWWhat's new?", showed praise as well. A 2018 paper by the University of Bologna evaluated the Italian-to-German translation capabilities and found the preliminary results to be similar in quality to Google Translate. In September 2021, Slator remarked that the language industry response was more measured than the press and noted that DeepL is still highly regarded by users. A reviewer noted in 2018 that DeepL had far fewer languages available for translation than competing products. == Awards and honors == DeepL won the 2020 Webby Award for Best Practices and the 2020 Webby Award for Technical Achievement (Apps, Mobile, and Features), both in the category Apps, Mobile & Voice. In April 2025, DeepL was featured in the Forbes AI 50 list.
Read more →
Logical Machine Corporation

Logical Machine Corporation (LOMAC) was an American computer company active from the mid-1970s to the 1980s and based in the San Francisco Bay Area. It was founded as John Peers and Company by the British entrepreneur John Peers in 1974. LOMAC developed the ADAM, a minicomputer which ran a specialized compiler for the company's natural English programming language. Throughout the late 1970s, the company acquired several technology firms, including Byte, Inc., the owner of the Byte Shop retail chain. Despite its unique approach to computing and earning $5 million in revenue in 1977, LOMAC struggled as the industry began to standardize around the IBM Personal Computer (IBM PC). Following Peers's departure in 1980, the company rebranded as Logical Business Machines, Inc. (LBM, or simply Logical), and attempted to pivot toward IBM PC–compatible hardware. However, financial difficulties led to the company filing for Chapter 11 bankruptcy in 1984. After emerging from bankruptcy in 1985 with new investment, Logical ceased hardware manufacturing to focus exclusively on software development and value-added reselling. == History == John Peers (born 1942) founded Logical Machine Corporation as John Peers and Company in September 1974. The company originally occupied a 4,500-square-foot office in Burlingame, California. The company was Peers' fourth; he had recently sold off Allied Business Systems of London to Trafalgar House in 1974. Peers sought to set up manufacturing in an agricultural zone in Ukiah, California. Following a delay, caused in part by concerned residents, a 30,000-square-foot plant was raised in Burke Hill, three miles south of Ukiah. The Ukiah plant was built to mass manufacture the company's ADAM minicomputer. The ADAM computer ran a specialized compiler for the company's natural English programming language; that is to say, the programming language attempted to closely emulate English syntax. Prototypes of the ADAM were built in May 1974, based on specifications devised in October 1973. Peers had yet to patent the technology as of June 1975. The ADAM's central processing unit was bolted onto an 7-by-6-foot L-shaped desk, on which rested its terminal. Twenty units of the ADAM were installed between April 1975 and February 1976, out of a backlog of orders for 3,500 from 500 clients, manufactured out of the company's Burlingame headquarters. It cost US$40,000. A controversial print advertisement featuring a naked woman seated at an ADAM terminal—as a pastiche of Adam and Eve—was recalled in early 1976 as a result of outcry from the National Organization for Women. The company changed its name to Logical Machine Corporation (LOMAC) in October 1976 and moved its headquarters to a 26,000-square-foot building in Sunnyvale, California, in anticipation of a ramping up of orders for the ADAM. The company originally occupied half of the building; they later purchased the other half from the tenant in July 1977 to double its manufacturing output. For fiscal year 1977, the company earned $5 million in revenue. In December 1977, LOMAC acquired Byte, Inc.—the proprietor of The Byte Shop, the first computer retail chain—from Paul Terrell and Boyd Wilson for an unspecified amount. The Byte Shop had 65 locations in the San Francisco Bay Area in 1978; it catered mainly to hobbyists with low cost microcomputer kits, in contrast to the high cost of LOMAC's ADAM. By July 1978, however, LOMAC were able to reduce the price of the ADAM down to $15,000. The company by that point had shipped their 50th ADAM and expanded to 14 countries. Also in 1978, LOMAC acquired Mass Memory—a high-tech optical storage company based in Phoenix, Arizona, whose products had storage capacities on the order gigabytes and terabytes—and Centigram, makers of the Mike—a computer with speech recognition. Later that year, the company introduced Tina, a low-cost version of the ADAM. LOMAC suffered losses that year and appointed Jerry Brandt to the board of directions, naming him chief operating officer, in August 1978. Brandt had Logical absorb Mass Memory and Centigram into the parent operations, shutting down their respective plants in the process, converted 10 Byte Shops to franchises and opened 25 more franchised Byte locations, and stopped direct sales of LOMAC's business computer products. By the beginning of 1979, LOMAC was profitable once more, and Brandt was let go from LOMAC. Peers left LOMAC in 1980, following a slump in the company's sales. He became an executive director of the United States Robotics Society, a consortium for industrial automation companies, that year. Following Peers' departure, LOMAC changed its name to Logical Business Machines, adopting the name of its European subsidiary. In 1983, the company announced a 16-bit clone of the IBM PC, called the Logical L-XT, which featured a 10-MB hard drive, 320-KB floppy drive and 192 KB of RAM, and a real-time clock, and came shipped with various software (including MS-DOS, a word processor, and a spreadsheet application) and an amber CRT monitor. The following year, the company introduced L-NET, a local area network system based on the L-XT that could link up to 64 computers. L-NET came shipped with a natural programming language, Diplomat—a descendant of the programming language used on the ADAM. In June 1983, Logical sued Coleco Industries over trademark infringement with the latter's to-be-released Adam microcomputer. Logical cited confusion from their existing ADAM customer base caused by the announcement of the Coleco Adam as the basis for the suit. Coleco challenged Logical in the press, writing that Logical's rights to the Adam trademark for use in computers had lapsed earlier in the year. The two settled out of court, with Coleco agreeing to license the Adam name from Logical in exchange for unlimited rights to the Adam trademark. Logical halted development of the L-XT when they filed for Chapter 11 bankruptcy in July 1984. The company had been $4 million in debt. They emerged from bankruptcy in September 1985, after being infused with $2 million from Carat Ltd. The latter immediately received a little less than 50 percent ownership in Logical—this stake set to grow to over 50 percent over the next six months. As part of the terms of exiting bankruptcy, Logical stopped manufacturing hardware and strictly became a software development company and value-added reseller of computer systems.
Read more →
Top 10 AI Writing Assistants Compared (2026)

