AI Code Ui

AI Code Ui — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

  • Co–Star

    Co–Star

    Co–Star is an American astrological social networking service founded in 2017, and headquartered in New York City. Users enter the date, time and place they were born to generate an astrological chart and daily horoscopes, which can be compared with those of other users. == History == The concept for Co-Star began in 2015 when Banu Guler created an astrological chart as a gift. The idea later developed into a mobile application with collaborators Anna Kopp and Ben Weitzman. The app publicly launched in 2017. The app includes astrological readings, charts, and daily push notifications that have been noted for their unconventional tone. In early 2018, the company raised a $750,000 pre-seed round from Female Founders Fund. In 2019, Co–Star raised a $5.2 million seed round from Maveron, Aspect, and 14W. In January 2020, Co–Star for Android was launched to a 120,000-person waitlist—two years after their iOS version. In April 2021, the company announced a $15 million Series A, led by Spark Capital. As of that date, Co–Star reported more than 20 million downloads and increased adoption among young women in the United States. == Features == Co–Star employs artificial intelligence to analyze publicly accessible NASA JPL data and find patterns in a user's transits. Co–Star's algorithm maps human-written snippets of text to planetary movements to display personalized content for each user. That content has been called “slightly robotic,” “wildly beautiful,” “truly insane," “brutally honest,” and compared to “a free therapy session.” In July 2023, Co–Star released an in-app service called The Void that allows users to ask open-ended questions and receive answers informed by Co–Star's astrological database.

    Read more →
  • GermaNet

    GermaNet

    GermaNet is a semantic network for the German language. It relates nouns, verbs, and adjectives semantically by grouping lexical units that express the same concept into synsets and by defining semantic relations between these synsets. GermaNet is free for academic use, after signing a license. GermaNet shares much in common with the English WordNet and can be viewed as an online thesaurus or a light-weight ontology. GermaNet has been developed and maintained at the University of Tübingen since 1997 within the research group for General and Computational Linguistics. It has been integrated into the EuroWordNet, a multilingual lexical-semantic database. == Database == === Contents === GermaNet partitions the lexical space into a set of concepts that are interlinked by semantic relations. A semantic concept is modeled by a synset. A synset is a set of words (called lexical units) where all the words are taken to have the same or almost the same meaning. Thus, a synset is a set of synonyms grouped under one definition, or "gloss". In addition to the gloss, synsets are labeled with their syntactic function and accompanied by example sentences for each distinct meaning in the synset. Just as in WordNet, for each word category the semantic space is divided into a number of semantic fields closely related to major nodes in the semantic network: Ort, or "location", Körper, or "body", etc. As of version 20.0 (release November 2025), GermaNet contains: Synsets: 179438 Lexical units: 231500 Literals: 216517 1.29 lexical units per synset Number of conceptual relations: 194367 Number of lexical relations: 13602 (synonymy excluded) Number of split compounds: 130901 Number of Interlingual Index (ILI) records: 28561 Number of Wiktionary sense descriptions: 29539 === Format === All GermaNet data is stored in a PostgreSQL relational database. The database schema follows the internal structure of GermaNet: there are tables to store synsets, lexical units, conceptual and lexical relations, etc. GermaNet data is distributed both in this database format and as XML files. In the XML data, two types of files, one for synsets and the other for relations, represent all data available in the GermaNet database. == Interfaces == There are software libraries and APIs available for Java and Python. These programs are distributed under free-software licenses and provide easy access to all information in various versions of GermaNet. GermaNet Rover is an on-line application that can be used to search for synsets in GermaNet, explore the data associated with them, and calculate the semantic similarity of pairs of synsets. It features visualizations of the hypernym relation and advanced filtering options for synset searching. == Licenses == GermaNet 20.0 (released November 2025) can be distributed under one of the following types of license agreements: Academic Research License Agreement: for the purpose of research at academic institutions. There is no license fee for academic use. Licenses are not given to individual students, and those seeking a license are required to talk to an academic advisor. Research and Development License Agreement: applies to non-academic institutions and research consortia. To be used strictly for technology development and internal research. Commercial License Agreement: applies to non-academic institutions and commercial enterprises. It permits technology development and internal research, as well as giving the non-exclusive right to distribute and market any derived product or service. == Alternatives == Open-de-WordNet is a freely available alternative to GermaNet which is compatible with WordNet. == Linguistic applications == GermaNet has been used for a variety of applications, including: semantic analysis shallow recognition of implicit document structure compound analysis analyzing sectional preferences word sense disambiguation

