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.
Eigenmoments
EigenMoments is a set of orthogonal, noise robust, invariant to rotation, scaling and translation and distribution sensitive moments. Their application can be found in signal processing and computer vision as descriptors of the signal or image. The descriptors can later be used for classification purposes. It is obtained by performing orthogonalization, via eigen analysis on geometric moments. == Framework summary == EigenMoments are computed by performing eigen analysis on the moment space of an image by maximizing signal-to-noise ratio in the feature space in form of Rayleigh quotient. This approach has several benefits in Image processing applications: Dependency of moments in the moment space on the distribution of the images being transformed, ensures decorrelation of the final feature space after eigen analysis on the moment space. The ability of EigenMoments to take into account distribution of the image makes it more versatile and adaptable for different genres. Generated moment kernels are orthogonal and therefore analysis on the moment space becomes easier. Transformation with orthogonal moment kernels into moment space is analogous to projection of the image onto a number of orthogonal axes. Nosiy components can be removed. This makes EigenMoments robust for classification applications. Optimal information compaction can be obtained and therefore a few number of moments are needed to characterize the images. == Problem formulation == Assume that a signal vector s ∈ R n {\displaystyle s\in {\mathcal {R}}^{n}} is taken from a certain distribution having correlation C ∈ R n × n {\displaystyle C\in {\mathcal {R}}^{n\times n}} , i.e. C = E [ s s T ] {\displaystyle C=E[ss^{T}]} where E[.] denotes expected value. Dimension of signal space, n, is often too large to be useful for practical application such as pattern classification, we need to transform the signal space into a space with lower dimensionality. This is performed by a two-step linear transformation: q = W T X T s , {\displaystyle q=W^{T}X^{T}s,} where q = [ q 1 , . . . , q n ] T ∈ R k {\displaystyle q=[q_{1},...,q_{n}]^{T}\in {\mathcal {R}}^{k}} is the transformed signal, X = [ x 1 , . . . , x n ] T ∈ R n × m {\displaystyle X=[x_{1},...,x_{n}]^{T}\in {\mathcal {R}}^{n\times m}} a fixed transformation matrix which transforms the signal into the moment space, and W = [ w 1 , . . . , w n ] T ∈ R m × k {\displaystyle W=[w_{1},...,w_{n}]^{T}\in {\mathcal {R}}^{m\times k}} the transformation matrix which we are going to determine by maximizing the SNR of the feature space resided by q {\displaystyle q} . For the case of Geometric Moments, X would be the monomials. If m = k = n {\displaystyle m=k=n} , a full rank transformation would result, however usually we have m ≤ n {\displaystyle m\leq n} and k ≤ m {\displaystyle k\leq m} . This is specially the case when n {\displaystyle n} is of high dimensions. Finding W {\displaystyle W} that maximizes the SNR of the feature space: S N R t r a n s f o r m = w T X T C X w w T X T N X w , {\displaystyle SNR_{transform}={\frac {w^{T}X^{T}CXw}{w^{T}X^{T}NXw}},} where N is the correlation matrix of the noise signal. The problem can thus be formulated as w 1 , . . . , w k = a r g m a x w w T X T C X w w T X T N X w {\displaystyle {w_{1},...,w_{k}}=argmax_{w}{\frac {w^{T}X^{T}CXw}{w^{T}X^{T}NXw}}} subject to constraints: w i T X T N X w j = δ i j , {\displaystyle w_{i}^{T}X^{T}NXw_{j}=\delta _{ij},} where δ i j {\displaystyle \delta _{ij}} is the Kronecker delta. It can be observed that this maximization is Rayleigh quotient by letting A = X T C X {\displaystyle A=X^{T}CX} and B = X T N X {\displaystyle B=X^{T}NX} and therefore can be written as: w 1 , . . . , w k = a r g m a x x w T A w w T B w {\displaystyle {w_{1},...,w_{k}}={\underset {x}{\operatorname {arg\,max} }}{\frac {w^{T}Aw}{w^{T}Bw}}} , w i T B w j = δ i j {\displaystyle w_{i}^{T}Bw_{j}=\delta _{ij}} === Rayleigh quotient === Optimization of Rayleigh quotient has the form: max w R ( w ) = max w w T A w w T B w {\displaystyle \max _{w}R(w)=\max _{w}{\frac {w^{T}Aw}{w^{T}Bw}}} and A {\displaystyle A} and B {\displaystyle B} , both are symmetric and B {\displaystyle B} is positive definite and