AI Art Generator From Image

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

• 

  SQLBuddy

  SQL Buddy is an open-source web-based application primarily coded in PHP, that allows users to control both MySQL and SQLite database through a web browser. The project was well regarded for its easy installation process and the friendly user interface it offered. The application was further praised for its cross-platform compatibility, meaning users could manage their databases on various operating systems, including Linux, Windows, and macOS. The development of SQL Buddy has stopped, with version 1.3.3 being the final release on January 18, 2011. No further releases are expected.

  Read more →
• 

  VoID

  The Vocabulary of Interlinked Datasets (VoID) is a vocabulary for providing concise summaries (metadata) of Resource Description Framework (RDF) datasets—meaningful collections of semantic triples—using the syntax of RDF Schema. It can be used for general metadata (such as information about the license of the dataset), access metadata (information about how to access the dataset), structural metadata (information about how the dataset is structured), and linking metadata (information about links between datasets). A linked dataset is a collection of data, published and maintained by a single provider, available as RDF on the Web, where at least some of the resources in the dataset are identified by dereferencable Uniform Resource Identifiers (URIs). VoID is used to provide metadata on RDF datasets to facilitate query processing on a graph of interlinked datasets in the Semantic Web.

  Read more →
• 

  Alliance for Secure AI

  The Alliance for Secure AI is a U.S.-based nonprofit organization which educates the public about the risks of advanced artificial intelligence (AI). Politico has described the Alliance as a "bipartisan nonprofit trying to push a middle-ground approach to AI guardrails." == History == In June 2025, the Alliance was launched as a 501(c)(3) nonprofit watchdog in Washington, D.C. That same month, the organization rolled out a six-figure advertising campaign featuring bipartisan warnings about advanced AI. The ad campaign presented different messages for different political audiences. The Alliance opposed the idea of a moratorium on state AI laws as part of the July 2025 budget bill, in addition to President Donald Trump's December 2025 executive order on the issue. The group has also criticized AI companies like Meta and OpenAI for what it says are failures to prevent harms to children. In addition, the Alliance has criticized OpenAI for subpoenaing nonprofit organizations in the AI safety space. In March 2026, the Alliance launched JobLoss.ai, a website that tracks the jobs that have been eliminated with AI cited as a contributing factor. As of April 2026, JobLoss.ai has tracked more than 127,000 lost jobs. == Leadership == Brendan Steinhauser, a longtime political and communications strategist, is the founder and CEO of the Alliance. He was an early Tea Party movement organizer, and ran campaigns for multiple members of Congress, including Sen. John Cornyn, Rep. Dan Crenshaw, and Rep. Michael McCaul. Peyton Hornberger is the group's communications director. In July 2025, Hornberger criticized Palantir for its use of AI in a USA Today op-ed column.

  Read more →
• 

  Johns Hopkins Beast

  The Johns Hopkins Beast was a mobile automaton, an early pre-robot, built in the 1960s at the Johns Hopkins University Applied Physics Laboratory. The machine had a rudimentary intelligence and the ability to survive on its own. As it wandered through the white halls of the laboratory, it would seek black wall outlets. When it found one it would plug in and recharge. The robot was cybernetic. It did not use a computer. Its control circuitry consisted of dozens of transistors controlling analog voltages. It used photocell optics and sonar to navigate. The 2N404 transistors were used to create NOR logic gates that implemented the Boolean logic to tell it what to do when a specific sensor was activated. The 2N404 transistors were also used to create timing gates to tell it how long to do something. 2N1040 Power transistors were used to control the power to the motion treads, the boom, and the charging mechanism. The original sensors in Mod I were physical touch only. The wall socket was detected by physical switches on the arm that followed the wall. Once detected, two electrical prongs were extended until they entered the wall socket and made the electrical connection to charge the vehicle. The stairway, doors, and pipes on the hall wall were also detected by physical switches and recognized by appropriate logic. The sonar guidance system was developed for Mod I and improved for Mod II. It used two ultrasonic transducers to determine distance, location within the halls, and obstructions in its path. This provided "The Beast" with bat-like guidance. At this point, it could detect obstructions in the hallway, such as people. Once an obstruction was detected, the Beast would slow down and then decide whether to stop or divert around the obstruction. It could also ultrasonically recognize the stairway and doorways to take appropriate action. An optical guidance system was added to Mod II. This provided, among other capabilities, the ability to optically identify the black wall sockets that contrasted with the white wall. The Hopkins Beast Autonomous Robot Mod II link below was written by Dr. Ronald McConnell, at that time a co-op student and one of the designers for Mod II.

  Read more →
• 

  Figure AI

  Figure AI, Inc. is an American robotics company developing humanoid robots that operate via artificial intelligence. The company was founded in 2022 by Brett Adcock. As of late 2025, the company has a $39 billion valuation. Three generations of humanoid robots (Figure 01–03) have been developed, as well as two iterations of a vision-language-action model (Helix 01–02), which can control up to two robots at once. By 2026, the robots demonstrated the potential ability to perform household work and the company gained publicity when a Figure 03 appeared at a White House event. == History == Figure AI was founded in 2022 by Brett Adcock, also known for founding Archer Aviation and Vettery. That year, the company introduced its prototype, Figure 01, a bipedal robot designed for manual labor, initially targeting the logistics and warehousing sectors. The initial model utilized external cabling for easier maintenance. In May 2023, Figure AI raised $70 million from investors including Adcock, who invested $20 million, and Parkway Venture Capital. In January 2024, Figure AI announced a partnership with BMW to deploy humanoid robots in automotive manufacturing facilities. In February 2024, Figure AI secured $675 million in venture capital funding from a consortium that includes Jeff Bezos, Microsoft, Nvidia, Intel, and the startup-funding divisions of Amazon and OpenAI; the company was then valued at $2.6 billion. Figure AI also announced a partnership with OpenAI, which would build specialized artificial intelligence (AI) models for Figure AI's humanoid robots, enabling its robots to process language; the collaboration ended after a year, with Adcock stating that large language models had become a smaller problem compared to those allowing for "high rate robot control". In August 2024, the company introduced Figure 02, describing it as the next step toward deploying humanoids for industrial use. The machine has 35 degrees of freedom (DOF), while the five-fingered hands have 16 DOF and the ability to carry up to 25 kilograms (55 lb). The model is equipped with cabling integrated into the limbs, a torso-placed battery, six RGB cameras, and an onboard vision-language-action (VLA) model. It has three times the computing power (including inference AI) of the previous model, including two graphics processing units, supported by Nvidia. Microphones, speakers, and custom AI models (developed with OpenAI) enable communication with humans. In early 2025, Figure AI announced BotQ, a manufacturing facility aiming to produce 12,000 humanoids per year with the help of its own humanoid robots, and Helix, a VLA model that can control up to two robots at once. Helix enables a robot to interact with the world without extensive manual training, according to the company allowing it to pick up nearly any small household object. By April, the company issued cease-and-desist letters to at least two secondary brokers promoting its private stock without authorization. In September, a third round of financing exceeded $1 billion, raising the company's total valuation to $39 billion. Investors included Brookfield Asset Management, Intel, Macquarie Capital, Nvidia, Parkway Venture Capital, Qualcomm, Salesforce, and T-Mobile. In October 2025, Figure 03 was introduced. According to the company, its hardware and software redesign aims to create a general-purpose robot able to learn directly from humans. An upgraded camera system delivers twice the frame rate, a quarter the latency, and a 60% wider field of view, in addition to a camera in each hand. Tactile sensors in the fingertips can detect forces as little as 3 grams (0.1 oz). It incorporates soft materials and a protected battery for safety, and removable, washable textiles. It supports wireless inductive charging. In November 2025, the former head of product safety sued the company on the basis of being fired for raising the concern that the company's robots were strong enough to fracture a human skull. By early 2026, Figure 02 had been used in demonstrations showing that it could load a washing machine, sort packages, and fold laundry. That January, Helix 02 was released, expanding the AI model to the entire body to allow for functional autonomy. A Helix 02–powered Figure 02 was shown to be capable of loading and unloading a dishwasher, based on hours of motion-capture data and simulation-based machine learning. In March, U.S. First Lady Melania Trump appeared at the White House with a Figure 03, promoting the presumptive eventual ability of AI to teach children. In May 2026, Figure AI livestreamed a group of their robots processing packages nonstop for almost a week, inspiring a 10-hour competition between their robot and a human, in which the robot performed 98.5% as well as the human.