    Read more →
  • Pretext

    Pretext

    A pretext (adj.: pretextual) is an excuse to do something or say something that is not accurate. Pretexts may be based on a half-truth or developed in the context of a misleading fabrication. Pretexts have been used to conceal the true purpose or rationale behind actions and words. They are often heard in political speeches. In US law, a pretext usually describes false reasons that hide the true intentions or motivations for a legal action. If a party can establish a prima facie case for the proffered evidence, the opposing party must prove that these reasons were "pretextual" or false. This can be accomplished by directly demonstrating that the motivations behind the presentation of evidence is false, or indirectly by evidence that the motivations are not "credible". In Griffith v. Schnitzer, an employment discrimination case, a jury award was reversed by a Court of Appeals because the evidence was not sufficient that the defendant's reasons were "pretextual". That is, the defendant's evidence was either undisputed, or the plaintiff's was "irrelevant subjective assessments and opinions". A "pretextual" arrest by law enforcement officers is one carried out for illegal purposes such as to conduct an unjustified search and seizure. As one example of pretext, in the 1880s, the Chinese government raised money on the pretext of modernizing the Chinese navy. Instead, these funds were diverted to repair a ship-shaped, two-story pavilion which had been originally constructed for the mother of the Qianlong Emperor. This pretext and the Marble Barge are famously linked with Empress Dowager Cixi. This architectural folly, known today as the Marble Boat (Shifang), is "moored" on Lake Kunming in what the empress renamed the "Garden for Cultivating Harmony" (Yiheyuan). Another example of pretext was demonstrated in the speeches of the Roman orator Cato the Elder (234–149 BC). For Cato, every public speech became a pretext for a comment about Carthage. The Roman statesman had come to believe that the prosperity of ancient Carthage represented an eventual and inevitable danger to Rome. In the Senate, Cato famously ended every speech by proclaiming his opinion that Carthage had to be destroyed (Carthago delenda est). This oft-repeated phrase was the ultimate conclusion of all logical argument in every oration, regardless of the subject of the speech. This pattern persisted until his death in 149, which was the year in which the Third Punic War began. In other words, any subject became a pretext for reminding his fellow senators of the dangers Carthage represented. == Uses in warfare == The early years of Japan's Tokugawa shogunate were unsettled, with warring factions battling for power. The causes for the fighting were in part pretextual, but the outcome brought diminished armed conflicts after the Siege of Osaka in 1614–1615. The next two-and-a-half centuries of Japanese history were comparatively peaceful under the successors of Tokugawa Ieyasu and the bakufu government he established. === United States === During the War of 1812, US President James Madison was often accused of using impressment of American sailors by the Royal Navy as a pretext to invade Canada. The sinking of the USS Maine in 1898 was blamed on the Spanish, despite early reports of it having been an accident, contributing to U.S. entry into the Spanish–American War. The slogan "Remember the Maine! To hell with Spain!" was used as a rallying cry. Some have argued that United States President Franklin D. Roosevelt used the attack on Pearl Harbor by Japanese forces on December 7, 1941, as a pretext to enter World War II. American soldiers and supplies had been assisting British and Soviet operations for almost a year by this point, and the United States had thus "chosen a side", but due to the political climate in the States at the time and some campaign promises made by Roosevelt that he would not send American troops to fight in foreign wars, Roosevelt could not declare war for fear of public backlash. The attack on Pearl Harbor united the American people's resolve against the Axis powers and created the bellicose atmosphere in which to declare war. The 1964 Gulf of Tonkin incident, later revealed to have been partly provoked and partly not to have happened, was used to bring the United States fully into the Vietnam War. United States President George W. Bush used the September 11 attacks and faulty intelligence about the existence of weapons of mass destruction as a pretext for the war in Iraq. == Social engineering == A type of social engineering called pretexting uses a pretext to elicit information fraudulently from a target. The pretext in this case includes research into the identity of a certain authorized person or personality type in order to establish legitimacy in the mind of the target.

