AI Face Paint

AI Face Paint — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Excalidraw

  Excalidraw is an open-source, web-based virtual whiteboard and diagramming application. It is used to create diagrams, wireframes, and sketches within a web browser without requiring account registration. The software features a characteristic hand-drawn visual style and supports real-time multi-user collaboration using client-side end-to-end encryption. Excalidraw is released under the MIT License and is maintained by Excalidraw s.r.o., a company based in Brno, Czech Republic. == History == Excalidraw was created on 1 January 2020 by Christopher Chedeau, a software engineer at Meta Platforms. Chedeau, who previously co-created React Native and Prettier, initially developed the application as a personal project before registering the domain on 3 January 2020. Within its first months, the project attracted open-source contributors who assisted in expanding its features and rewriting the codebase into TypeScript and React. By early 2021, day-to-day operations moved to Czech developers David Luzar and Milos Vetesnik. In May 2021, the team incorporated Excalidraw s.r.o. in Brno and launched a commercial cloud-based version named Excalidraw+ to fund the open-source project's development. By May 2026, the main open-source repository on GitHub had accumulated over 123,000 stars. == Features and architecture == The application provides an infinite canvas for geometric shapes, lines, arrows, text, and freehand drawing. Its visual presentation relies on Rough.js, a JavaScript graphics library that alters standard vector paths to mimic irregular, hand-drawn lines. Excalidraw operates as a Progressive web application (PWA), allowing local installation and offline usage, saving data natively to local browser storage. Files use a native, JSON-based extension format (.excalidraw), and canvases can be exported to PNG or SVG formats. Real-time collaboration sessions are executed using Socket.IO via a relay server. Data transmission uses the browser's native Web Cryptography API to achieve end-to-end encryption. A symmetric AES key is generated on the client side and appended to the sharing URL as a fragment identifier (following the # character). Because web browsers do not transmit URL fragments to HTTP servers, the data remains unreadable to the distribution server. == Ecosystem == Excalidraw is distributed as an npm package, allowing third-party developers to embed the whiteboard component directly into external React web applications. Community-developed extensions integrate the application's file format into text editors and note-taking systems, including Visual Studio Code and Obsidian. The platform also has native integrations in commercial platforms such as Notion and HackerRank. == Reception == Google's developer relations team published a technical case study on Excalidraw as a reference implementation for Progressive Web Apps. The analysis highlighted the software's adoption of advanced web platform capabilities, specifically its utilization of the File System Access API and native Clipboard API to replicate desktop software behavior within a web browser environment.