  Read more →
• 

  Public First Action

  Public First Action is a 501(c)(4) nonprofit organization focused on United States public policy related to artificial intelligence. Public First Action is a bipartisan group that advocates for AI transparency, safeguards, and export controls on advanced AI chips. The organization is aligned with the political action committees Jobs and Democracy, Defending Our Values and Public First. == History == Public First Action was formed in 2025 by former Congressmen Brad Carson, a Democrat, and Chris Stewart, a Republican, to advocate for federal, state, and local regulations related to AI. The group's formation followed the founding of a super PAC network, Leading the Future, which advocates for deregulation of the AI industry and faster development of the new technology. Public First Action supports measures that would increase transparency at frontier AI companies and impose export controls on advanced AI chips, in addition to opposing the preemption of state-level AI laws. In February 2026, Public First Action received $20 million from the AI company Anthropic. That same month, the group announced plans to support 30 to 50 Democrats and Republicans in state and federal races, with Public First Action and aligned super PACs launching advertisements in Nebraska, Tennessee, and other states. In one ad, Public First Action touted Senator Marsha Blackburn for her work on child online safety. As of 2026, the group plans to raise between $50 and $75 million for public oversight of AI and related reforms. == Organization == === Leadership and funding === Public First Action is led by Carson and Stewart. The group has raised nearly $50 million in funding with a goal of raising $75 million during the 2026 midterms. Anthropic has contributed $20 million to the group. === Structure === Public First Action is aligned with three political action committees: "Jobs and Democracy", which supports Democratic candidates; "Defending Our Values", which supports Republican candidates; and "Public First", which supports both Republicans and Democrats.

  Read more →
• 

  Inbenta

  Inbenta is an AI company that originated in Barcelona, Spain, in 2005. Inbenta is currently headquartered in Allen, Texas, with additional offices in Spain, São Paulo, Brazil, Toulouse, France, and Tokyo, Japan. Inbenta provides natural language processing and semantic search through artificial intelligence. == History == Inbenta raised $12 Million in their Series B funding round to extend the reach of their artificial intelligence for business solutions. In 2023 Inbenta's new chief executive officer Melissa Solis moved Inbenta's headquarters to One Bethany West in Allen, Texas from Foster City, California. == Controversy == On 23 June 2018, Ticketmaster UK identified malicious software on a customer support product hosted by Inbenta Technologies, compromising personal data and payment details for thousands of Ticketmaster customers. Three days later, Inbenta's CEO Issued a message about the incident to convey the full scope of the breach. Also on its FAQ section, Inbenta claimed that "After a careful analysis of all clues and snapshots from our systems, the technical team at Inbenta discovered that the script had been implemented on the payment page. We were unaware of this, and would have advised against doing so had we known, as it presents a point of vulnerability". On November 13, 2020, the Information Commissioner's Office fined Ticketmaster UK Limited £1.25 million for failing to protect customers' payment details. According to the ICO, "It was because of Ticketmaster's business decision to include the [Inbenta] chat bot on its payment page that the chat bot was able to unlawfully process the personal data of customers."