therefore invertible. Scaling w {\displaystyle w} does not change the value of the object function and hence and additional scalar constraint w T B w = 1 {\displaystyle w^{T}Bw=1} can be imposed on w {\displaystyle w} and no solution would be lost when the objective function is optimized. This constraint optimization problem can be solved using Lagrangian multiplier: max w w T A w {\displaystyle \max _{w}{w^{T}Aw}} subject to w T B w = 1 {\displaystyle {w^{T}Bw}=1} max w L ( w ) = max w ( w T A w − λ w T B w ) {\displaystyle \max _{w}{\mathcal {L}}(w)=\max _{w}(w{T}Aw-\lambda w^{T}Bw)} equating first derivative to zero and we will have: A w = λ B w {\displaystyle Aw=\lambda Bw} which is an instance of Generalized Eigenvalue Problem (GEP). The GEP has the form: A w = λ B w {\displaystyle Aw=\lambda Bw} for any pair ( w , λ ) {\displaystyle (w,\lambda )} that is a solution to above equation, w {\displaystyle w} is called a generalized eigenvector and λ {\displaystyle \lambda } is called a generalized eigenvalue. Finding w {\displaystyle w} and λ {\displaystyle \lambda } that satisfies this equations would produce the result which optimizes Rayleigh quotient. One way of maximizing Rayleigh quotient is through solving the Generalized Eigen Problem. Dimension reduction can be performed by simply choosing the first components w i {\displaystyle w_{i}} , i = 1 , . . . , k {\displaystyle i=1,...,k} , with the highest values for R ( w ) {\displaystyle R(w)} out of the m {\displaystyle m} components, and discard the rest. Interpretation of this transformation is rotating and scaling the moment space, transforming it into a feature space with maximized SNR and therefore, the first k {\displaystyle k} components are the components with highest k {\displaystyle k} SNR values. The other method to look at this solution is to use the concept of simultaneous diagonalization instead of Generalized Eigen Problem. === Simultaneous diagonalization === Let A = X T C X {\displaystyle A=X^{T}CX} and B = X T N X {\displaystyle B=X^{T}NX} as mentioned earlier. We can write W {\displaystyle W} as two separate transformation matrices: W = W 1 W 2 . {\displaystyle W=W_{1}W_{2}.} W 1 {\displaystyle W_{1}} can be found by first diagonalize B: P T B P = D B {\displaystyle P^{T}BP=D_{B}} . Where D B {\displaystyle D_{B}} is a diagonal matrix sorted in increasing order. Since B {\displaystyle B} is positive definite, thus D B > 0 {\displaystyle D_{B}>0} . We can discard those eigenvalues that large and retain those close to 0, since this means the energy of the noise is close to 0 in this space, at this stage it is also possible to discard those eigenvectors that have large eigenvalues. Let P ^ {\displaystyle {\hat {P}}} be the first k {\displaystyle k} columns of P {\displaystyle P} , now P T ^ B P ^ = D B ^ {\displaystyle {\hat {P^{T}}}B{\hat {P}}={\hat {D_{B}}}} where D B ^ {\displaystyle {\hat {D_{B}}}} is the k × k {\displaystyle k\times k} principal submatrix of D B {\displaystyle D_{B}} . Let W 1 = P ^ D B ^ − 1 / 2 {\displaystyle W_{1}={\hat {P}}{\hat {D_{B}}}^{-1/2}} and hence: W 1 T B W 1 = ( P ^ D B ^ − 1 / 2 ) T B ( P ^ D B ^ − 1 / 2 ) = I {\displaystyle W_{1}^{T}BW_{1}=({\hat {P}}{\hat {D_{B}}}^{-1/2})^{T}B({\hat {P}}{\hat {D_{B}}}^{-1/2})=I} . W 1 {\displaystyle W_{1}} whiten B {\displaystyle B} and reduces the dimensionality from m {\displaystyle m} to k {\displaystyle k} . The transformed space resided by q ′ = W 1 T X T s {\displaystyle q'=W_{1}^{T}X^{T}s} is called the noise space. Then, we diagonalize W 1 T A W 1 {\displaystyle W_{1}^{T}AW_{1}} : W 2 T W 1 T A W 1 W 2 = D A {\displaystyle W_{2}^{T}W_{1}^{T}AW_{1}W_{2}=D_{A}} , where W 2 T W 2 = I {\displaystyle W_{2}^{T}W_{2}=I} . D A {\displaystyle D_{A}} is the matrix with eigenvalues of W 1 T A W 1 {\displaystyle W_{1}^{T}AW_{1}} on its diagonal. We may retain all the eigenvalues and their corresponding eigenvectors since most of the noise are already discarded in previous step. Finally the transformation is given by: W = W 1 W 2 {\displaystyle W=W_{1}W_{2}} where W {\displaystyle W} diagonalizes both the numerator and denominator of the SNR, W T A W = D A {\displaystyle W^{T}AW=D_{A}} , W T B W = I {\displaystyle W^{T}BW=I} and the transformation of signal s {\displaystyle s} is defined as q = W T X T s = W 2 T W 1 T X T s {\displaystyle q=W^{T}X^{T}s=W_{2}^{T}W_{1}^{T}X^{T}s} . === Information loss === To find the information loss when we discard some of the eigenvalues and eigenvectors we can perform following analysis: η = 1 − t r a c e ( W 1 T A W 1 ) t r a c e ( D B − 1 / 2 P T A P D B − 1 / 2 ) = 1 − t r a c e ( D B ^ − 1 / 2 P ^ T A P ^ D B ^ − 1 / 2 ) t r a c e ( D B − 1 / 2 P T A P D B − 1 / 2 ) {\displaystyle {\begin{array}{lll}\eta &=&