  Read more →
• 

  Markov switching multifractal

  In financial econometrics (the application of statistical methods to economic data), the Markov-switching multifractal (MSM) is a model of asset returns developed by Laurent E. Calvet and Adlai J. Fisher that incorporates stochastic volatility components of heterogeneous durations. MSM captures the outliers, log-memory-like volatility persistence and power variation of financial returns. In currency and equity series, MSM compares favorably with standard volatility models such as GARCH(1,1) and FIGARCH both in- and out-of-sample. MSM is used by practitioners in the financial industry for different types of forecasts. == MSM specification == The MSM model can be specified in both discrete time and continuous time. === Discrete time === Let P t {\displaystyle P_{t}} denote the price of a financial asset, and let r t = ln ⁡ ( P t / P t − 1 ) {\displaystyle r_{t}=\ln(P_{t}/P_{t-1})} denote the return over two consecutive periods. In MSM, returns are specified as r t = μ + σ ¯ ( M 1 , t M 2 , t . . . M k ¯ , t ) 1 / 2 ϵ t , {\displaystyle r_{t}=\mu +{\bar {\sigma }}(M_{1,t}M_{2,t}...M_{{\bar {k}},t})^{1/2}\epsilon _{t},} where μ {\displaystyle \mu } and σ {\displaystyle \sigma } are constants and { ϵ t {\displaystyle \epsilon _{t}} } are independent standard Gaussians. Volatility is driven by the first-order latent Markov state vector: M t = ( M 1 , t M 2 , t … M k ¯ , t ) ∈ R + k ¯ . {\displaystyle M_{t}=(M_{1,t}M_{2,t}\dots M_{{\bar {k}},t})\in R_{+}^{\bar {k}}.} Given the volatility state M t {\displaystyle M_{t}} , the next-period multiplier M k , t + 1 {\displaystyle M_{k,t+1}} is drawn from a fixed distribution M with probability γ k {\displaystyle \gamma _{k}} , and is otherwise left unchanged. The transition probabilities are specified by γ k = 1 − ( 1 − γ 1 ) ( b k − 1 ) {\displaystyle \gamma _{k}=1-(1-\gamma _{1})^{(b^{k-1})}} . The sequence γ k {\displaystyle \gamma _{k}} is approximately geometric γ k ≈ γ 1 b k − 1 {\displaystyle \gamma _{k}\approx \gamma _{1}b^{k-1}} at low frequency. The marginal distribution M has a unit mean, has a positive support, and is independent of k. ==== Binomial MSM ==== In empirical applications, the distribution M is often a discrete distribution that can take the values m 0 {\displaystyle m_{0}} or 2 − m 0 {\displaystyle 2-m_{0}} with equal probability. The return process r t {\displaystyle r_{t}} is then specified by the parameters θ = ( m 0 , μ , σ ¯ , b , γ 1 ) {\displaystyle \theta =(m_{0},\mu ,{\bar {\sigma }},b,\gamma _{1})} . Note that the number of parameters is the same for all k ¯ > 1 {\displaystyle {\bar {k}}>1} . === Continuous time === MSM is similarly defined in continuous time. The price process follows the diffusion: d P t P t = μ d t + σ ( M t ) d W t , {\displaystyle {\frac {dP_{t}}{P_{t}}}=\mu dt+\sigma (M_{t})\,dW_{t},} where σ ( M t ) = σ ¯ ( M 1 , t … M k ¯ , t ) 1 / 2 {\displaystyle \sigma (M_{t})={\bar {\sigma }}(M_{1,t}\dots M_{{\bar {k}},t})^{1/2}} , W t {\displaystyle W_{t}} is a standard Brownian motion, and μ {\displaystyle \mu } and σ ¯ {\displaystyle {\bar {\sigma }}} are constants. Each component follows the dynamics: The intensities vary geometrically with k: γ k = γ 1 b k − 1 . {\displaystyle \gamma _{k}=\gamma _{1}b^{k-1}.} When the number of components k ¯ {\displaystyle {\bar {k}}} goes to infinity, continuous-time MSM converges to a multifractal diffusion, whose sample paths take a continuum of local Hölder exponents on any finite time interval. == Inference and closed-form likelihood == When M {\displaystyle M} has a discrete distribution, the Markov state vector M t {\displaystyle M_{t}} takes finitely many values m 1 , . . . , m d ∈ R + k ¯ {\displaystyle m^{1},...,m^{d}\in R_{+}^{\bar {k}}} . For instance, there are d = 2 k ¯ {\displaystyle d=2^{\bar {k}}} possible states in binomial MSM. The Markov dynamics are characterized by the transition matrix A = ( a i , j ) 1 ≤ i , j ≤ d {\displaystyle A=(a_{i,j})_{1\leq i,j\leq d}} with components a i , j = P ( M t + 1 = m j | M t = m i ) {\displaystyle a_{i,j}=P\left(M_{t+1}=m^{j}|M_{t}=m^{i}\right)} . Conditional on the volatility state, the return r t {\displaystyle r_{t}} has Gaussian density f ( r t | M t = m i ) = 1 2 π σ 2 ( m i ) exp ⁡ [ − ( r t − μ ) 2 2 σ 2 ( m i ) ] . {\displaystyle f(r_{t}|M_{t}=m^{i})={\frac {1}{\sqrt {2\pi \sigma ^{2}(m^{i})}}}\exp \left[-{\frac {(r_{t}-\mu )^{2}}{2\sigma ^{2}(m^{i})}}\right].} === Conditional distribution === === Closed-form Likelihood === The log likelihood function has the following analytical expression: ln ⁡ L ( r 1 , … , r T ; θ ) = ∑ t = 1 T ln ⁡ [ ω ( r t ) . ( Π t − 1 A ) ] . {\displaystyle \ln L(r_{1},\dots ,r_{T};\theta )=\sum _{t=1}^{T}\ln[\omega (r_{t}).(\Pi _{t-1}A)].} Maximum likelihood provides reasonably precise estimates in finite samples. === Other estimation methods === When M {\displaystyle M} has a continuous distribution, estimation can proceed by simulated method of moments, or simulated likelihood via a particle filter. == Forecasting == Given r 1 , … , r t {\displaystyle r_{1},\dots ,r_{t}} , the conditional distribution of the latent state vector at date t + n {\displaystyle t+n} is given by: Π ^ t , n = Π t A n . {\displaystyle {\hat {\Pi }}_{t,n}=\Pi _{t}A^{n}.\,} MSM often provides better volatility forecasts than some of the best traditional models both in and out of sample. Calvet and Fisher report considerable gains in exchange rate volatility forecasts at horizons of 10 to 50 days as compared with GARCH(1,1), Markov-Switching GARCH, and Fractionally Integrated GARCH. Lux obtains similar results using linear predictions. == Applications == === Multiple assets and value-at-risk === Extensions of MSM to multiple assets provide reliable estimates of the value-at-risk in a portfolio of securities. === Asset pricing === In financial economics, MSM has been used to analyze the pricing implications of multifrequency risk. The models have had some success in explaining the excess volatility of stock returns compared to fundamentals and the negative skewness of equity returns. They have also been used to generate multifractal jump-diffusions. == Related approaches == MSM is a stochastic volatility model with arbitrarily many frequencies. MSM builds on the convenience of regime-switching models, which were advanced in economics and finance by James D. Hamilton. MSM is closely related to the Multifractal Model of Asset Returns. MSM improves on the MMAR's combinatorial construction by randomizing arrival times, guaranteeing a strictly stationary process. MSM provides a pure regime-switching formulation of multifractal measures, which were pioneered by Benoit Mandelbrot.