    Read more →
  • Richard S. Sutton

    Richard S. Sutton

    Richard Stuart Sutton (born 1957 or 1958) is a Canadian computer scientist. He is a professor of computing science at the University of Alberta, fellow & Chief Scientific Advisor at the Alberta Machine Intelligence Institute, and a research scientist at Keen Technologies. Sutton is considered one of the founders of modern computational reinforcement learning. In particular, he contributed to temporal difference learning and policy gradient methods. He received the 2024 Turing Award with Andrew Barto. == Education and early life == Richard Sutton was born in either 1957 or 1958 in Toledo, Ohio, and grew up in Oak Brook, Illinois, a suburb of Chicago, United States. Sutton received his Bachelor of Arts (BA) degree in psychology from Stanford University in 1978 before taking a Master of Science (1980) and PhD (1984) in computer science from the University of Massachusetts Amherst supervised by Andrew Barto. His doctoral dissertation introduced actor-critic architectures and temporal credit assignment. He was influenced by Harry Klopf's work in the 1970s, which proposed that supervised learning is insufficient for AI or explaining intelligent behavior, and trial-and-error learning, driven by "hedonic aspects of behavior", is necessary. This focused his interest to reinforcement learning. == Career and research == Sutton held a postdoctoral research position at the University of Massachusetts Amherst in 1984. He worked at GTE Laboratories in Waltham, Massachusetts as principal member of technical staff from 1985 to 1994, then returned to the University of Massachusetts Amherst as a senior research scientist. He joined AT&T Labs Shannon Laboratory in Florham Park, New Jersey as principal technical staff member from 1998 to 2002. He has been a professor of computing science at the University of Alberta since 2003, where he helped establish the Reinforcement Learning and Artificial Intelligence Laboratory. In 2017 he became a distinguished research scientist with Google DeepMind and helped launch DeepMind Alberta in Edmonton, a research office operated in close collaboration with the University of Alberta. 1984: Postdoctoral researcher, University of Massachusetts Amherst (Amherst, Massachusetts) 1985–1994: Principal member of technical staff, Computer and Intelligent Systems Laboratory, GTE Laboratories (Waltham, Massachusetts) 1995–1998: Senior research scientist, University of Massachusetts Amherst (Amherst, Massachusetts) 1998–2002: Principal technical staff member, Artificial Intelligence Department, AT&T Labs Shannon Laboratory (Florham Park, New Jersey) 2003–present: Professor of computing science, University of Alberta (Edmonton, Alberta) 2017–2023: Distinguished research scientist, DeepMind Alberta, Google DeepMind (Edmonton, Alberta) 2024–Present: Research scientist, Keen Technologies === Reinforcement learning === Sutton joined Andrew Barto in the early 1980s at UMass, trying to explore the behavior of neurons in the human brain as the basis for human intelligence, a concept that had been advanced by computer scientist A. Harry Klopf. Sutton and Barto used mathematics toward furthering the concept and using it as the basis for artificial intelligence. This concept became known as reinforcement learning and went on to becoming a key part of artificial intelligence techniques. Barto and Sutton used Markov decision processes (MDP) as the mathematical foundation to explain how agents (algorithmic entities) made decisions when in a stochastic or random environment, receiving rewards at the end of every action. Traditional MDP theory assumed the agents knew all information about the MDPs in their attempt toward maximizing their cumulative rewards. Barto and Sutton's reinforcement learning techniques allowed for both the environment and the rewards to be unknown, and thus allowed for these category of algorithms to be applied to a wide array of problems. Sutton returned to Canada in the 2000s and continued working on the topic which continued to develop in academic circles until one of its first major real world applications saw Google's AlphaGo program built on this concept defeating the then prevailing human champion. Barto and Sutton have widely been credited and accepted as pioneers of modern reinforcement learning, with the technique itself being foundational to the AI boom. In a 2019 essay, Sutton proposed the "bitter lesson", which criticized the field of AI research for failing to learn that "building in how we think we think does not work in the long run", arguing that "70 years of AI research [had shown] that general methods that leverage computation are ultimately the most effective, and by a large margin", beating efforts building on human knowledge about specific fields like computer vision, speech recognition, chess or Go. Sutton argues that large language models aren’t capable of learning on-the-job, and so new model architectures are required to enable continual learning. Sutton further argues that a special training phase will be unnecessary — the agent will learn on-the-fly, rendering large language models obsolete. In 2023, Sutton and John Carmack announced a partnership for the development of artificial general intelligence (AGI). === Awards and honors === Sutton has been a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI) since 2001; his nomination read: "For significant contributions to many topics in machine learning, including reinforcement learning, temporal difference techniques, and neural networks." In 2003, he received the President's Award from the International Neural Network Society and in 2013, the Outstanding Achievement in Research award from the University of Massachusetts Amherst. He received the 2024 Turing Award from the Association for Computing Machinery together with Andrew Barto; the citation of the award read: "For developing the conceptual and algorithmic foundations of reinforcement learning." In 2016, Sutton was elected Fellow of the Royal Society of Canada. In 2021, he was elected Fellow of the Royal Society (FRS) of London. === Research === Sutton introduced temporal-difference methods for prediction and control, establishing convergence properties and practical algorithms. He proposed integrated learning and planning through the Dyna architecture. He co-developed the options framework for temporal abstraction in reinforcement learning. He co-authored the first modern policy gradient formulation with function approximation. Sutton's essay The Bitter Lesson argued that general methods that scale with computation dominate domain-specific approaches in the long run. His former doctoral students include David Silver and Doina Precup. === Selected publications === His publications include: == Personal life == Sutton became a Canadian citizen in 2015, and his renunciation of US citizenship was reported in 2017.