  Read more →
• 

  Fei-Fei Li

  Fei-Fei Li (Chinese: 李飞飞; pinyin: Lǐ Fēifēi; born July 3, 1976) is a Chinese-born American computer scientist best known for establishing ImageNet, the dataset that enabled rapid advances in computer vision in the 2010s. She is a professor of computer science at Stanford University, with research expertise in artificial intelligence, machine learning, deep learning, computer vision, and cognitive neuroscience. Li is a co-director of the Stanford Institute for Human-Centered Artificial Intelligence and a co-director of the Stanford Vision and Learning Lab, and served as Chief Scientist of AI/ML at Google Cloud and the director of the Stanford Artificial Intelligence Laboratory from 2013 to 2018. In 2017, she co-founded AI4ALL, a nonprofit organization working to increase diversity in the field of artificial intelligence. In 2023, Li was named one of the Time 100 AI Most Influential People. Li received the Intel Lifetime Achievements Innovation Award in 2017 for her contributions to artificial intelligence, and was elected member of the National Academy of Engineering, the National Academy of Medicine in 2020 and the American Academy of Arts and Sciences in 2021. In 2025, she was named as one of the "Architects of AI" for Time's Person of the Year. On August 3, 2023, Li was appointed to the United Nations Scientific Advisory Board, established by Secretary-General Antonio Guterres. In 2024, Li was included on the Gold House's most influential Asian A100 list. In 2024, she raised $230 million for a startup called World Labs, which she and three colleagues founded to develop a "spatial intelligence" AI technology that can understand how the three-dimensional physical world works. In 2026, World Labs raised $1 Billion. == Early life and education == Li was born in Beijing, China, in 1976 and grew up in Chengdu, Sichuan. She studied at Sichuan Chengdu No.7 High School. When she was 12, her father immigrated to Parsippany, New Jersey. When she was 16, Li and her mother joined him in the United States. While attending Parsippany High School, Li worked weekends at her family's dry-cleaning shop. She graduated from Parsippany High School in 1995. She was inducted into the hall of fame at Parsippany High School in 2017. Li pursued undergraduate study at Princeton University, where she received a Bachelor of Arts with a major in physics in 1999. Li completed her senior thesis, "Auditory binaural correlogram difference: a new computational model for Huggins dichotic pitch", under the supervision of Bradley Dickinson, professor of electrical engineering. During her years at Princeton, Li returned home most weekends to help run her family's dry cleaning business and worked as a dishwasher to supplement the family income. Li pursued graduate study at the California Institute of Technology, where she received a Master of Science in electrical engineering in 2001 and a Doctor of Philosophy in electrical engineering in 2005. Li completed her dissertation, "Visual Recognition: Computational Models and Human Psychophysics", under the primary supervision of Pietro Perona and secondary supervision of Christof Koch. Her graduate studies were supported by the National Science Foundation Graduate Research Fellowship and The Paul & Daisy Soros Fellowships for New Americans. == Career and research == From 2005 to 2006, Li was an assistant professor in the Electrical and Computer Engineering Department at the University of Illinois Urbana-Champaign, and from 2007 to 2009, she was an assistant professor in the Computer Science Department at Princeton University. She joined Stanford in 2009 as an assistant professor, and was promoted to associate professor with tenure in 2012, and then full professor in 2018. At Stanford, Li served as the director of Stanford Artificial Intelligence Lab (SAIL) from 2013 to 2018. Her research has focused on computer vision, deep learning, and cognitive neuroscience, with over 300 peer-reviewed publications. She became the founding co-director of Stanford's University-level initiative - the Human-Centered AI Institute, along with co-director Dr. John Etchemendy, former provost of Stanford University. The institute aligns with Li's aims to advance AI research, education, policy, and practice to improve the human condition. While at Princeton in 2007, Li led the development of ImageNet, a massive visual database designed to advance object recognition in AI. The project involved labeling over 14 million images using Amazon Mechanical Turk and inspired the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), which catalyzed progress in deep learning and led to dramatic improvements in image classification performance. The database addressed a key bottleneck in computer vision: the lack of large, annotated datasets for training machine learning models. Today, ImageNet is credited as a cornerstone innovation that underpins advancements in autonomous vehicles, facial recognition, and medical imaging. On her sabbatical from Stanford University from January 2017 to fall of 2018, Li joined Google Cloud as its Chief Scientist of AI/ML and Vice President. At Google, her team focused on democratizing AI technology and lowering the barrier for entrance to businesses and developers, including the developments of products like AutoML. In September 2017, Google secured a contract from the Department of Defense called Project Maven, which aimed to use AI techniques to interpret images captured by drone cameras. Google told employees who protested the company's work on Project Maven that their role was "specifically scoped to be for non-offensive purposes". In June 2018, Google told employees it would not seek renewal of the contract. In internal emails which were later leaked to reporters, Li expressed enthusiasm for the Google Cloud role in Project Maven, but warned against mentioning its AI component, saying that military AI is linked in the public mind with the danger of autonomous weapons. Asked about those leaked emails, Li told The New York Times, "I believe in human-centered AI to benefit people in positive and benevolent ways. It is deeply against my principles to work on any project that I think is to weaponize AI." In the fall of 2018, Li left Google and returned to Stanford University to continue her professorship. In 2023, Li co-led the launch of the RAISE-Health (Responsible AI for Safe and Equitable Health) initiative at Stanford University in collaboration with Stanford medicine. The initiative aims to develop frameworks for the responsible use of artificial intelligence in healthcare, including clinical care, biomedical research, and patient safety. According to her Stanford profile, she has been on partial academic leave from January 2024 through the end of 2025 to focus on entrepreneurial ventures. In 2024, Li said there was a disparity between private-sector investment in AI and support for academic and government research, and called for greater public funding for scientific uses of the technology and for studying its risks. Li is also known for her non-profit work as the co-founder and chairperson of nonprofit organization AI4ALL, whose mission is to educate the next generation of AI technologists, thinkers and leaders by promoting diversity and inclusion through human-centered AI principles. The program was created in collaboration with Melinda French Gates and Jensen Huang. Prior to establishing AI4ALL in 2017, Li and her former student Olga Russakovsky, currently an assistant professor in Princeton University, co-founded and co-directed the precursor program at Stanford called SAILORS (Stanford AI Lab OutReach Summers). SAILORS was an annual summer camp at Stanford dedicated to 9th grade high school girls in AI education and research, established in 2015 till it changed its name to AI4ALL @Stanford in 2017. In 2018, AI4ALL has successfully launched five more summer programs in addition to Stanford, including Princeton University, Carnegie Mellon University, Boston University, University of California Berkeley, and Canada's Simon Fraser University. We are at a turning point. AI's influence continues to grow, but representation and inclusion of a diversity of researchers in the field does not. It's critical that we seize this moment to create structures that will support long-term, positive changes. This won't happen via a single mechanism or quick fix. It starts with early education and extends to the existing structures of power within academia, work cultures among current AI researchers, and gatekeeping functions of research publishing, to name a few levers of change. Li has been described as a "researcher bringing humanity to AI". Li was elected as a member of the American Academy of Arts and Sciences in 2021, the National Academy of Engineering in 2020, and the National Academy of Medicine in 2020. In a November 2023 interview with The Guardian, Li said that while she would not refer to herself as the "godmother