Trying to pick the best AI writing assistant? An AI writing assistant is software that uses machine learning to help you get more done — it scales effortlessly from a single task to thousands. The best picks balance beginner-friendly simplicity with the depth power users need, and they ship updates often. Whether you are a beginner or a pro, the right AI writing assistant slots into your workflow and pays for itself fast. Read on for hands-on impressions, pricing tiers, and the standout features that matter.
Read more →
Krzysztof Wołk

Krzysztof Wołk (born 16 August 1986) is a Polish IT researcher who specializes in artificial intelligence, machine learning, mobile applications, linguistic engineering, multimedia, NLP and graphic applications. His research works have been cited in more than 70 international research journals, books and research papers. He is member of scientific committee at the Health and Social Care Information Systems and Technologies (HCist), an international conference which brings in new ideas, new technologies, academic scientists, healthcare IT professionals, managers and solution providers from all over the world. His research in statistical machine learning has been recognized as one of the most cited researches in the world. He is the member of Scientific Committee-Reviewers at Research Conference in Technical Disciplines (RCITD), based in Slovakia, which brings together the academic scientists and researchers from all around the world. == Biography == He obtained the doctorate degree in 2016 from the Polish-Japanese Academy of Information and Technology in Warsaw, Poland. He is currently working as researcher and assistant professor at the Polish-Japanese Computer Science Academy (PJATK) in Warsaw, Poland. == Achievements == He has published three books: Biblia Windows Server 2012, Administrator's Guide, Mac OS X Server 10.8, and MAC OS X Server 10.6 and 10.7 Practical Guide has been cited by many researchers in the scholarly books, research journals and articles. His research work on the Polish-English statistical machine translation has been featured in the book New Research in Multimedia and Internet System. Similarly, his works regarding the machine translation system have been featured in the books New Perspective in Information System and Technologies Volume 1, Multimedia and Network Information System, and Recent Advances in Information Systems and Technologies, Volume 1.
Read more →
Alexander Gammerman