    Read more →
  • Dental AI

    Dental AI

    Dental artificial intelligence (Dental AI) refers to the application of artificial intelligence (AI) and machine-learning methods to oral healthcare data. These systems can be used to find patterns or make predictions that can aid in diagnosis, treatment, patient communication, or practice management. == History and development == Research into AI for dentistry dates to the 1990s and 2000s, alongside early CAD/CAM and image-analysis work in dental radiology. Recent developments in deep learning, especially those involving computer vision, such as convolutional neural networks, trained on large image datasets, led to a rapid improvement in performance, as well as a move from prototype technology to productization suitable for use in dental chairs. Dental schools and continuing education programs started incorporating AI content in the 2020s. == Definition and core technologies == The dental AI software accomplishes this task by using various dental images and patient data. Dental images and data used by the dental AI software include bitewing and periapical X-rays, complete mouth X-rays, detailed 3D images, intraoral images, and the patient’s medical history. The dental AI software utilizes several core technologies in accomplishing its task of assisting the dentist. First, the dental AI software utilizes machine learning and deep learning using programs that can learn from examples. Such programs are referred to as convolutional neural network (CNN) and can detect cavities and identify bone changes related to gum disease. The dental AI software utilizes computer vision, which enables the AI software to identify and quantify important features in images and data, whether they are 2D images or 3D images. Natural language processing (NLP) is used for the AI software to understand written text and can automatically generate dental notes and communicate with the patient. Furthermore, the dental AI software utilizes predictive analytics to identify patients that are more prone to dental complications and can suggest the best intervals for checkups or future dental procedures. == Applications in dentistry == Reported clinical and operational applications include diagnostic assistance for caries and periodontal disease, treatment planning assistance, patient education overlays, quality assurance, curriculum assistance for dental education, and claims documentation. Systematic reviews continue to find image-based applications such as caries detection with some variability in study design and a need for prospective validation. == Academic research and clinical validation == Several peer-reviewed studies have measured the effectiveness of AI for applications such as interproximal caries detection and periodontal bone level assessment, showing improvements over unaided readings with a focus on bias within the dataset. The Dental AI Council found variability among clinicians for diagnosis and treatment planning, suggesting the use of a standard tool as an assist. == Industry adoption == Multiple vendors offer FDA-cleared chairside AI for dental imaging: Pearl — Received U.S. FDA 510(k) clearance for its real-time radiologic aid (“Second Opinion”) in 2022 (2D), with subsequent clearances including pediatric and CBCT (“Second Opinion 3D”). TIME gave “Second Opinion” a special mention on its Best Inventions of 2022 list. Overjet — FDA-cleared for bone-level quantification and detection/outline of caries and calculus (e.g., K210187), with additional clearances expanding capabilities. VideaHealth — Received an FDA 510(k) covering 30+ detections across common dental findings (K232384), including indications for patients ages 3 and up; trade coverage has described elements of this as the first pediatric dental-AI clearance. == Regulations == In the U.S., AI-enabled dental imaging software is generally reviewed via the FDA’s 510(k) pathway. The FDA maintains a public AI-Enabled Medical Devices List, which includes numerous medical-imaging AI tools (including dental). Specific dental clearances include Overjet (K210187), VideaHealth (K232384), and Pearl entries such as “Second Opinion 3D” (K243989).