  Read more →
• 

  Highway network

  In machine learning, the Highway Network was the first working very deep feedforward neural network with hundreds of layers, much deeper than previous neural networks. It uses skip connections modulated by learned gating mechanisms to regulate information flow, inspired by long short-term memory (LSTM) recurrent neural networks. The advantage of the Highway Network over other deep learning architectures is its ability to overcome or partially prevent the vanishing gradient problem, thus improving its optimization. Gating mechanisms are used to facilitate information flow across the many layers ("information highways"). Highway Networks have found use in text sequence labeling and speech recognition tasks. In 2014, the state of the art was training deep neural networks with 20 to 30 layers. Stacking too many layers led to a steep reduction in training accuracy, known as the "degradation" problem. In 2015, two techniques were developed to train such networks: the Highway Network (published in May), and the residual neural network, or ResNet (December). ResNet behaves like an open-gated Highway Net. == Model == The model has two gates in addition to the H ( W H , x ) {\displaystyle H(W_{H},x)} gate: the transform gate T ( W T , x ) {\displaystyle T(W_{T},x)} and the carry gate C ( W C , x ) {\displaystyle C(W_{C},x)} . The latter two gates are non-linear transfer functions (specifically sigmoid by convention). The function H {\displaystyle H} can be any desired transfer function. The carry gate is defined as: C ( W C , x ) = 1 − T ( W T , x ) {\displaystyle C(W_{C},x)=1-T(W_{T},x)} while the transform gate is just a gate with a sigmoid transfer function. == Structure == The structure of a hidden layer in the Highway Network follows the equation: y = H ( x , W H ) ⋅ T ( x , W T ) + x ⋅ C ( x , W C ) = H ( x , W H ) ⋅ T ( x , W T ) + x ⋅ ( 1 − T ( x , W T ) ) {\displaystyle {\begin{aligned}y=H(x,W_{H})\cdot T(x,W_{T})+x\cdot C(x,W_{C})\\=H(x,W_{H})\cdot T(x,W_{T})+x\cdot (1-T(x,W_{T}))\end{aligned}}} == Related work == Sepp Hochreiter analyzed the vanishing gradient problem in 1991 and attributed to it the reason why deep learning did not work well. To overcome this problem, Long Short-Term Memory (LSTM) recurrent neural networks have residual connections with a weight of 1.0 in every LSTM cell (called the constant error carrousel) to compute y t + 1 = F ( x t ) + x t {\textstyle y_{t+1}=F(x_{t})+x_{t}} . During backpropagation through time, this becomes the residual formula y = F ( x ) + x {\textstyle y=F(x)+x} for feedforward neural networks. This enables training very deep recurrent neural networks with a very long time span t. A later LSTM version published in 2000 modulates the identity LSTM connections by so-called "forget gates" such that their weights are not fixed to 1.0 but can be learned. In experiments, the forget gates were initialized with positive bias weights, thus being opened, addressing the vanishing gradient problem. As long as the forget gates of the 2000 LSTM are open, it behaves like the 1997 LSTM. The Highway Network of May 2015 applies these principles to feedforward neural networks. It was reported to be "the first very deep feedforward network with hundreds of layers". It is like a 2000 LSTM with forget gates unfolded in time, while the later Residual Nets have no equivalent of forget gates and are like the unfolded original 1997 LSTM. If the skip connections in Highway Networks are "without gates," or if their gates are kept open (activation 1.0), they become Residual Networks. The residual connection is a special case of the "short-cut connection" or "skip connection" by Rosenblatt (1961) and Lang & Witbrock (1988) which has the form x ↦ F ( x ) + A x {\displaystyle x\mapsto F(x)+Ax} . Here the randomly initialized weight matrix A does not have to be the identity mapping. Every residual connection is a skip connection, but almost all skip connections are not residual connections. The original Highway Network paper not only introduced the basic principle for very deep feedforward networks, but also included experimental results with 20, 50, and 100 layers networks, and mentioned ongoing experiments with up to 900 layers. Networks with 50 or 100 layers had lower training error than their plain network counterparts, but no lower training error than their 20 layers counterpart (on the MNIST dataset, Figure 1 in ). No improvement on test accuracy was reported with networks deeper than 19 layers (on the CIFAR-10 dataset; Table 1 in ). The ResNet paper, however, provided strong experimental evidence of the benefits of going deeper than 20 layers. It argued that the identity mapping without modulation is crucial and mentioned that modulation in the skip connection can still lead to vanishing signals in forward and backward propagation (Section 3 in ). This is also why the forget gates of the 2000 LSTM were initially opened through positive bias weights: as long as the gates are open, it behaves like the 1997 LSTM. Similarly, a Highway Net whose gates are opened through strongly positive bias weights behaves like a ResNet. The skip connections used in modern neural networks (e.g., Transformers) are dominantly identity mappings.

  Read more →
• 

  Intelligent Robotics Group

  The Intelligent Robotics Group (IRG) is a research organization within the Intelligent Systems Division at the NASA Ames Research Center in California's Silicon Valley. IRG conducts applied research in the area of robotics and autonomy and is one of the principal organizations at NASA responsible for robotics expertise, along with groups at the Jet Propulsion Laboratory and Johnson Space Center. The group's portfolio includes robotics in support of human exploration, perception and navigation, user interfaces, software architectures, and simulation. IRG developed the Astrobee free-flying robots on the International Space Station and was a primary contributor to the VIPER lunar rover in the areas of flight software, navigation, simulation, and mission operations. IRG has also conducted many robotic field test campaigns in support of spaceflight mission concept developments. These experiences led to the commercialization of the GigaPan system in collaboration with Carnegie Mellon University.