AlphaGo Zero
AlphaGo Zero is a version of DeepMind's Go software AlphaGo. AlphaGo's team published an article in Nature in October 2017 introducing AlphaGo Zero, a version created without using data from human games, and stronger than any previous version. By playing games against itself, AlphaGo Zero: surpassed the strength of AlphaGo Lee in three days by winning 100 games to 0; reached the level of AlphaGo Master in 21 days; and exceeded all previous versions in 40 days. Training artificial intelligence (AI) without datasets derived from human experts has significant implications for the development of AI with superhuman skills, as expert data is "often expensive, unreliable, or simply unavailable." Demis Hassabis, the co-founder and CEO of DeepMind, said that AlphaGo Zero was so powerful because it was "no longer constrained by the limits of human knowledge". Furthermore, AlphaGo Zero performed better than standard deep reinforcement learning models (such as Deep Q-Network implementations) due to its integration of Monte Carlo tree search. David Silver, one of the first authors of DeepMind's papers published in Nature on AlphaGo, said that it is possible to have generalized AI algorithms by removing the need to learn from humans. Google later developed AlphaZero, a generalized version of AlphaGo Zero that could play chess and shōgi in addition to Go. In December 2017, AlphaZero beat the 3-day version of AlphaGo Zero by winning 60 games to 40, and with 8 hours of training it outperformed AlphaGo Lee on an Elo scale. AlphaZero also defeated a top chess program (Stockfish) and a top Shōgi program (Elmo). == Architecture == The network in AlphaGo Zero is a ResNet with two heads. The stem of the network takes as input a 17x19x19 tensor representation of the Go board. 8 channels are the positions of the current player's stones from the last eight time steps. (1 if there is a stone, 0 otherwise. If the time step go before the beginning of the game, then 0 in all positions.) 8 channels are the positions of the other player's stones from the last eight time steps. 1 channel is all 1 if black is to move, and 0 otherwise. The body is a ResNet with either 20 or 40 residual blocks and 256 channels. There are two heads, a policy head and a value head. Policy head outputs a logit array of size 19 × 19 + 1 {\displaystyle 19\times 19+1} , representing the logit of making a move in one of the points, plus the logit of passing. Value head outputs a number in the range ( − 1 , + 1 ) {\displaystyle (-1,+1)} , representing the expected score for the current player. -1 represents current player losing, and +1 winning. == Training == AlphaGo Zero's neural network was trained using TensorFlow, with 64 GPU workers and 19 CPU parameter servers. Only four TPUs were used for inference. The neural network initially knew nothing about Go beyond the rules. Unlike earlier versions of AlphaGo, Zero only perceived the board's stones, rather than having some rare human-programmed edge cases to help recognize unusual Go board positions. The AI engaged in reinforcement learning, playing against itself until it could anticipate its own moves and how those moves would affect the game's outcome. In the first three days AlphaGo Zero played 4.9 million games against itself in quick succession. It appeared to develop the skills required to beat top humans within just a few days, whereas the earlier AlphaGo took months of training to achieve the same level. According to Epoch.ai, training cost 3e23 FLOPs. For comparison, the researchers also trained a version of AlphaGo Zero using human games, AlphaGo Master, and found that it learned more quickly, but actually performed more poorly in the long run. DeepMind submitted its initial findings in a paper to Nature in April 2017, which was then published