    Read more →
  • Capsule neural network

    Capsule neural network

    A capsule neural network (CapsNet) is a machine learning system that is a type of artificial neural network (ANN) that can be used to better model hierarchical relationships. The approach is an attempt to more closely mimic biological neural organization. The idea is to add structures called "capsules" to a convolutional neural network (CNN), and to reuse output from several of those capsules to form more stable (with respect to various perturbations) representations for higher capsules. The output is a vector consisting of the probability of an observation, and a pose for that observation. This vector is similar to what is done for example when doing classification with localization in CNNs. Among other benefits, capsnets address the "Picasso problem" in image recognition: images that have all the right parts but that are not in the correct spatial relationship (e.g., in a "face", the positions of the mouth and one eye are switched). For image recognition, capsnets exploit the fact that while viewpoint changes have nonlinear effects at the pixel level, they have linear effects at the part/object level. This can be compared to inverting the rendering of an object of multiple parts. == History == In 2000, Geoffrey Hinton et al. described an imaging system that combined segmentation and recognition into a single inference process using parse trees. So-called credibility networks described the joint distribution over the latent variables and over the possible parse trees. That system proved useful on the MNIST handwritten digit database. A dynamic routing mechanism for capsule networks was introduced by Hinton and his team in 2017. The approach was claimed to reduce error rates on MNIST and to reduce training set sizes. Results were claimed to be considerably better than a CNN on highly overlapped digits. In Hinton's original idea one minicolumn would represent and detect one multidimensional entity. == Transformations == An invariant is an object property that does not change as a result of some transformation. For example, the area of a circle does not change if the circle is shifted to the left. Informally, an equivariant is a property that changes predictably under transformation. For example, the center of a circle moves by the same amount as the circle when shifted. A nonequivariant is a property whose value does not change predictably under a transformation. For example, transforming a circle into an ellipse means that its perimeter can no longer be computed as π times the diameter. In computer vision, the class of an object is expected to be an invariant over many transformations. I.e., a cat is still a cat if it is shifted, turned upside down or shrunken in size. However, many other properties are instead equivariant. The volume of a cat changes when it is scaled. Equivariant properties such as a spatial relationship are captured in a pose, data that describes an object's translation, rotation, scale and reflection. Translation is a change in location in one or more dimensions. Rotation is a change in orientation. Scale is a change in size. Reflection is a mirror image. Unsupervised capsnets learn a global linear manifold between an object and its pose as a matrix of weights. In other words, capsnets can identify an object independent of its pose, rather than having to learn to recognize the object while including its spatial relationships as part of the object. In capsnets, the pose can incorporate properties other than spatial relationships, e.g., color (cats can be of various colors). Multiplying the object by the manifold poses the object (for an object, in space). == Pooling == Capsnets reject the pooling layer strategy of conventional CNNs that reduces the amount of detail to be processed at the next higher layer. Pooling allows a degree of translational invariance (it can recognize the same object in a somewhat different location) and allows a larger number of feature types to be represented. Capsnet proponents argue that pooling: violates biological shape perception in that it has no intrinsic coordinate frame; provides invariance (discarding positional information) instead of equivariance (disentangling that information); ignores the linear manifold that underlies many variations among images; routes statically instead of communicating a potential "find" to the feature that can appreciate it; damages nearby feature detectors, by deleting the information they rely