  Read more →
• 

  TD-Gammon

  TD-Gammon is a computer backgammon program developed in the 1990s by Gerald Tesauro at IBM's Thomas J. Watson Research Center. Its name comes from the fact that it is an artificial neural net trained by a form of temporal-difference learning, specifically TD-Lambda. It explored strategies that humans had not pursued and led to advances in the theory of correct backgammon play. In 1993, TD-Gammon (version 2.1) was trained with 1.5 million games of self-play, and achieved a level of play just slightly below that of the top human backgammon players of the time. In 1998, during a 100-game series, it was defeated by the world champion by a mere margin of 8 points. Its unconventional assessment of some opening strategies had been accepted and adopted by expert players. TD-gammon is commonly cited as an early success of reinforcement learning and neural networks, and was cited in, for example, papers for deep Q-learning and AlphaGo. == Algorithm for play and learning == During play, TD-Gammon examines on each turn all possible legal moves and all their possible responses (lookahead search), feeds each resulting board position into its evaluation function, and chooses the move that leads to the board position that got the highest score. In this respect, TD-Gammon is no different than almost any other computer board-game program. TD-Gammon's innovation was in how it learned its evaluation function. TD-Gammon's learning algorithm consists of updating the weights in its neural net after each turn to reduce the difference between its evaluation of previous turns' board positions and its evaluation of the present turn's board position—hence "temporal-difference learning". The score of any board position is a set of four numbers reflecting the program's estimate of the likelihood of each possible game result: White wins normally, Black wins normally, White wins a gammon, Black wins a gammon. For the final board position of the game, the algorithm compares with the actual result of the game rather than its own evaluation of the board position. The core of TD-gammon is a neural network with 3 layers. The input layer has two types of neurons. One type codes for the board position. They are non-negative integers ranging from 0 to 15, indicating the number of White or Black checkers at each board location. There are 99 input neurons for each, totaling 198 neurons. Another type codes for hand-crafted features previously used in Neurogammon. These features encoded standard concepts used by human experts, such as "advanced anchor," "blockade strength," "home board strength" and the probability of a "blot" (single checker) being hit. The hidden layer contains hidden neurons. Later versions had more of these. The output layer contains 4 neurons, representing the network's estimate of the probability ("equity") that the current board would lead to. The 4 neurons code for: White normal win, White gammon win, Black normal win, Black gammon win. Backgammon win is so rare that Tesauro opted to not represent it. After each turn, the learning algorithm updates each weight in the neural net according to the following rule: w t + 1 − w t = α ( Y t + 1 − Y t ) ∑ k = 1 t λ t − k ∇ w Y k {\displaystyle w_{t+1}-w_{t}=\alpha (Y_{t+1}-Y_{t})\sum _{k=1}^{t}\lambda ^{t-k}\nabla _{w}Y_{k}} where: It was found that picking small λ {\displaystyle \lambda } offered performance roughly equally good, and large λ {\displaystyle \lambda } degraded performance. Because of this, after 1992, TD-Gammon was trained with λ = 0 {\displaystyle \lambda =0} , degenerating into standard TD-learning. This saved compute by a factor of 2. == Development history == Version 1.0 used simple 1-ply search: every next move is scored by the neural net, and the highest-scoring move is selected. Versions 2.0 and 2.1 used 2-ply search: Make a 1-ply analysis to remove unlikely moves ("forward pruning"). Make a 2-play minimax analysis for only the likely moves. Pick the best move, probability-weighted by each of the opponent's 21 possible dice rolls (weighting non-doubles twice as much as doubles). Versions 3.0 and 3.1 used 3-ply search, using 21 2 = 441 {\displaystyle 21^{2}=441} possible dice rolls instead of 21. The last version, 3.1, was trained specifically for an exhibition match against Malcolm Davis at the 1998 AAAI Hall of Champions. It lost at -8 points, mainly due to one blunder, where TD-Gammon opted to double and got gammoned at -32 points. == Experiments and stages of training == Unlike previous neural-net backgammon programs such as Neurogammon (also written by Tesauro), where an expert trained the program by supplying the "correct" evaluation of each position, TD-Gammon was at first programmed "knowledge-free". In early experimentation, using only a raw board encoding with no human-designed features, TD-Gammon reached a level of play comparable to Neurogammon: that of an intermediate-level human backgammon player. Even though TD-Gammon discovered insightful features on its own, Tesauro wondered if its play could be improved by using hand-designed features like Neurogammon's. Indeed, the self-training TD-Gammon with expert-designed features soon surpassed all previous computer backgammon programs. It stopped improving after about 1,500,000 games (self-play) using a three-layered neural network, with 198 input units encoding expert-designed features, 80 hidden units, and one output unit representing predicted probability of winning. == Advances in backgammon theory == TD-Gammon's exclusive training through self-play (rather than imitation learning) enabled it to explore strategies that humans previously had not considered or had ruled out erroneously. Its success with unorthodox strategies had a significant impact on the backgammon community. Late 1991, Bill Robertie, Paul Magriel, and Malcolm Davis, were invited to play against TD-Gammon (version 1.0). A total of 51 games were played, with TD-Gammon losing at -0.25 ppg. Robertie found TD-Gammon to be at the level of a competent advanced player, and better than any previous backgammon program. Robertie subsequently wrote about the use of TD-Gammon for backgammon study. For example, on the opening play, the conventional wisdom was that given a roll of 2-1, 4-1, or 5-1, White should move a single checker from point 6 to point 5. Known as "slotting", this technique trades the risk of a hit for the opportunity to develop an aggressive position. TD-Gammon found that the more conservative play of splitting 24-23 was superior. Tournament players began experimenting with TD-Gammon's move, and found success. Within a few years, slotting had disappeared from tournament play, replaced by splitting, though in 2006 it made a reappearance for 2-1. Backgammon expert Kit Woolsey found that TD-Gammon's positional judgement, especially its weighing of risk against safety, was superior to his own or any human's. TD-Gammon's excellent positional play was undercut by occasional poor endgame play. The endgame requires a more analytical approach, sometimes with extensive lookahead. TD-Gammon's limitation to two-ply lookahead put a ceiling on what it could achieve in this part of the game. TD-Gammon's strengths and weaknesses were the opposite of symbolic artificial intelligence programs and most computer software in general: it was good at matters that require an intuitive "feel" but bad at systematic analysis. It is also poor at doubling strategies. This is likely due to the fact that the neural network is trained without the doubling cube, with the doubling added by feeding the neural network's cubeless equity estimates into theoretically-based heuristic formulae. This was particularly the case in the 1998 exhibition match, where it played 100 games against Malcolm Davis. A single doubling blunder lost the match. TD-gammon was never commercialized or released to the public in some other form, but it inspired commercial backgammon programs based on neural networks, such as JellyFish (1994) and Snowie (1998).

  Read more →
• 

  Neuromorphic computing

  Neuromorphic computing is a computing approach inspired by the human brain's structure and function. It uses artificial neurons to perform computations, mimicking neural systems for tasks such as perception, motor control, and multisensory integration. These systems, implemented in analog, digital, or mixed-mode VLSI, prioritize robustness, adaptability, and learning by emulating the brain’s distributed processing across small computing elements. This interdisciplinary field integrates biology, physics, mathematics, computer science, and electronic engineering to develop systems that emulate the brain’s morphology and computational strategies. Neuromorphic systems aim to enhance energy efficiency and computational power for applications including artificial intelligence, pattern recognition, and sensory processing. == History == Carver Mead proposed one of the first applications for neuromorphic engineering in the late 1980s. In 2006, researchers at Georgia Tech developed a field programmable neural array, a silicon-based chip modeling neuron channel-ion characteristics. In 2011, MIT researchers created a chip mimicking synaptic communication using 400 transistors and standard CMOS techniques. In 2012 HP Labs researchers reported that Mott memristors exhibit volatile behavior at low temperatures, enabling the creation of neuristors that mimic neuron behavior and support Turing machine components. Also in 2012, Purdue University researchers presented a neuromorphic chip design using lateral spin valves and memristors, noted for energy efficiency. The 2013 Blue Brain Project creates detailed digital models of rodent brains. Neurogrid, developed by Brains in Silicon at Stanford University, used 16 NeuroCore chips to emulate 65,536 neurons with high energy efficiency in 2014. The 2014 BRAIN Initiative and IBM’s TrueNorth chip contributed to neuromorphic advancements. The 2016 BrainScaleS project, a hybrid neuromorphic supercomputer at University of Heidelberg, operated 864 times faster than biological neurons. In 2017, Intel unveiled its Loihi chip, using an asynchronous artificial neural network for efficient learning and inference. Also in 2017 IMEC’s self-learning chip, based on OxRAM, demonstrated music composition by learning from minuets. In 2022, MIT researchers developed artificial synapses using protons for analog deep learning. In 2019, the European Union funded neuromorphic quantum computing to explore quantum operations using neuromorphic systems. Also in 2022, researchers at the Max Planck Institute for Polymer Research developed an organic artificial spiking neuron for in-situ neuromorphic sensing and biointerfacing. Researchers reported in 2024 that chemical systems in liquid solutions can detect sound at various wavelengths, offering potential for neuromorphic applications. == Neurological inspiration == Neuromorphic engineering emulates the brain’s structure and operations, focusing on the analog nature of biological computation and the role of neurons in cognition. The brain processes information via neurons using chemical signals, abstracted into mathematical functions. Neuromorphic systems distribute computation across small elements, similar to neurons, using methods guided by anatomical and functional neural maps from electron microscopy and neural connection studies. == Implementation == Neuromorphic systems employ hardware such as oxide-based memristors, spintronic memories, threshold switches, and transistors. Software implementations train spiking neural networks using error backpropagation. === Neuromemristive systems === Neuromemristive systems use memristors to implement neuroplasticity, focusing on abstract neural network models rather than detailed biological mimicry. These systems enable applications in speech recognition, face recognition, and object recognition, and can replace conventional digital logic gates. The Caravelli-Traversa-Di Ventra equation describes memristive memory evolution, revealing tunneling phenomena and Lyapunov functions. === Neuromorphic sensors === Neuromorphic principles extend to sensors, such as the retinomorphic sensor or event camera, which mimic human vision by registering brightness changes individually, optimizing power consumption. An example of this applied to detecting light is the retinomorphic sensor or, when employed in an array, an event camera. == Ethical considerations == Neuromorphic systems raise the same ethical questions as those for other approaches to artificial intelligence. Daniel Lim argued that advanced neuromorphic systems could lead to machine consciousness, raising concerns about whether civil rights and other protocols should be extended to them. Legal debates, such as in Acohs Pty Ltd v. Ucorp Pty Ltd, question ownership of work produced by neuromorphic systems, as non-human-generated outputs may not be copyrightable.