in October 2017. == Hardware cost == The hardware cost for a single AlphaGo Zero system in 2017, including the four TPUs, has been quoted as around $25 million. == Applications == According to Hassabis, AlphaGo's algorithms are likely to be of the most benefit to domains that require an intelligent search through an enormous space of possibilities, such as protein folding (see AlphaFold) or accurately simulating chemical reactions. AlphaGo's techniques are probably less useful in domains that are difficult to simulate, such as learning how to drive a car. DeepMind stated in October 2017 that it had already started active work on attempting to use AlphaGo Zero technology for protein folding, and stated it would soon publish new findings. == Reception == AlphaGo Zero was widely regarded as a significant advance, even when compared with its groundbreaking predecessor, AlphaGo. Oren Etzioni of the Allen Institute for Artificial Intelligence called AlphaGo Zero "a very impressive technical result" in "both their ability to do it—and their ability to train the system in 40 days, on four TPUs". The Guardian called it a "major breakthrough for artificial intelligence", citing Eleni Vasilaki of Sheffield University and Tom Mitchell of Carnegie Mellon University, who called it an impressive feat and an “outstanding engineering accomplishment" respectively. Mark Pesce of the University of Sydney called AlphaGo Zero "a big technological advance" taking us into "undiscovered territory". Gary Marcus, a psychologist at New York University, has cautioned that for all we know, AlphaGo may contain "implicit knowledge that the programmers have about how to construct machines to play problems like Go" and will need to be tested in other domains before being sure that its base architecture is effective at much more than playing Go. In contrast, DeepMind is "confident that this approach is generalisable to a large number of domains". In response to the reports, South Korean Go professional Lee Sedol said, "The previous version of AlphaGo wasn’t perfect, and I believe that’s why AlphaGo Zero was made." On the potential for AlphaGo's development, Lee said he will have to wait and see but also said it will affect young Go players. Mok Jin-seok, who directs the South Korean national Go team, said the Go world has already been imitating the playing styles of previous versions of AlphaGo and creating new ideas from them, and he is hopeful that new ideas will come out from AlphaGo Zero. Mok also added that general trends in the Go world are now being influenced by AlphaGo's playing style. "At first, it was hard to understand and I almost felt like I was playing against an alien. However, having had a great amount of experience, I’ve become used to it," Mok said. "We are now past the point where we debate the gap between the capability of AlphaGo and humans. It’s now between computers." Mok has reportedly already begun analyzing the playing style of AlphaGo Zero along with players from the national team. "Though having watched only a few matches, we received the impression that AlphaGo Zero plays more like a human than its predecessors," Mok said. Chinese Go professional Ke Jie commented on the remarkable accomplishments of the new program: "A pure self-learning AlphaGo is the strongest. Humans seem redundant in front of its self-improvement." == Comparison with predecessors == == AlphaZero == On 5 December 2017, DeepMind team released a preprint on arXiv, introducing AlphaZero, a program using generalized AlphaGo Zero's approach, which achieved within 24 hours a superhuman level of play in chess, shogi, and Go, defeating world-champion programs, Stockfish, Elmo, and 3-day version of AlphaGo Zero in each case. AlphaZero (AZ) is a more generalized variant of the AlphaGo Zero (AGZ) algorithm, and is able to play shogi and chess as well as Go. Differences between AZ and AGZ include: AZ has hard-coded rules for setting search hyperparameters. The neural network is now updated continually. Chess (unlike Go) can end in a tie; therefore AZ can take into account the possibility of a tie game. An open source program, Leela Zero, based on the ideas from the AlphaGo papers is available. It uses a GPU instead of the TPUs recent versions of AlphaGo rely on.