upon. == Capsules == A capsule is a set of neurons that individually activate for various properties of a type of object, such as position, size and hue. Formally, a capsule is a set of neurons that collectively produce an activity vector with one element for each neuron to hold that neuron's instantiation value (e.g., hue). Graphics programs use instantiation value to draw an object. Capsnets attempt to derive these from their input. The probability of the entity's presence in a specific input is the vector's length, while the vector's orientation quantifies the capsule's properties. Artificial neurons traditionally output a scalar, real-valued activation that loosely represents the probability of an observation. Capsnets replace scalar-output feature detectors with vector-output capsules and max-pooling with routing-by-agreement. Because capsules are independent, when multiple capsules agree, the probability of correct detection is much higher. A minimal cluster of two capsules considering a six-dimensional entity would agree within 10% by chance only once in a million trials. As the number of dimensions increase, the likelihood of a chance agreement across a larger cluster with higher dimensions decreases exponentially. Capsules in higher layers take outputs from capsules at lower layers, and accept those whose outputs cluster. A cluster causes the higher capsule to output a high probability of observation that an entity is present and also output a high-dimensional (20-50+) pose. Higher-level capsules ignore outliers, concentrating on clusters. This is similar to the Hough transform, the RHT and RANSAC from classic digital image processing. == Routing by agreement == The outputs from one capsule (child) are routed to capsules in the next layer (parent) according to the child's ability to predict the parents' outputs. Over the course of a few iterations, each parents' outputs may converge with the predictions of some children and diverge from those of others, meaning that that parent is present or absent from the scene. For each possible parent, each child computes a prediction vector by multiplying its output by a weight matrix (trained by backpropagation). Next the output of the parent is computed as the scalar product of a prediction with a coefficient representing the probability that this child belongs to that parent. A child whose predictions are relatively close to the resulting output successively increases the coefficient between that parent and child and decreases it for parents that it matches less well. This increases the contribution that that child makes to that parent, thus increasing the scalar product of the capsule's prediction with the parent's output. After a few iterations, the coefficients strongly connect a parent to its most likely children, indicating that the presence of the children imply the presence of the parent in the scene. The more children whose predictions are close to a parent's output, the more quickly the coefficients grow, driving convergence. The pose of the parent (reflected in its output) progressively becomes compatible with that of its children. The coefficients' initial logits are the log prior probabilities that a child belongs to a parent. The priors can be trained discriminatively along with the weights. The priors depend on the location and type of the child and parent capsules, but not on the current input. At each iteration, the coefficients are adjusted via a "routing" softmax so that they continue to sum to 1 (to express the probability that a given capsule is the parent of a given child.) Softmax amplifies larger values and diminishes smaller values beyond their proportion of the total. Similarly, the probability that a feature is present in the input is exaggerated by a nonlinear "squashing" function that reduces values (smaller ones drastically and larger ones such that they are less than 1). This dynamic routing mechanism provides the necessary deprecation of alternatives ("explaining away") that is needed for segmenting overlapped objects. This learned routing of signals has no clear biological equivalent. Some operations can be found in cortical layers, but they do not seem to relate this technique. === Math/code === The pose vector u i {\textstyle \mathbf {u} _{i}} is rotated and translated by a matrix W i j {\textstyle \mathbf {W} _{ij}} into a vector u ^ j | i {\textstyle \mathbf {\hat {u}} _{j|i}} that predicts the output of the parent capsule. u ^ j | i = W i j u i {\displaystyle \mathbf {