  Read more →
• 

  Collocation

  In corpus linguistics, a collocation is a series of words or terms that co-occur more often than would be expected by chance. In phraseology, a collocation is a type of compositional phraseme, meaning that it can be understood from the words that make it up. This contrasts with an idiom, where the meaning of the whole cannot be inferred from its parts, and may be completely unrelated. There are about seven main types of collocations: adjective + noun, noun + noun (such as collective nouns), noun + verb, verb + noun, adverb + adjective, verbs + prepositional phrase (phrasal verbs), and verb + adverb. Collocation extraction is a computational technique that finds collocations in a document or corpus, using various computational linguistics elements resembling data mining. == Expanded definition == Collocations are partly or fully fixed expressions that become established through repeated context-dependent use. Such terms as crystal clear, middle management, nuclear family, and cosmetic surgery are examples of collocated pairs of words. Collocations can be in a syntactic relation (such as verb–object: make and decision), lexical relation (such as antonymy), or they can be in no linguistically defined relation. Knowledge of collocations is vital for the competent use of a language: a grammatically correct sentence will stand out as awkward if collocational preferences are violated. This makes collocation a common focus for language teaching. Corpus linguists specify a key word in context (KWIC) and identify the words immediately surrounding them, to illustrate the way words are used in practice. The processing of collocations involves a number of parameters, the most important of which is the measure of association, which evaluates whether the co-occurrence is purely by chance or statistically significant. Due to the non-random nature of language, most collocations are classed as significant, and the association scores are simply used to rank the results. Commonly used measures of association include mutual information, t scores, and log-likelihood. Rather than select a single definition, Gledhill proposes that collocation involves at least three different perspectives: co-occurrence, a statistical view, which sees collocation as the recurrent appearance in a text of a node and its collocates; construction, which sees collocation either as a correlation between a lexeme and a lexical-grammatical pattern, or as a relation between a base and its collocative partners; and expression, a pragmatic view of collocation as a conventional unit of expression, regardless of form. These different perspectives contrast with the usual way of presenting collocation in phraseological studies. Traditionally speaking, collocation is explained in terms of all three perspectives at once, in a continuum: == In dictionaries == In 1933, Harold Palmer's Second Interim Report on English Collocations highlighted the importance of collocation as a key to producing natural-sounding language, for anyone learning a foreign language. Thus from the 1940s onwards, information about recurrent word combinations became a standard feature of monolingual learner's dictionaries. As these dictionaries became "less word-centred and more phrase-centred", more attention was paid to collocation. This trend was supported, from the beginning of the 21st century, by the availability of large text corpora and intelligent corpus-querying software, making it possible to provide a more systematic account of collocation in dictionaries. Using these tools, dictionaries such as the Macmillan English Dictionary and the Longman Dictionary of Contemporary English included boxes or panels with lists of frequent collocations. There are also a number of specialized dictionaries devoted to describing the frequent collocations in a language. These include (for Spanish) Redes: Diccionario combinatorio del español contemporaneo (2004), (for French) Le Robert: Dictionnaire des combinaisons de mots (2007), and (for English) the LTP Dictionary of Selected Collocations (1997) and the Macmillan Collocations Dictionary (2010). == Statistically significant collocation == Student's t-test can be used to determine whether the occurrence of a collocation in a corpus is statistically significant. For a bigram w 1 w 2 {\displaystyle w_{1}w_{2}} , let P ( w 1 ) = # w 1 N {\displaystyle P(w_{1})={\frac {\#w_{1}}{N}}} be the unconditional probability of occurrence of w 1 {\displaystyle w_{1}} in a corpus with size N {\displaystyle N} , and let P ( w 2 ) = # w 2 N {\displaystyle P(w_{2})={\frac {\#w_{2}}{N}}} be the unconditional probability of occurrence of w 2 {\displaystyle w_{2}} in the corpus. The t-score for the bigram w 1 w 2 {\displaystyle w_{1}w_{2}} is calculated as: where x ¯ = # w i w j N {\displaystyle {\bar {x}}={\frac {\#w_{i}w_{j}}{N}}} is the sample mean of the occurrence of w 1 w 2 {\displaystyle w_{1}w_{2}} , # w 1 w 2 {\displaystyle \#w_{1}w_{2}} is the number of occurrences of w 1 w 2 {\displaystyle w_{1}w_{2}} , μ = P ( w i ) P ( w j ) {\displaystyle \mu =P(w_{i})P(w_{j})} is the probability of w 1 w 2 {\displaystyle w_{1}w_{2}} under the null-hypothesis that w 1 {\displaystyle w_{1}} and w 2 {\displaystyle w_{2}} appear independently in the text, and s 2 = x ¯ ( 1 − x ¯ ) ≈ x ¯ {\displaystyle s^{2}={\bar {x}}(1-{\bar {x}})\approx {\bar {x}}} is the sample variance. With a large N {\displaystyle N} , the t-test is equivalent to a Z-test.

  Read more →
• 

  Best AI Code-review Tools in 2026

  Looking for the best AI code-review tool? An AI code-review tool is software that uses machine learning to help you get more done — it can save you hours every week by automating repetitive work. Most options offer a generous free tier, with paid plans unlocking higher limits, faster processing, and team features. Whether you are a beginner or a pro, the right AI code-review tool 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 →
• 

  Reciprocal human machine learning

  Reciprocal Human Machine Learning (RHML) is an interdisciplinary approach to designing human-AI interaction systems. RHML aims to enable continual learning between humans and machine learning models by having them learn from each other. This approach keeps the human expert "in the loop" to oversee and enhance machine learning performance and simultaneously support the human expert continue learning. == Background == RHML emerged in the context of the rise of big data analytics and artificial intelligence for intelligent tasks like sense-making and decision-making. As machine learning advanced to take on more roles, researchers realized fully autonomous systems had limitations and needed human guidance. RHML extends the concept of human-in-the-loop systems by promoting reciprocal learning. Humans learn from their interactions with machine learning models, staying up-to-date on evolving technology. The models also learn from human feedback and oversight. This amplification of learning on both sides is a key focus of RHML. The approach draws on theories of learning in dyads from education and psychology. It also builds on human-computer interaction and human-centered design principles. Implementing RHML requires developing specialized tools and interfaces tailored to the application == Applications == RHML has been explored across diverse domains including: Cybersecurity - Software to enable reciprocal learning between experts and AI models for social media threat detection. Organizational decision-making - RHML to structure collaboration between humans and AI systems. Workplace training - Using RHML for workers to learn from AI technologies on the job. Open science - Using human and AI collaboration to promote open science. Production and logistics - turning workers and intelligent machines into teammates. RHML maintains human oversight and control over AI systems, while enabling cutting-edge machine learning performance. This collaborative approach highlights the importance of keeping the human expert involved in the loop. An example of RHML in application is Free Spirit (AFSFCV), an open-source architecture first published in early 2025 as a whitepaper, proposing a visually structured approach to intent-based human–AI interaction.

  Read more →
• 

  Is an AI Sales Assistant Worth It in 2026?