AlphaStar (software)
AlphaStar is an artificial intelligence (AI) software developed by DeepMind for playing the video game StarCraft II. It was unveiled to the public by name in January 2019. AlphaStar attained "Grandmaster" status in August 2019, considered a milestone for AI in video games at the time. == Background == Games created for humans are considered to have external validity as benchmarks of progress in artificial intelligence. IBM's chess engine Deep Blue (1997) and DeepMind's AlphaGo (2016) were considered major milestones; some argue that StarCraft would also be a major milestone, due to the game's "real-time play, partial observability, no single dominant strategy, complex rules that make it hard to build a fast forward model, and a particularly large and varied action space." Though difficult, StarCraft may still be tractable with current technology because "its rules are known and the world is discrete with only a few types of objects". StarCraft II is a popular fast-paced online real-time strategy game developed by Blizzard Entertainment. == History == DeepMind Technologies was founded in the UK in 2010. As early as 2011, founder Demis Hassabis called StarCraft "the next step up" after games like Go. DeepMind became a subsidiary of Google in 2014, after demonstrating self-learning bots with superhuman ability at a variety of Atari 2600 games. In February 2015, computer scientist Zachary Mason predicted Deepmind's research "leads to StarCraft in five or ten years". In March 2016, following AlphaGo's victory over Lee Sedol, a world champion Go player, Hassabis publicly mulled building an AI for StarCraft, citing it as a strategic game with incomplete information where, unlike Go, much of the "board" is invisible. A formal collaboration was announced at BlizzCon in November 2016, alongside a plan to release an open development environment for bots in Q1 of 2017. By 2017, DeepMind was experimenting with feeding StarCraft data into its software. In August 2017, DeepMind and Blizzard released development tools to assist in bot development, as well as data from 65,000 historical games. At the time, computer scientist and StarCraft tournament manager David Churchill estimated it would take five years for a bot to beat a human, but made the caveat that AlphaGo had beaten expectations. In Wired, tech journalist Tom Simonite stated "No one expects the robot to win anytime soon. But when it does, it will be a far greater achievement than DeepMind's conquest of Go." In December 2018, DeepMind's bot defeated professional player Grzegorz "MaNa" Komincz, 5-0. DeepMind announced the bot, named "AlphaStar", in January 2019. A journalist at Ars Technica and others argued that AlphaStar still had unfair advantages: "AlphaStar has the ability to make its clicks with surgical precision using an API, whereas human players are constrained by the mechanical limits of computer mice". AlphaStar also had a global view rather than being limited by the in-game camera. Furthermore, while there was a cap on the number of actions over a five-second window, AlphaStar was free to allocate its action quota unevenly across the window in order to launch superhuman bursts of activity at critical moments. DeepMind quickly retrained AlphaStar under more realistic constraints, and then lost a rematch with Komincz. Starting in July 2019, the new, constrained version of AlphaStar anonymously competed against players who "opted in" on the public 1v1 European multiplayer ladder. By the end of August 2019, AlphaStar had attained Grandmaster level, ranking among the top 0.2% of human players. == Algorithms == Unlike AlphaZero, AlphaStar initially learns to imitate the moves of the best players in its database of human vs. human games; this step is necessary to solve what DeepMind's Dave Silver calls "the exploration problem": discovering new strategies would otherwise be like finding a "needle in a haystack". Agents then play each other and deploy deep reinforcement learning. These main agents also learn by playing against suboptimal "exploiter agents" whose purpose is to expose weaknesses in the main agents. == Reactions == After his 5-0 defeat in December 2018, Komincz stated "I wasn't expecting the AI to be that good". Stuart Russell assessed that AlphaStar's 2018 victory required "a fair amount of problem-specific effort" and that general-purpose methods were "not quite ready for StarCraft". An article in Wired UK judged AlphaStar's new constraints, adopted for the July 2019 matches, to be "fair" this time around. StarCraft professional Raza "RazerBlader" Sekha stated AlphaStar was "impressive" but had its quirks, succumbing in one game to an unorthodox army composition made