  Read more →
• 

  Quantum machine learning

  Quantum machine learning (QML) is the study of quantum algorithms for machine learning. It often refers to quantum algorithms for machine learning tasks which analyze classical data, sometimes called quantum-enhanced machine learning. QML algorithms use qubits and quantum operations to try to improve the space and time complexity of classical machine learning algorithms. Hybrid QML methods involve both classical and quantum processing, where computationally difficult subroutines are outsourced to a quantum device. These routines can be more complex in nature and executed faster on a quantum computer. Furthermore, quantum algorithms can be used to analyze quantum states instead of classical data. The term "quantum machine learning" is sometimes used to refer classical machine learning methods applied to data generated from quantum experiments (i.e. machine learning of quantum systems), such as learning the phase transitions of a quantum system or creating new quantum experiments. QML also extends to a branch of research that explores methodological and structural similarities between certain physical systems and learning systems, in particular neural networks. For example, some mathematical and numerical techniques from quantum physics are applicable to classical deep learning and vice versa. Furthermore, researchers investigate more abstract notions of learning theory with respect to quantum information, sometimes referred to as "quantum learning theory". == Machine learning with quantum computers == Quantum-enhanced machine learning refers to quantum algorithms that solve tasks in machine learning, thereby improving and often expediting classical machine learning techniques. Such algorithms typically require one to encode the given classical data set into a quantum computer to make it accessible for quantum information processing. Subsequently, quantum information processing routines are applied and the result of the quantum computation is read out by measuring the quantum system. For example, the outcome of the measurement of a qubit reveals the result of a binary classification task. While many proposals of QML algorithms are still purely theoretical and require a full-scale universal quantum computer to be tested, others have been implemented on small-scale or special purpose quantum devices. === Quantum associative memories and quantum pattern recognition === Early work on quantum associative memories has been done by Dan Ventura and Tony Martinez and by Carlo A. Trugenberger in the late 1990s and early 2000s. Associative (or content-addressable) memories are able to recognize stored content on the basis of a similarity measure, while random access memories are accessed by the address of stored information and not its content. As such they must be able to retrieve both incomplete and corrupted patterns, the essential machine learning task of pattern recognition. Typical classical associative memories store p patterns in the O ( n 2 ) {\displaystyle O(n^{2})} interactions (synapses) of a real, symmetric energy matrix over a network of n artificial neurons. The encoding is such that the desired patterns are local minima of the energy functional and retrieval is done by minimizing the total energy, starting from an initial configuration. Unfortunately, classical associative memories are severely limited by the phenomenon of cross-talk. When too many patterns are stored, spurious memories appear which quickly proliferate, so that the energy landscape becomes disordered and no retrieval is anymore possible. The number of storable patterns is typically limited by a linear function of the number of neurons, p ≤ O ( n ) {\displaystyle p\leq O(n)} . Quantum associative memories (in their simplest realization) store patterns in a unitary matrix U acting on the Hilbert space of n qubits. Retrieval is realized by the unitary evolution of a fixed initial state to a quantum superposition of the desired patterns with probability distribution peaked on the most similar pattern to an input. By its very quantum nature, the retrieval process is thus probabilistic. Because quantum associative memories are free from cross-talk, however, spurious memories are never generated. Correspondingly, they have a superior capacity than classical ones. The number of parameters in the unitary matrix U is O ( p n ) {\displaystyle O(pn)} . One can thus have efficient, spurious-memory-free quantum associative memories for any polynomial number of patterns. If the matrix U is encoded as a unique operator (as opposed as to a sequence of gates as in the circuit model), e.g. by an optical interferometer, the retrieval becomes efficient even for an exponential number of patterns. === Linear algebra simulation with quantum amplitudes === A number of quantum algorithms for machine learning are based on the idea of amplitude encoding, that is, to associate the amplitudes of a quantum state with the inputs and outputs of computations. Since a state of n {\displaystyle n} qubits is described by 2 n {\displaystyle 2^{n}} complex amplitudes, this information encoding can allow for an exponentially compact representation. Intuitively, this corresponds to associating a discrete probability distribution over binary random variables with a classical vector. The goal of algorithms based on amplitude encoding is to formulate quantum algorithms whose resources grow polynomially in the number of qubits n {\displaystyle n} , which amounts to a logarithmic time complexity in the number of amplitudes and thereby the dimension of the input. Many QML algorithms in this category are based on variations of the quantum algorithm for linear systems of equations (colloquially called HHL, after the paper's authors) which, under specific conditions, performs a matrix inversion using an amount of physical resources growing only logarithmically in the dimensions of the matrix. One of these conditions is that a Hamiltonian which entry-wise corresponds to the matrix can be simulated efficiently, which is known to be possible if the matrix is sparse or low rank. For reference, any known classical algorithm for matrix inversion requires a number of operations that grows more than quadratically in the dimension of the matrix (e.g. O ( n 2.373 ) {\displaystyle O{\mathord {\left(n^{2.373}\right)}}} ), but they are not restricted to sparse matrices. Quantum matrix inversion can be applied to machine learning methods in which the training reduces to solving a linear system of equations, for example in least-squares linear regression, the least-squares version of support vector machines, and Gaussian processes. A crucial bottleneck of methods that simulate linear algebra computations with the amplitudes of quantum states is state preparation, which often requires one to initialise a quantum system in a state whose amplitudes reflect the features of the entire dataset. Although efficient methods for state preparation are known for specific cases, this step easily hides the complexity of the task. === Variational quantum algorithms (VQAs) === In a variational quantum algorithm, a classical computer optimizes the parameters used to prepare a quantum state, while a quantum computer is used to do the actual state preparation and measurement. VQAs are considered promising candidates for noisy intermediate-scale quantum computers. Variational quantum circuits (or parameterized quantum circuits) are a popular class of VQAs where the parameters are those used in a fixed quantum circuit. Researchers have studied VQCs to solve optimization problems and find the ground state energy of complex quantum systems, which were difficult to solve using a classical computer. === Quantum binary classifier === Pattern reorganization is one of the important tasks of machine learning, binary classification is one of the tools or algorithms to find patterns. Binary classification is used in supervised learning and in unsupervised learning. In QML, classical bits are converted to qubits and they are mapped to Hilbert space; complex value data are used in a quantum binary classifier to use the advantage of Hilbert space. By exploiting the quantum mechanic properties such as superposition, entanglement, interference the quantum binary classifier produces the accurate result in short period of time. === Quantum machine learning algorithms based on Grover search === Another approach to improving classical machine learning with quantum information processing uses amplitude amplification methods based on Grover's search algorithm, which has been shown to solve unstructured search problems with a quadratic speedup compared to classical algorithms. These quantum routines can be employed for learning algorithms that translate into an unstructured search task, as can be done, for instance, in the case of the k-medians and the k-nearest neighbors algorithms. Other applications include quadratic speedups in the training of perceptrons. An e