  Shopping for the best AI sales assistant? An AI sales assistant is software that uses machine learning to help you get more done — it keeps getting smarter as the underlying models improve. Pricing, accuracy, and the size of the model behind the tool are the three factors that most affect daily usefulness. Whether you are a beginner or a pro, the right AI sales assistant slots into your workflow and pays for itself fast. Below we compare features, pricing, and real output so you can choose with confidence.

  Read more →
• 

  Philipp Koehn

  Philipp Koehn (born 1 August 1971 in Erlangen, West Germany) is a computer scientist and researcher in the field of machine translation. His primary research interest is statistical machine translation and he is one of the inventors of a method called phrase based machine translation. This is a sub-field of statistical translation methods that employs sequences of words (or so-called "phrases") as the basis of translation, expanding the previous word based approaches. A 2003 paper which he authored with Franz Josef Och and Daniel Marcu called Statistical phrase-based translation has attracted wide attention in Machine translation community and has been cited over a thousand times. Phrase based methods are widely used in machine translation applications in industry. Philipp Koehn received his PhD in computer science in 2003 from the University of Southern California, where he worked at the Information Sciences Institute advised by Kevin Knight. After a year as a postdoctoral fellow under Michael Collins at the Massachusetts Institute of Technology, he joined the University of Edinburgh as a lecturer in the School of Informatics in 2005. He was appointed reader in 2010 and professor in 2012. In 2014, he was appointed professor at the computer science department of The Johns Hopkins University, where he is affiliated with the Center for Language and Speech Processing. == Moses statistical machine translation decoder == The Moses machine translation decoder is an open source project that was created by and is maintained under the guidance of Philipp Koehn. The Moses decoder is a platform for developing Statistical machine translation systems given a parallel corpus for any language pair. The decoder was mainly developed by Hieu Hoang and Philipp Koehn at the University of Edinburgh and extended during a Johns Hopkins University Summer Workshop and further developed under Euromatrix and GALE project funding. The decoder (which is part of a complete statistical machine translation toolkit) is the de facto benchmark for research in the field. Although Koehn continues to play a major role in the development of Moses, the Moses decoder was supported by the European Framework 6 projects Euromatrix, TC-Star, the European Framework 7 projects EuroMatrixPlus, Let's MT, META-NET and MosesCore and the DARPA GALE project, as well as several universities such as the University of Edinburgh, the University of Maryland, ITC-irst, Massachusetts Institute of Technology, and others. Substantial additional contributors to the Moses decoder include Hieu Hoang, Chris Dyer, Josh Schroeder, Marcello Federico, Richard Zens, and Wade Shen. == Europarl corpus == The Europarl corpus is a set of documents that consists of the proceedings of the European Parliament from 1996 to the present. The corpus has been compiled and expanded by a group of researchers led by Philipp Koehn at University of Edinburgh. The data that makes up the corpus was extracted from the website of the European Parliament and then prepared for linguistic research. The latest release (2012) comprised up to 60 million words per language, with 21 European languages represented: Romanic (French, Italian, Spanish, Portuguese, Romanian), Germanic (English, Dutch, German, Danish, Swedish), Slavic (Bulgarian, Czech, Polish, Slovak, Slovene), Finno-Ugric (Finnish, Hungarian, Estonian), Baltic (Latvian, Lithuanian), and Greek. == Other interests and activities in chronological order == Koehn is a professor at Johns Hopkins University where he continues his research into machine translation through his affiliation with the Center for Language and Speech Processing Koehn is a professor and chair of machine translation at the University of Edinburgh School of Informatics and contributes to its statistical machine translation group which organises workshops, seminars and project related to the subject. Koehn has consulted to SYSTRAN periodically between 2006 and 2011. SYSTRAN was acquired by CLSI, a Korean machine translation company in April 2014. Koehn worked for Facebook/META AI Research from 2018 to 2022. Koehn is also chief scientist for Omniscien Technologies and a shareholder in Omniscien Technologies since 2007. Omniscien Technologies is a private company developing and commercialising machine translation technologies. Koehn authored a book titled "Statistical Machine Translation" in 2009 and a book titled "Neural Machine Translation" in 2020. == Awards and recognition == 2013: One of three finalists in the category of Research for the European Patent Office (EPO) 2013 European Inventor Award. Koehn was recognised for patent EP 1488338 B, Phrase-Based Joint Probability Model for Statistical Machine Translations, a translation model that uses mathematical probabilities to determine the most likely interpretation of chunks of text between foreign languages. 2015: Koehn received the Award of Honor of the International Association for Machine Translation. 2024: Koehn was named Fellow of the Association for Computational Linguistics (ACL).