up of only air units. The UK's top player, Joshua "RiSky" Hayward, expressed some disappointment, saying AlphaStar "often didn't make the most efficient, strategic decisions". Professional Diego "Kelazhur" Schwimer called AlphaStar's play "unimaginably unusual; it really makes you question how much of StarCraft's diverse possibilities pro players have really explored". AlphaStar's opponents often did not realize they were playing a bot. Ian Sample, of The Guardian, called AlphaStar a "landmark achievement" for the field of AI. Churchill stated that he had previously seen bots that master one or two elements of StarCraft, but that AlphaStar was the first that can handle the game in its entirety. Gary Marcus expressed his continuing skepticism about deep learning, stating: "So far the field has struggled to take techniques like this out of the laboratory and game environments and into the real world, and I don't immediately see this result as progress in that direction". AI researcher Jon Dodge was surprised by AlphaStar, stating that he did not expect such a "superhuman" performance for "another couple of years"; in contrast, Churchill states "StarCraft is nowhere near being 'solved', and AlphaStar is not yet even close to playing at a world champion level". == Legacy == DeepMind argues that insights from AlphaStar might benefit robots, self-driving cars, and virtual assistants, which need to operate with "imperfectly observed information". Silver has indicated his lab "may rest at this point", rather than try to substantially improve AlphaStar. Silver himself argues that "AlphaStar has become the first AI system to reach the top tier of human performance in any professionally played e-sport on the full unrestricted game under professionally approved conditions... Ever since computers cracked Go, chess, and poker, the game of StarCraft has emerged, essentially by consensus from the community, as the next grand challenge for AI." Computer scientist Noel Sharkey argues, disapprovingly, that "military analysts will certainly be eyeing the successful AlphaStar real-time strategies as a clear example of the advantages of AI for battlefield planning". In contrast, Silver argues: "To say that this has any kind of military use is saying no more than to say an AI for chess could be used to lead to military applications".
Open Neural Network Exchange
The Open Neural Network Exchange (ONNX) [ˈɒnɪks] is an open-source artificial intelligence ecosystem of technology companies and research organizations that establish open standards for representing machine learning algorithms and software tools to enable a standard format for representing machine learning models. ONNX is available on GitHub. == History == ONNX was originally named Toffee and was developed by the PyTorch team at Facebook. In September 2017 it was renamed to ONNX and announced by Facebook and Microsoft. Later, IBM, Huawei, Intel, AMD, Arm and Qualcomm announced support for the initiative. In October 2017, Microsoft announced that it would add its Cognitive Toolkit and Project Brainwave platform to the initiative. In November 2019 ONNX was accepted as graduate project in Linux Foundation AI. In October 2020 Zetane Systems became a member of the ONNX ecosystem. == Intent == The initiative targets: === Framework interoperability === Enable developers to move machine learning models between different frameworks, which may be used at different stages of the development process, such as training, architecture design, or deployment on mobile devices. === Shared optimization === Provide a common representation that can be used by hardware vendors and other developers to apply optimizations to artificial neural network models across multiple machine learning frameworks. == Contents == ONNX provides definitions of an extensible computation graph model, built-in operators and standard data types, focused on inferencing (evaluation).. The container format is Protocol Buffers. Each computation dataflow graph is a list of nodes that form an acyclic graph. Nodes have inputs and outputs. Each node is a call to an operator. Metadata documents the graph. Built-in operators are to be available on each ONNX-supporting framework. ONNX models can be trained in a single framework, such as PyTorch or TensorFlow, and then exported to ONNX. This format allows models to be transferred from the training framework to other environments for testing or deployment. Once a model is in ONNX format, it can be executed in different runtime systems or on various hardware platforms, such as GPUs or specialized AI accelerators. Using a common format enables the same model representation to be used across multiple systems and frameworks.