Alexander Gammerman (born 2 November 1944) is a British computer scientist, and professor at Royal Holloway University of London. He is the co-inventor of conformal prediction. He is the founding director of the Centre for Machine Learning at Royal Holloway, University of London, and a Fellow of the Royal Statistical Society. == Career == Gammerman's academic career has been pursued in the Soviet Union and the United Kingdom. He started working as a Research Fellow in the Agrophysical Research Institute, St. Petersburg. In 1983, he emigrated to the United Kingdom and was appointed as a lecturer in the Computer Science Department at Heriot-Watt University, Edinburgh. Together with Roger Thatcher, Gammerman published several articles on Bayesian inference. In 1993, he was appointed to the established chair in Computer Science at University of London tenable at Royal Holloway and Bedford New College, where he served as the Head of Computer Science department from 1995 to 2005. In 1998, the Centre for Reliable Machine Learning was established, and Gammerman became the first director of the centre. Gammerman has written 7 books. == Honours and awards == In 1996, Gammerman received the P.W. Allen Award from the Forensic Science Society. In 2006, he became an Honorary Professor, at University College London. In 2009, he became a Distinguished Professor at Complutense University of Madrid, Spain. In 2019, he received a research grant funded by the energy company Centrica about predicting the time to the next failure of equipment. In 2020, he received the Amazon Research Award for the project titled Conformal Martingales for Change-Point Detection == Selected books == Measures of Complexity (2016), Springer, ISBN 3319357786. Algorithmic Learning in a Random World (2005), Springer, ISBN 0387001522. Causal Models and Intelligent Data Management (1999), Springer, ISBN 978-3-642-58648-4. Probabilistic Reasoning and Bayesian Belief Networks (1998), Nelson Thornes Ltd, ISBN 1872474268. Computational Learning and Probabilistic Reasoning (1996), Wiley, ISBN 0471962791.
Read more →
List of Go software and tools

This is a list of Go software and tools, including compilers, development environments, build tools, testing frameworks, web frameworks, database tools, and related software for the Go programming language. == Core toolchain == Go — programming language and toolchain go command — build and package tool gofmt — source code formatter go vet — static analysis tool == Compilers and runtimes == gc — default Go compiler gccgo — GCC front end for Go GopherJS — Go-to-JavaScript compiler gollvm — Go compiler using the LLVM backend llgo — experimental Go frontend for LLVM TinyGo — compiler for embedded systems and WebAssembly Yaegi — Go interpreter == Development environments and editors == Emacs — text editor with Go support GoLand — JetBrains integrated development environment LiteIDE — Go-focused integrated development environment Neovim — text editor with Go support TextMate — text editor with Go support Vim — text editor with Go support Visual Studio Code — editor with Go support == Language servers and editor tools == delve — debugger gopls — Go language server golangci-lint — lint runner revive — linter staticcheck — static analysis tool == Build, dependency and release tools == Air — live reload development tool dep — deprecated dependency manager Go modules — dependency management system Goreleaser — release automation tool Mage — build tool Task — task runner == Testing and benchmarking == benchstat — benchmark comparison tool Ginkgo — testing framework GoMock — mock generation tool testify — testing toolkit testing — standard testing package == Web frameworks and HTTP tools == Beego — web framework Caddy — web server Chi — router Echo — web framework Fiber — web framework Gin — web framework Gorilla Mux — router Hugo — static site generator Revel — web framework Traefik — reverse proxy and load balancer == RPC and API tools == Goa — API design framework gRPC — remote procedure call framework grpc-gateway — REST gateway oapi-codegen — OpenAPI code generator Swag — OpenAPI documentation tool == Database and ORM tools == Bun — SQL toolkit and ORM CockroachDB client libraries — database drivers and tools ent — entity framework GORM — object–relational mapper sqlx — SQL toolkit == Command-line and terminal tools == Bubble Tea — terminal user interface framework Cobra — command-line framework pflag — flag parsing library urfave/cli — command-line framework Viper — configuration library == GUI toolkits and application frameworks == Fyne — cross-platform graphical user interface toolkit == Documentation, generation and analysis == errcheck — unchecked error checker godoc — documentation tool goimports — import management tool mockgen — mock generator pkgsite — package documentation site Prometheus — monitoring and alerting toolkit stringer — code generation tool wire — dependency injection code generator == Package hosting and community services == GoCenter — former Go package repository pkg.go.dev — package documentation and discovery site proxy.golang.org — module proxy == Major applications written in Go == Consul — service networking platform Docker — containerization platform InfluxDB — time-series database written in Go Kubernetes — container orchestration platform Ollama — platform for running and managing large language models locally Terraform — infrastructure as code tool Vault — secrets management tool
Read more →
Generalized nondeterministic finite automaton