  Read more →
• 

  Jürgen Schmidhuber

  Jürgen Schmidhuber (born 17 January 1963) is a German computer scientist noted for his work in the field of artificial intelligence, specifically artificial neural networks. He has been described by media outlets as a leading pioneer of modern artificial intelligence. He is a scientific director of the Dalle Molle Institute for Artificial Intelligence Research in Switzerland. He is also director of the Artificial Intelligence Initiative and professor of the Computer Science program in the Computer, Electrical, and Mathematical Sciences and Engineering (CEMSE) division at the King Abdullah University of Science and Technology (KAUST) in Saudi Arabia. He is best known for his work on long short-term memory (LSTM), a type of neural network architecture which was the dominant technique for various natural language processing tasks in research and commercial applications in the 2010s. He also introduced principles of dynamic neural networks, meta-learning, generative adversarial networks and linear transformers, all of which are widespread in modern AI. == Career == Schmidhuber completed his undergraduate (1987) and PhD (1991) studies at the Technical University of Munich in Munich, Germany. His PhD advisors were Wilfried Brauer and Klaus Schulten. He taught there from 2004 until 2009. From 2009 to 2021, he was a professor of artificial intelligence at the Università della Svizzera Italiana in Lugano, Switzerland. He has served as the director of Dalle Molle Institute for Artificial Intelligence Research (IDSIA), a Swiss AI lab, since 1995. Since 2021, he has also been the director of the AI Initiative at the King Abdullah University of Science and Technology (KAUST). In 2014, Schmidhuber formed a company, NNAISENSE, to work on commercial applications of artificial intelligence in fields such as finance, heavy industry and self-driving cars. Sepp Hochreiter, Jaan Tallinn, and Marcus Hutter are advisers to the company. Sales were under US$11 million in 2016; however, Schmidhuber states that the current emphasis is on research and not revenue. NNAISENSE raised its first round of capital funding in January 2017. Schmidhuber's overall goal is to create an all-purpose AI by training a single AI in sequence on a variety of narrow tasks, but as of 2026 he has said that the focus of NNAISENSE has shifted from artificial general intelligence to asset management. == Research == In the 1980s, backpropagation did not work well for deep learning with long credit assignment paths in artificial neural networks. To overcome this problem, Schmidhuber (1991) proposed a hierarchy of recurrent neural networks (RNNs) pre-trained one level at a time by self-supervised learning. It uses predictive coding to learn internal representations at multiple self-organizing time scales, facilitating downstream deep learning. The RNN hierarchy can be collapsed into a single RNN, by distilling a higher level chunker network into a lower level automatizer network. In 1993, a chunker solved a deep learning task whose depth exceeded 1000. In 1991, Schmidhuber published adversarial neural networks that contest with each other in the form of a zero-sum game, where one network's gain is the other network's loss. The first network is a generative model that models a probability distribution over output patterns. The second network learns by gradient descent to predict the reactions of the environment to these patterns. This was called "artificial curiosity". In 2014, this principle was used in the creation of the generative adversarial network, which Schmidhuber describes as a special case of artificial curiosity where the environmental reaction is 1 or 0 depending on whether the first network's output is in a given set. Schmidhuber supervised the 1991 diploma thesis of his student Sepp Hochreiter which he considered "one of the most important documents in the history of machine learning". It studied the neural history compressor and analyzed and overcame the vanishing gradient problem. This led to the creation of long short-term memory (LSTM), a type of recurrent neural network. The name LSTM was introduced in a tech report in 1995, leading to the most cited LSTM publication, published in 1997 and co-authored by Hochreiter and Schmidhuber. The standard LSTM architecture was introduced in 2000 by Felix Gers, Schmidhuber, and Fred Cummins. Today's "vanilla LSTM" using backpropagation through time was published with his student Alex Graves in 2005, and its connectionist temporal classification (CTC) training algorithm in 2006. CTC was applied to end-to-end speech recognition with LSTM. In 2014, the state of the art was training “very deep neural network” with 20 to 30 layers. Stacking too many layers led to a steep reduction in training accuracy, known as the "degradation" problem. In May 2015, Rupesh Kumar Srivastava, Klaus Greff, and Schmidhuber used LSTM principles to create the highway network, a feedforward neural network with hundreds of layers, much deeper than previous networks. In Dec 2015, the residual neural network (ResNet) was published, which is a variant of the highway network. In 1992, Schmidhuber published fast weights programmer, an alternative to recurrent neural networks. It has a slow feedforward neural network that learns by gradient descent to control the fast weights of another neural network through outer products of self-generated activation patterns, and the fast weights network itself operates over inputs. This was later shown to be equivalent to the unnormalized linear transformer. In 2011, Schmidhuber's team at IDSIA with his postdoc Dan Ciresan also achieved dramatic speedups of convolutional neural networks (CNNs) using graphics processing units (GPUs), based on CNN designs introduced much earlier by Kunihiko Fukushima. An earlier CNN on GPU by Chellapilla et al. (2006) was 4 times faster than an equivalent implementation on CPU. The deep CNN of Dan Ciresan et al. (2011) at IDSIA was 60 times faster and achieved the first superhuman performance in a computer vision contest in August 2011. Between 15 May 2011 and 10 September 2012, these CNNs won four more image competitions and improved the state of the art on multiple image benchmarks. The approach has become central to the field of computer vision. == Credit disputes == Schmidhuber has controversially argued that he and other researchers have been denied adequate recognition for their contribution to the field of deep learning, in favour of Geoffrey Hinton, Yoshua Bengio and Yann LeCun, who shared the 2018 Turing Award for their work in deep learning. He wrote a "scathing" 2015 article arguing that Hinton, Bengio and LeCun "heavily cite each other" but "fail to credit the pioneers of the field". In a statement to the New York Times, Yann LeCun wrote that "Jürgen is manically obsessed with recognition and keeps claiming credit he doesn't deserve for many, many things... It causes him to systematically stand up at the end of every talk and claim credit for what was just presented, generally not in a justified manner." Schmidhuber replied that LeCun did this "without any justification, without providing a single example", and published details of numerous priority disputes with Hinton, Bengio and LeCun. The term "schmidhubered" has been jokingly used in the AI community to describe Schmidhuber's habit of publicly challenging the originality of other researchers' work, a practice seen by some in the AI community as a "rite of passage" for young researchers. Some suggest that Schmidhuber's significant accomplishments have been underappreciated due to his confrontational personality. == Recognition == Schmidhuber received the Helmholtz Award of the International Neural Network Society in 2013, and the Neural Networks Pioneer Award of the IEEE Computational Intelligence Society in 2016 for "pioneering contributions to deep learning and neural networks." He is a member of the European Academy of Sciences and Arts. He has been referred to as the "father of modern AI", the "father of generative AI", and the "father of deep learning". Schmidhuber himself, however, has called Alexey Grigorevich Ivakhnenko the "father of deep learning", and gives credit to many even earlier AI pioneers. The New York Times ran a profile under the headline "When A.I. Matures, It May Call Jürgen Schmidhuber 'Dad'", highlighting his early work on deep learning and his long‑term vision for self‑improving AI. == Views == Schmidhuber is a proponent of open source AI, and believes that they will become competitive against commercial closed-source AI. Since the 1970s, Schmidhuber wanted to create "intelligent machines that could learn and improve on their own and become smarter than him within his lifetime." He differentiates between two types of AIs: tool AI, such as those for improving healthcare, and autonomous AIs that set their own goals, perform their own research, and explore the universe. He has worked on both types for de