Alias Eclipse
Eclipse was a professional 2D image editing program available on Silicon Graphics and Windows workstations. Designed to manipulate high-resolution images like digitized movie frames and photographs for print, it offered color correction tools, image processing effects, rudimentary paint features, and spline-based drawing and masking. == History == Eclipse was originally developed in the late 1980s by Full Color Computing, an early provider of photo retouch and color prepress software for Silicon Graphics workstations. Alias Research (later Alias Systems Corporation), a developer of professional 3D graphics applications for the SGI platform, purchased the rights to Eclipse in fall 1990. Alias developed Eclipse through the early to mid-1990s, releasing version 2.5 in 1995 with improvements to the speed of color correction, effects, and rendering. Xyvision's Contex Prepress division purchased exclusive rights to Eclipse from Alias in 1996, and released version 3.0 the following year. Eclipse was subsequently sold to German developer Form & Vision GmbH, which continued development and ported it to the Windows platform. In 1999, Form & Vision released a demo of Eclipse 3.1.3 on the SGI platform which was limited to 1600 x 1600 pixel images, then ceased development of Eclipse on the SGI platform. Eclipse was thereafter developed exclusively for the Windows platform, culminating with version 3.1.4 in 2001. In the same year the firm went bankrupt. == Features == Eclipse was designed to work with very large images that could not be manipulated in real time on contemporary computer systems due to memory limitations, and thus allowed the user to make modifications to a lower-resolution copy of the original image in "proxy mode." Brush strokes, color corrections, and other edits were saved in proxy mode, then applied to the full-size image in post processing. This method also allowed for batch processing of a high-resolution image sequence using the edits applied to the original proxy image. Other features included color correction and separation, warping, special effects, text, and shape masking. Wavelet image compression created by LuraTech was added to Eclipse 3.1.4
Andrej Karpathy
Andrej Karpathy (born 23 October 1986) is a Slovak-Canadian AI researcher, who co-founded and formerly worked at OpenAI, where he specialized in deep learning and computer vision. He also worked as the director of artificial intelligence and Autopilot Vision at Tesla, and in 2024 he founded Eureka Labs, an AI education platform. In 2026 he joined Anthropic as part of the pretraining team. == Education and early life == Karpathy was born in Bratislava, Czechoslovakia (now Slovakia), and moved with his family to Toronto when he was 15. He completed his Computer Science and Physics bachelor's degrees at University of Toronto in 2009 and his master's degree at University of British Columbia in 2011, where he worked on physically simulated figures (for example, a simulated runner or a simulated person in a crowd) with his adviser Michiel van de Panne. In 2006, Karpathy began posting videos on YouTube on his channel, badmephisto. He garnered fame by posting Rubik's cube tutorials which have been used by famous speedcubers such as Feliks Zemdegs. The channel has over 9 million views as of June 2025. Karpathy received a PhD from Stanford University in 2015 under the supervision of Fei-Fei Li, focusing on the intersection of natural language processing and computer vision, and deep learning models suited for this task. == Career and research == He authored and was the primary instructor of the first deep learning course at Stanford, CS 231n: Convolutional Neural Networks for Visual Recognition. The course became one of the largest classes at Stanford, growing from 150 students in 2015 to 750 in 2017. Karpathy is a founding member of the artificial intelligence research group OpenAI, where he was a research scientist from 2015 to 2017. In June 2017 he became Tesla's director of artificial intelligence and reported to Elon Musk. He was named one of MIT Technology Review's Innovators Under 35 for 2020. After taking a several-months-long sabbatical from Tesla, he announced he was leaving the company in July 2022. As of February 2023, he makes YouTube videos on how to create artificial neural networks. On February 9, 2023, Karpathy announced he was returning to OpenAI. A year later on February 13, 2024, an OpenAI spokesperson confirmed that Karpathy had left OpenAI. In the same year, he was named one of Time Magazine's 100 Most Influential People in AI. On July 16, 2024, Karpathy announced on his X account that he started a new AI education company called Eureka Labs. Their first product was the AI course, LLM101n. He also has a broader educational effort, the "Zero to Hero" series on LLM fundamentals. The company also advocates for AI teaching assistants, a concept which has been criticized due to data privacy concerns and the removal of personal connection between teacher and student. In February 2025, Karpathy coined the term vibe coding to describe how AI tools allow hobbyists to construct apps and websites just by typing prompts. On May 19, 2026, he announced that he joined Anthropic via a statement on X, while the company stated that he will be leading a team for research in pretraining.