  Read more →
• 

  Hyperion Data Center

  The Richland Parish Data Center, nicknamed "Hyperion", is a planned artificial intelligence data center by Meta Platforms under-construction along Highway La. 183 in Richland Parish, Louisiana, just outside of Holly Ridge. It is one of a number of "titan clusters" being built in preparation for the emergence of AI superintelligence. Modern technological researchers disagree as to whether or not superintelligence will ever exist, though Meta CEO Mark Zuckerberg has expressed belief that its creation is inevitable. Current plans allot for the investment of $27 billion, as the structure is built from 2025 to 2030. == History == Meta was considering potential locations for their flagship data center in early 2024. Before being announced later in December, the plan was completely secret; meetings held between involved organisations and even government officials could only refer to it by the codename "Project Sucre" to protect it from potential corporate espionage. The data center was first announced on 04 December 2024, though its full scale was yet to be revealed. At first, Meta would not even claim responsibility for it, channelling all of its investments through the secret shell subsidiary Laidley LLC. We set out looking for a place where we could expand into gigawatts pretty quickly, and really get moving within that community on a large plot of land very quickly. We looked at finding very, very large contiguous plots of land that had access to the infrastructure that we need, the energy that we needed, and could move very, very quickly for us. The Louisiana-based Entergy Corporation, aiming for the facility to be built in its own backyard, negotiated a deal with the government of Louisiana to provide Meta with enormous tax breaks if they agreed to build Hyperion there. The Louisiana legislature responded by passing Act 730, which provides significant tax rebates on the purchase or lease of equipment for building and operating data centers. Meta found the arrangement acceptable, and bought a plot of land from the government. The government also had to further amend its laws to allow Meta to do this, as pre-existing policy forbade purchasing land directly from the government instead of hosting a public auction. The plot of land, originally called Franklin Farms, was purchased from the Franklin family in 2006 by the government, intending for it to be developed into an automotive manufacturing plant. Greater attention was brought to Hyperion it when Zuckerberg posted about the project on 14 July 2025 on Threads. The project subsequently caught media attention for its large size, as Zuckerberg's post portrayed the structure superimposed over Manhattan (pictured). The construction site spans 2,250 acres (9.1 km2) with a planned floor area of 4,000,000 square feet (371612 m2), making it the third largest building in the world by floor area upon completion. Meta initially reported the construction cost to be over $10 billion, but in October 2025, it announced a partnership with Blue Owl Capital providing for at least $27 billion. == Operation == The facility is expected to consume up to 5 gigawatts (GW) of computational power, more electricity than is currently used by the entire State of Louisiana. As part of their deal made with Meta, Entergy plans to be able to produce at least 3.8 GW of electricity for the operation. == Response to the project == Louisiana Governor Jeff Landry thanked Meta for their decision to build Hyperion in Louisiana, stating that it would "create opportunities for Louisiana workers to fill high-paying jobs of the future." and calling it "A New Chapter" for the state. The Louisiana Economic Development (LED) state agency further praised the project, citing Meta's estimate that it would create 1,500 jobs. Additionally, Richland Parish Supervisor Joey Evans stated that he was excited about the project. As part of their agreement with Meta, Energy announced their plan to increase electricity production state-wide. They say that this will result in the cost of energy reducing, though Entergy filings revealed in June 2025 that the cost of electricity would rise and be passed onto consumers. Meta also pledged to match all of Hyperion's power consumption with 100% environmentally friendly electricity production. So far, Entergy has begun building three gas-powered combined-cycle power plants and a substation in response to the project. Delta Community College announced in response to Hyperion's construction that it would expand its construction and trade programs. In January 2025, Business Facilities Magazine selected Hyperion for its annual Deal of the Year Platinum Award for 2024. Much of the initial backlash following Hyperion's announcement centered around the fast-tracked approval of the project by the state government, and scepticism around Meta's various claims (environmental friendliness, 100% renewable energy, local economic stimulation, price reductions). The Sierra Club criticised Meta for gentrifying the surrounding area, and was highly sceptical of their promise to keep it environmentally friendly. Environmental activist group Earthjustice attempted to have a subpoena of Meta approved to determine if they were compliant with environmental protection laws, though they were unsuccessful. Many residents of Holy Ridge have been critical of the construction, complaining about the increased construction vehicle traffic and intense gentrification. Another point of contention is Meta's continued reliance on out-of-state contractors in the facility's construction in spite of their previous commitment to "hire as many local folk as [we] possibly can." In spite of Entergy's continual denial that the facility's construction will not adversely affect the power grid, numerous electrical outages have been reported since construction began.