  Read more →
• 

  Wix.com

  Wix.com Ltd. (Hebrew: וויקס.קום, romanized: wix.com) or simply Wix is an Israeli software company, publicly listed in the US, that provides cloud-based web development services. It offers tools for creating HTML5 websites for desktop and mobile platforms using online drag-and-drop editing. Along with its headquarters and other offices in Israel, Wix also has offices in Brazil, Canada, Germany, India, Ireland, Japan, Lithuania, Poland, the Netherlands, the United States, Ukraine, and Singapore. Users can add applications for social media, e-commerce, online marketing, contact forms, e-mail marketing, and community forums to their websites. The Wix website builder is built on a freemium business model, earning its revenues through premium upgrades. According to the W3Techs technology survey website, Wix was used by 2.5% of websites as of September 2023; at the end of May 2025, it was 3.8%. == History == === Corporate affairs === Wix was founded in 2006 by Israeli developers Avishai Abrahami, Nadav Abrahami, and Giora Kaplan. With its main offices in Tel Aviv, Wix was backed by investors Insight Venture Partners, Mangrove Capital Partners, Bessemer Venture Partners, DAG Ventures, and Benchmark Capital. By April 2010, Wix had 3.5 million users and raised US$10 million in Series C funding provided by Benchmark Capital and existing investors Bessemer Venture Partners and Mangrove Capital Partners. In March 2011, Wix had 8.5 million users and raised US$40 million in Series D funding, bringing its total funding to that date to US$61 million. By August 2013, the Wix platform had more than 34 million registered users. On 5 November 2013, Wix had an initial public offering on NASDAQ, raising about US$127 million for the company and some share holders. In 2016, Mark Tluszcz became the chair of the board of directors. In 2020, Wix's revenue increased to $989 million, a 30% rise year-on-year, primarily due to the shift of businesses online during the coronavirus pandemic. The company added over 31 million new registered users in 2020, reaching a total of 196.7 million by year's end. Wix added approximately 1 million net new premium subscriptions in 2020, surpassing $1 billion in annual collections for the first time. By the end of the year, there were 5.5 million premium subscriptions, a 22% increase compared to the end of 2019. As of its most recent reporting in June 2024, Wix has over 260 million users worldwide. === Product development === ==== 2000s ==== Wix entered an open beta phase in 2007 using a platform based on Adobe Flash. ==== 2010s ==== In June 2011, Wix launched the Facebook store module, making its first step into social commerce. In March 2012, Wix launched a new HTML5 site builder, replacing the Adobe Flash technology. In October 2012, Wix launched an app market for users to sell applications built with the company's automated web development technology. In August 2014, Wix launched Wix Hotels, a booking system for hotels, bed and breakfasts, and vacation rentals that use Wix websites. In June 2016, Wix introduced Wix ADI (Artificial Design Intelligence), a platform that uses artificial intelligence to design websites. ==== 2020s ==== In 2020, Wix launched an additional CMS, EditorX, which included additional CSS features to the original builder. In July 2023, Wix announced that it would be building on its ADI technology to create an AI powered website generator In October 2023, Wix launched the Wix Studio website builder. Co-founder and CEO, Avishai Abrahami described the platform as a “product for agencies”. In March 2024, the AI web builder, which uses a chatbot to help users create content was launched to the public. In March 2025, the digital publisher CNET has identified Wix as the "Best overall website builder overall." In August 2025, Wix announced it would launch banking services—including checking accounts and loans for small businesses—via a partnership with Israeli fintech Unit Finance, as it sought to diversify amid what it described as threats to its core website-building business from artificial intelligence. In January 2026, Wix launched Wix Harmony. Wix harmony is an AI website builder that uses agentic technology, generative design and vibe coding—with manual editing features for additional control. In May 2026, Wix announced layoffs affecting approximately 1,000 employees, or 20% of its workforce. CEO Avishai Abrahami cited two factors: the need to restructure around artificial intelligence and the appreciation of the Israeli shekel against the US dollar, which increased the cost of its Israel-based workforce relative to its dollar-denominated revenue. === Acquisitions === In April 2014, Wix announced the acquisition of Appixia, an Israeli startup for creating native mobile commerce (mCommerce) apps. In October 2014, Wix announced its acquisition of OpenRest, a developer of online ordering systems for restaurants. In April 2015, Wix acquired Moment.me, a mobile website builder for events and marketing tools for social lead generation. On 23 February 2017, Wix acquired the online art community DeviantArt for US$36 million. In January 2017, the company acquired Flok, a provider of customer loyalty programs tools. In February 2020, Wix acquired Inkfrog for eBay sellers, a web design company that provides customized business management software for eBay sellers. On 2 March 2021, Wix acquired SpeedETab, a Miami-based restaurant online technology provider. In May 2021, Wix acquired Rise.ai, a gift card and customer re-engagement package for online brands. A month later, Wix acquired Modalyst, a marketplace and drop-shipping platform. In May 2025, Wix acquired Hour One, a startup specializing in AI-powered video creation tools, to enhance its generative AI capabilities. In June 2025, the company acquired Base44, owned by independent entrepreneur Maor Shlomo, with the intention of integrating Base44's artificial intelligence capabilities and conversational interface into Wix's website and app building platform. == Description == Wix uses a freemium business model. Users can create websites for free then must purchase premium packages to connect their sites to their own domains, remove Wix ads, access the form builder, add e-commerce capabilities, or buy extra data storage and bandwidth. Wix provides customizable website templates and a drag-and-drop HTML5 website builder that includes apps, graphics, image galleries, fonts, vectors, animations, and other options. Users also may opt to create their web sites from scratch. In October 2013, Wix introduced a mobile editor for mobile viewing customization. Wix App Market offers both free and subscription-based applications, with a revenue split of 80% for the developer and 20% for Wix. Customers can integrate third-party applications into their own web sites, such as photograph feeds, blogging, music playlists, online community, e-mail marketing, and file management. Custom JavaScript code can be inserted into Wix webpages using the Velo API. == Controversies == === Use of WordPress code === In October 2016, there was a controversy over Wix's use of WordPress's GPL-licensed code. In response, Avishai Abrahami, Wix's CEO, published a response describing which open-source code was used and how Wix says it collaborates with the open-source community. However, it was subsequently noted that collaboration with the open-source community was not sufficient under the terms of the GPL license, which requires any code built on GPL-licensed code to be released under the same license. === Censorship === On 31 May 2021, 2021 Hong Kong Charter, a Wix-hosted website run by exiled Hong Kong activists, was shut down at the request of the Hong Kong Police. This was the first known case of Hong Kong's National Security Law being used to censor content on an overseas website. Wix later apologized for "mistakenly removing the website" and reinstated the website after it had been down for four days. In October 2023, Wix fired an employee in Dublin, Ireland, for having made social media posts critical of Israel. This incident led to criticism of Wix from members of the Oireachtas (the Irish parliament) and from the head of the Irish government, Taoiseach Leo Varadkar, who said it was "not okay to dismiss somebody because of their political views". Deputy head of government, Tánaiste Micheál Martin, also condemned their dismissal, stating "we tolerate debate with freedom of speech, freedom of opinion, and people have different opinions on these issues." The dismissed employee, Courtney Carey, successfully sued the company for unfair dismissal. Wix did not contest the charge, admitting liability. === Outreach abroad === In October 2023, The Irish Times reported that an Israeli advertising agency advised Wix staff how they can tailor posts for "outreach abroad". This included advice for Wix employees to “show Westernity” in social media posts supporting Israel, stating that “unlike the Gazans,