In the theory of computation, a generalized nondeterministic finite automaton (GNFA), also known as an expression automaton or a generalized nondeterministic finite state machine, is a variation of a nondeterministic finite automaton (NFA) where each transition is labeled with any regular expression. The GNFA reads blocks of symbols from the input which constitute a string as defined by the regular expression on the transition. There are several differences between a standard finite state machine and a generalized nondeterministic finite state machine. A GNFA must have only one start state and one accept state, and these cannot be the same state, whereas an NFA or DFA both may have several accept states, and the start state can be an accept state. A GNFA must have only one transition between any two states, whereas a NFA or DFA both allow for numerous transitions between states. In a GNFA, a state has a single transition to every state in the machine, although often it is a convention to ignore the transitions that are labelled with the empty set when drawing generalized nondeterministic finite state machines. == Formal definition == A GNFA can be defined as a 5-tuple, (S, Σ, T, s, a), consisting of a finite set of states (S); a finite set called the alphabet (Σ); a transition function (T : (S ∖ {\displaystyle \setminus } {a}) × (S ∖ {\displaystyle \setminus } {s}) → R); a start state (s ∈ S); an accept state (a ∈ S); where R is the collection of all regular expressions over the alphabet Σ. The transition function takes as its argument a pair of two states and outputs a regular expression (the label of the transition). This differs from other finite state machines, which take as input a single state and an input from the alphabet (or the empty string in the case of nondeterministic finite state machines) and outputs the next state (or the set of possible states in the case of nondeterministic finite state machines). A DFA or NFA can easily be converted into a GNFA and then the GNFA can be easily converted into a regular expression by repeatedly collapsing parts of it to single edges until S = {s, a}. Similarly, GNFAs can be reduced to NFAs by changing regular expression operators into new edges until each edge is labelled with a regular expression matching a single string of length at most 1. NFAs, in turn, can be reduced to DFAs using the powerset construction. This shows that GNFAs recognize the same set of formal languages as DFAs and NFAs.
Read more →
Zoubin Ghahramani

Zoubin Ghahramani FRS (Persian: زوبین قهرمانی; born 8 February 1970) is a British-Iranian machine learning and AI researcher, Vice President of Research at Google DeepMind and Professor of Information Engineering at the University of Cambridge. He has been a Fellow of St John's College, Cambridge since 2009. He held appointments at University College London from 1998 to 2005 and was Associate Research Professor in the Machine Learning Department at Carnegie Mellon University from 2003 to 2012. He was the Chief Scientist of Uber from 2016 until 2020. He joined Google Brain in 2020 as Senior Research Director, becoming a VP of Research in 2021, and heading Google Brain until its merger with DeepMind to form Google DeepMind. He was a founding Cambridge Liaison Director of the Alan Turing Institute and also founding Deputy Director of the Leverhulme Centre for the Future of Intelligence. Ghahramani contributed to the Royal Society's Machine Learning Report in 2017 and led the UK's Future of Compute Review, in 2023. == Education == Ghahramani was educated at the American School of Madrid in Spain and the University of Pennsylvania where he was awarded a dual degree in Cognitive Science and Computer Science in 1990. He obtained his Ph.D. in Cognitive Neuroscience from the Department of Brain and Cognitive Sciences at the Massachusetts Institute of Technology, supervised by Michael I. Jordan and Tomaso Poggio. == Research and career == Following his Ph.D., Ghahramani moved to the University of Toronto in 1995 as a Postdoctoral Fellow in the Artificial Intelligence Lab, working with Geoffrey Hinton. From 1998 to 2005, he was a member of the faculty at the Gatsby Computational Neuroscience Unit, University College London. Ghahramani has made significant contributions in the areas of Bayesian machine learning (particularly variational methods for approximate Bayesian inference), as well as graphical models and computational neuroscience. His current research focuses on nonparametric Bayesian modelling and statistical machine learning. He has also worked on artificial intelligence, information retrieval, bioinformatics and statistics which provide the mathematical foundations for handling uncertainty, making decisions, and designing learning systems. He has published over 300 papers, receiving over 100,000 citations (an h-index of 132). He co-founded Geometric Intelligence in 2014, with Gary Marcus, Doug Bemis, and Ken Stanley, which was acquired by Uber in 2016. Afterwards, he transferred to Uber's AI Labs in 2016, and later became VP of AI and Chief Scientist at Uber. In 2020 he joined Google and became VP of Research and head of Google Brain in 2021 until its merger with DeepMind in April 2023. == Awards and honors == Ghahramani was elected Fellow of the Royal Society (FRS) in 2015. His certificate of election reads: Zoubin Ghahramani is a world leader in the field of machine learning, significantly advancing the state-of-the-art in algorithms that can learn from data. He is known in particular for fundamental contributions to probabilistic modeling and Bayesian nonparametric approaches to machine learning systems, and to the development of approximate variational inference algorithms for scalable learning. He is one of the pioneers of semi-supervised learning methods, active learning algorithms, and sparse Gaussian processes. His development of novel infinite dimensional nonparametric models, such as the infinite latent feature model, has been highly influential.He was awarded the Royal Society Milner Award in 2021 in recognition of 'his fundamental contributions to probabilistic machine learning'.
Read more →