  Read more →
• 

  TensorFlow

  TensorFlow is a software library for machine learning and artificial intelligence. It can be used across a range of tasks, but is used mainly for training and inference of neural networks. It is one of the most popular deep learning frameworks, alongside others such as PyTorch. It is free and open-source software released under the Apache License 2.0. It was developed by the Google Brain team for Google's internal use in research and production. The initial version was released under the Apache License 2.0 in 2015. Google released an updated version, TensorFlow 2.0, in September 2019. TensorFlow can be used in a wide variety of programming languages, including Python, JavaScript, C++, and Java, facilitating its use in a range of applications in many sectors. == History == === DistBelief === Starting in 2011, Google Brain built DistBelief as a proprietary machine learning system based on deep learning neural networks. Its use grew rapidly across diverse Alphabet companies in both research and commercial applications. Google assigned multiple computer scientists, including Jeff Dean, to simplify and refactor the codebase of DistBelief into a faster, more robust application-grade library, which became TensorFlow. In 2009, the team, led by Geoffrey Hinton, had implemented generalized backpropagation and other improvements, which allowed generation of neural networks with substantially higher accuracy, for instance a 25% reduction in errors in speech recognition. === TensorFlow === TensorFlow is Google Brain's second-generation system. Version 1.0.0 was released on February 11, 2017. While the reference implementation runs on single devices, TensorFlow can run on multiple CPUs and GPUs (with optional CUDA and SYCL extensions for general-purpose computing on graphics processing units). TensorFlow is available on 64-bit Linux, macOS, Windows, and mobile computing platforms including Android and iOS. Its flexible architecture allows for easy deployment of computation across a variety of platforms (CPUs, GPUs, TPUs), and from desktops to clusters of servers to mobile and edge devices. TensorFlow computations are expressed as stateful dataflow graphs. The name TensorFlow derives from the operations that such neural networks perform on multidimensional data arrays, which are referred to as tensors. During the Google I/O Conference in June 2016, Jeff Dean stated that 1,500 repositories on GitHub mentioned TensorFlow, of which only 5 were from Google. In March 2018, Google announced TensorFlow.js version 1.0 for machine learning in JavaScript. In Jan 2019, Google announced TensorFlow 2.0. It became officially available in September 2019. In May 2019, Google announced TensorFlow Graphics for deep learning in computer graphics. === Tensor processing unit (TPU) === In May 2016, Google announced its Tensor processing unit (TPU), an application-specific integrated circuit (ASIC, a hardware chip) built specifically for machine learning and tailored for TensorFlow. A TPU is a programmable AI accelerator designed to provide high throughput of low-precision arithmetic (e.g., 8-bit), and oriented toward using or running models rather than training them. Google announced they had been running TPUs inside their data centers for more than a year, and had found them to deliver an order of magnitude better-optimized performance per watt for machine learning. In May 2017, Google announced the second-generation, as well as the availability of the TPUs in Google Compute Engine. The second-generation TPUs deliver up to 180 teraflops of performance, and when organized into clusters of 64 TPUs, provide up to 11.5 petaflops. In May 2018, Google announced the third-generation TPUs delivering up to 420 teraflops of performance and 128 GB high bandwidth memory (HBM). Cloud TPU v3 Pods offer 100+ petaflops of performance and 32 TB HBM. In February 2018, Google announced that they were making TPUs available in beta on the Google Cloud Platform. === Edge TPU === In July 2018, the Edge TPU was announced. Edge TPU is Google's purpose-built ASIC chip designed to run TensorFlow Lite machine learning (ML) models on small client computing devices such as smartphones known as edge computing. === TensorFlow Lite === In May 2017, Google announced TensorFlow Lite as a software stack to support machine learning models for mobile and embedded devices, and in November 2017, provided the developer preview. In January 2019, the TensorFlow team released a developer preview of the mobile GPU inference engine with OpenGL ES 3.1 Compute Shaders on Android devices and Metal Compute Shaders on iOS devices. In May 2019, Google announced that their TensorFlow Lite Micro (also known as TensorFlow Lite for Microcontrollers) and ARM's uTensor would be merging. It was renamed as LiteRT in 2024. === TensorFlow 2.0 === As TensorFlow's market share among research papers was declining to the advantage of PyTorch, the TensorFlow Team announced a release of a new major version of the library in September 2019. TensorFlow 2.0 introduced many changes, the most significant being TensorFlow eager, which changed the automatic differentiation scheme from the static computational graph to the "Define-by-Run" scheme originally made popular by Chainer and later PyTorch. Other major changes included removal of old libraries, cross-compatibility between trained models on different versions of TensorFlow, and significant improvements to the performance on GPU. == Features == === AutoDifferentiation === AutoDifferentiation is the process of automatically calculating the gradient vector of a model with respect to each of its parameters. With this feature, TensorFlow can automatically compute the gradients for the parameters in a model, which is useful to algorithms such as backpropagation which require gradients to optimize performance. To do so, the framework must keep track of the order of operations done to the input Tensors in a model, and then compute the gradients with respect to the appropriate parameters. === Eager execution === TensorFlow includes an "eager execution" mode, which means that operations are evaluated immediately as opposed to being added to a computational graph which is executed later. Code executed eagerly can be examined step-by step-through a debugger, since data is augmented at each line of code rather than later in a computational graph. This execution paradigm is considered to be easier to debug because of its step by step transparency. === Distribute === In both eager and graph executions, TensorFlow provides an API for distributing computation across multiple devices with various distribution strategies. This distributed computing can often speed up the execution of training and evaluating of TensorFlow models and is a common practice in the field of AI. === Losses === To train and assess models, TensorFlow provides a set of loss functions (also known as cost functions). Some popular examples include mean squared error (MSE) and binary cross entropy (BCE). === Metrics === In order to assess the performance of machine learning models, TensorFlow gives API access to commonly used metrics. Examples include various accuracy metrics (binary, categorical, sparse categorical) along with other metrics such as Precision, Recall, and Intersection-over-Union (IoU). === TF.nn === TensorFlow.nn is a module for executing primitive neural network operations on models. Some of these operations include variations of convolutions (1/2/3D, Atrous, depthwise), activation functions (Softmax, RELU, GELU, Sigmoid, etc.) and their variations, and other operations (max-pooling, bias-add, etc.). === Optimizers === TensorFlow offers a set of optimizers for training neural networks, including ADAM, ADAGRAD, and Stochastic Gradient Descent (SGD). When training a model, different optimizers offer different modes of parameter tuning, often affecting a model's convergence and performance. == Usage and extensions == === TensorFlow === TensorFlow serves as a core platform and library for machine learning. TensorFlow's APIs use Keras to allow users to make their own machine-learning models. In addition to building and training their model, TensorFlow can also help load the data to train the model, and deploy it using TensorFlow Serving. TensorFlow provides a stable Python Application Program Interface (API), as well as APIs without backwards compatibility guarantee for JavaScript, C++, and Java. Third-party language binding packages are also available for C#, Haskell, Julia, MATLAB, Object Pascal, R, Scala, Rust, OCaml, and Crystal. Bindings that are now archived and unsupported include Go and Swift. === TensorFlow.js === TensorFlow also has a library for machine learning in JavaScript. Using the provided JavaScript APIs, TensorFlow.js allows users to use either Tensorflow.js models or converted models from TensorFlow or TFLite, retrain the given models, and run on the web. === LiteRT === LiteRT, formerly known as Te

  Read more →