  Read more →
• 

  FastText

  fastText is a library for learning of word embeddings and text classification created by Facebook's AI Research (FAIR) lab. The model allows one to create an unsupervised learning or supervised learning algorithm for obtaining vector representations for words. Facebook makes available pretrained models for 294 languages. Several papers describe the techniques used by fastText. The GitHub repository was archived on March 19, 2024.

  Read more →
• 

  The Best Free AI Art Generator for Beginners

  Trying to pick the best AI art generator? An AI art generator 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 art generator 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 →
• 

  Maghi King

  Margaret (Maghi) Daniel King is a retired British computational linguist known for her work on evaluating the quality of machine translation. She is an honorary professor in the Department of Translation Technology of the University of Geneva in Switzerland, and the former director of the Dalle Molle Institute for Semantic and Cognitive Studies at the University of Geneva. == Education and career == King read classics, Ancient History and Philosophy (Greats) at the University of Oxford, worked as a computer programmer, and became a lecturer in the Department of Computation at the University of Manchester Institute of Science and Technology. She moved to the Dalle Molle Institute for Semantic and Cognitive Studies (ISSCO) in 1974. In 1976, ISSCO became part of the University of Geneva, and she continued there, becoming ISSCO's director in 1978. She remained director until her retirement in 2006. == Recognition == King is a Fellow of the European Association for Artificial Intelligence (formerly ECCAI), elected in 1999.

  Read more →
• 

  Flok (company)

  Flok (formerly Loyalblocks) was an American tech startup based in New York City that provides marketing services such as chatbots/AI, customer loyalty programs, mobile apps and CRM services to local businesses. In January 2017, the company was acquired by Wix.com. Around March 2017, Flok ceased regular communication. At some point in 2019 Flok communicated to its customers that it would shut down in March 2020. == Background == Flok was founded in 2011 by Ido Gaver and Eran Kirshenboim and has offices in Tel Aviv, Israel. In May 2013, Flok secured a $9 million Series A Round from General Catalyst Partners with participation from Founder Collective and existing investor Gemini Israel Ventures. In total, Flok has raised over $18 million in venture capital in three rounds. In May 2014, Flok announced a self-service loyalty platform for SMBs to build their own programs with beacon integration. At that time, approximately 40,000 businesses were using the service. In 2016, Flok released a turnkey chatbot service for local businesses, and was featured in AdWeek for developing the first weed bot chatbot for a California cannabis business. == Services == Flok offered an eponymous customer-facing app, that consumers use to receive rewards and deals from partner businesses, and a Flok business app for merchants to manage the platform.

  Read more →
• 

  Mirella Lapata

  Mirella Lapata is a computer scientist and Professor in the School of Informatics at the University of Edinburgh. Working on the general problem of extracting semantic information from large bodies of text, Lapata develops computer algorithms and models in the field of natural language processing (NLP). == Education == Lapata obtained a Master of Arts (MA) degree from Carnegie Mellon University and subsequently earned a doctorate from the University of Edinburgh. Lapata's doctoral research investigated the acquisition of information from polysemous linguistic units using probabilistic methods supervised by Alex Lascarides, Chris Brew and Steve Finch. == Career and research == After her doctorate, Lapata assumed academic positions at Saarland University and at the Department of Computer Science at the University of Sheffield. At the University of Edinburgh she became a reader in the School of Informatics where she is a full Professor and holds a personal chair in natural language processing. Lapata is a member of the Human Communication Research Center and Institute for Language, Cognition and Computation, both in Edinburgh. Between 2015 and 2017, Lapata served as a member of the Royal Society Machine Learning Working Group. Recently Lapata was granted a European Research Council (ERC) Consolidator Grant worth €1.9M to fund five years of her project, TransModal: Translating from Multiple Modalities into Text. === Awards and honours === In 2009 Lapata became the first recipient of the Microsoft British Computer Society (BCS)/BCS IRSG Karen Spärck Jones Award. The award recognises achievement in furthering the progress in information retrieval and natural language processing; the award commemorates the life and work of Karen Spärck Jones. In 2012 Lapata won an Empirical Methods in Natural Language Processing (EMNLP)-CoNLL 2012 Best Reviewer Award. In 2018 Lapata was awarded, alongside Li Dong, an Association for Computational Linguistics (ACL) Best Paper Honorable Mention. In 2019 Lapata was elected a Fellow of the Royal Society of Edinburgh In 2020 Lapata was elected to the Academia Europaea. In 2025 Lapata was awarded the BCS Lovelace Medal for Computing Research.

  Read more →
• 

  Sequential minimal optimization

  Sequential minimal optimization (SMO) is an algorithm for solving the quadratic programming (QP) problem that arises during the training of support-vector machines (SVM). It was invented by John Platt in 1998 at Microsoft Research. SMO is widely used for training support vector machines and is implemented by the popular LIBSVM tool. The publication of the SMO algorithm in 1998 has generated a lot of excitement in the SVM community, as previously available methods for SVM training were much more complex and required expensive third-party QP solvers. == Optimization problem == Consider a binary classification problem with a dataset (x1, y1), ..., (xn, yn), where xi is an input vector and yi ∈ {-1, +1} is a binary label corresponding to it. A soft-margin support vector machine is trained by solving a quadratic programming problem, which is expressed in the dual form as follows: max α ∑ i = 1 n α i − 1 2 ∑ i = 1 n ∑ j = 1 n y i y j K ( x i , x j ) α i α j , {\displaystyle \max _{\alpha }\sum _{i=1}^{n}\alpha _{i}-{\frac {1}{2}}\sum _{i=1}^{n}\sum _{j=1}^{n}y_{i}y_{j}K(x_{i},x_{j})\alpha _{i}\alpha _{j},} subject to: 0 ≤ α i ≤ C , for i = 1 , 2 , … , n , {\displaystyle 0\leq \alpha _{i}\leq C,\quad {\mbox{ for }}i=1,2,\ldots ,n,} ∑ i = 1 n y i α i = 0 {\displaystyle \sum _{i=1}^{n}y_{i}\alpha _{i}=0} where C is an SVM hyperparameter and K(xi, xj) is the kernel function, both supplied by the user; and the variables α i {\displaystyle \alpha _{i}} are Lagrange multipliers. == Algorithm == SMO is an iterative algorithm for solving the optimization problem described above. SMO breaks this problem into a series of smallest possible sub-problems, which are then solved analytically. Because of the linear equality constraint involving the Lagrange multipliers α i {\displaystyle \alpha _{i}} , the smallest possible problem involves two such multipliers. Then, for any two multipliers α 1 {\displaystyle \alpha _{1}} and α 2 {\displaystyle \alpha _{2}} , the constraints are reduced to: 0 ≤ α 1 , α 2 ≤ C , {\displaystyle 0\leq \alpha _{1},\alpha _{2}\leq C,} y 1 α 1 + y 2 α 2 = k , {\displaystyle y_{1}\alpha _{1}+y_{2}\alpha _{2}=k,} and this reduced problem can be solved analytically: one needs to find a minimum of a one-dimensional quadratic function. k {\displaystyle k} is the negative of the sum over the rest of terms in the equality constraint, which is fixed in each iteration. The algorithm proceeds as follows: Find a Lagrange multiplier α 1 {\displaystyle \alpha _{1}} that violates the Karush–Kuhn–Tucker (KKT) conditions for the optimization problem. Pick a second multiplier α 2 {\displaystyle \alpha _{2}} and optimize the pair ( α 1 , α 2 ) {\displaystyle (\alpha _{1},\alpha _{2})} . Repeat steps 1 and 2 until convergence. When all the Lagrange multipliers satisfy the KKT conditions (within a user-defined tolerance), the problem has been solved. Although this algorithm is guaranteed to converge, heuristics are used to choose the pair of multipliers so as to accelerate the rate of convergence. This is critical for large data sets since there are n ( n − 1 ) / 2 {\displaystyle n(n-1)/2} possible choices for α i {\displaystyle \alpha _{i}} and α j {\displaystyle \alpha _{j}} . == Related work == The first approach to splitting large SVM learning problems into a series of smaller optimization tasks was proposed by Bernhard Boser, Isabelle Guyon, and Vladimir Vapnik. It is known as the "chunking algorithm". The algorithm starts with a random subset of the data, solves this problem, and iteratively adds examples which violate the optimality conditions. One disadvantage of this algorithm is that it is necessary to solve QP-problems scaling with the number of SVs. On real world sparse data sets, SMO can be more than 1000 times faster than the chunking algorithm. In 1997, E. Osuna, R. Freund, and F. Girosi proved a theorem which suggests a whole new set of QP algorithms for SVMs. By the virtue of this theorem a large QP problem can be broken down into a series of smaller QP sub-problems. A sequence of QP sub-problems that always add at least one violator of the Karush–Kuhn–Tucker (KKT) conditions is guaranteed to converge. The chunking algorithm obeys the conditions of the theorem, and hence will converge. The SMO algorithm can be considered a special case of the Osuna algorithm, where the size of the optimization is two and both Lagrange multipliers are replaced at every step with new multipliers that are chosen via good heuristics. The SMO algorithm is closely related to a family of optimization algorithms called Bregman methods or row-action methods. These methods solve convex programming problems with linear constraints. They are iterative methods where each step projects the current primal point onto each constraint.

  Read more →