    Read more →
  • REEM

    REEM

    REEM is a prototype humanoid robot built by PAL Robotics in Spain. It is a 1.70 m high humanoid robot with 22 degrees of freedom, with a mobile base with wheels, allowing it to move at 4 km/hour. The upper part of the robot consists of a torso with a touch screen, two motorized arms, which give it a high degree of expression, and a head, which is also motorized. REEM-A and REEM-B are the first and second prototypes of humanoid robots created by PAL Robotics. REEM-B can recognize, grasp and lift objects and walk by itself, avoiding obstacles through simultaneous localization and mapping. The robot accepts voice commands and can recognize faces. == Specifications ==

    Read more →
  • Kaggle

    Kaggle

    Kaggle is a data science competition platform and online community for data scientists and machine learning practitioners under Google LLC. Kaggle enables users to find and publish datasets, explore and build models in a web-based data science environment, work with other data scientists and machine learning engineers, and enter competitions to solve data science challenges. Kaggle has also facilitated the use of unethical and unreliable data in medical research. == History == Kaggle was founded by Anthony Goldbloom in April 2010. Jeremy Howard, one of the first Kaggle users, joined in November 2010 and served as the President and Chief Scientist. Also on the team was Nicholas Gruen serving as the founding chair. In 2011, the company raised $12.5 million and Max Levchin became the chairman. On March 8, 2017, Fei-Fei Li, Chief Scientist at Google, announced that Google was acquiring Kaggle. In June 2017, Kaggle surpassed 1 million registered users, and as of October 2023, it has over 15 million users in 194 countries. In 2022, founders Goldbloom and Hamner stepped down from their positions and D. Sculley became the CEO. In February 2023, Kaggle introduced Models, allowing users to discover and use pre-trained models through deep integrations with the rest of Kaggle’s platform. In April 2025, Kaggle partnered with Wikimedia Foundation. == Site overview == === Competitions === Many machine-learning competitions have been run on Kaggle since the company was founded. Notable competitions include gesture recognition for Microsoft Kinect, making a association football AI for Manchester City, coding a trading algorithm for Two Sigma Investments, and improving the search for the Higgs boson at CERN. The competition host prepares the data and a description of the problem; the host may choose whether it's going to be rewarded with money or be unpaid. Participants experiment with different techniques and compete against each other to produce the best models. Work is shared publicly through Kaggle Kernels to achieve a better benchmark and to inspire new ideas. Submissions can be made through Kaggle Kernels, via manual upload or using the Kaggle API. For most competitions, submissions are scored immediately (based on their predictive accuracy relative to a hidden solution file) and summarized on a live leaderboard. After the deadline passes, the competition host pays the prize money in exchange for "a worldwide, perpetual, irrevocable and royalty-free license [...] to use the winning Entry", i.e. the algorithm, software and related intellectual property developed, which is "non-exclusive unless otherwise specified". Alongside its public competitions, Kaggle also offers private competitions, which are limited to Kaggle's top participants. Kaggle offers a free tool for data science teachers to run academic machine-learning competitions. Kaggle also hosts recruiting competitions in which data scientists compete for a chance to interview at leading data science companies like Facebook, Winton Capital, and Walmart. Kaggle's competitions have resulted in successful projects such as furthering HIV research, chess ratings and traffic forecasting. Geoffrey Hinton and George Dahl used deep neural networks to win a competition hosted by Merck. Vlad Mnih (one of Hinton's students) used deep neural networks to win a competition hosted by Adzuna. This resulted in the technique being taken up by others in the Kaggle community. Tianqi Chen from the University of Washington also used Kaggle to show the power of XGBoost, which has since replaced Random Forest as one of the main methods used to win Kaggle competitions. Several academic papers have been published based on findings from Kaggle competitions. A contributor to this is the live leaderboard, which encourages participants to continue innovating beyond existing best practices. The winning methods are frequently written on the Kaggle Winner's Blog. === Progression system === Kaggle has implemented a progression system to recognize and reward users based on their contributions and achievements within the platform. This system consists of five tiers: Novice, Contributor, Expert, Master, and Grandmaster. Each tier is achieved by meeting specific criteria in competitions, datasets, kernels (code-sharing), and discussions. The highest tier, Kaggle Grandmaster, is awarded to users who have ranked at the top of multiple competitions including high ranking in a solo team. As of April 2, 2025, out of 23.29 million Kaggle accounts, 2,973 have achieved Kaggle Master status and 612 have achieved Kaggle Grandmaster status. === Kaggle Notebooks === Kaggle includes a free, browser-based online integrated development environment, called Kaggle Notebooks, designed for data science and machine learning. Users can write and execute code in Python or R, import datasets, use popular libraries, and train models on CPUs, GPUs, or TPUs directly in the cloud. This environment is often used for competition submissions, tutorials, education, and exploratory data analysis. == Medical Research Problems == In December 2025, an article was published in The Transmitter titled "Exclusive: Springer Nature retracts, removes nearly 40 publications that trained neural networks on ‘bonkers’ dataset". The dataset in question was uploaded to Kaggle containing photographs of autistic and non-autistic children's faces. This dataset contained more than 2,900 images and it is unlikely that these children or their families gave consent for the photos for use in medical research or the images were ethically approved for research. The articles using the dataset in Springer Nature were retracted from the scientific literature. At least 90 other publications cite a version of the dataset. In April 2026, another two datasets were identified on Kaggle with no data provenance having been published in Nature titled: "Dozens of AI disease-prediction models were trained on dubious data". These datasets were used in 124 clinical prediction models, at least two of which have been used in hospitals in Indonesia and Spain, while one article using the dataset was referenced in a medical device patent. As of April 17, 2026, three of the articles using these datasets have been retracted from the scientific literature. In May 2026, an additional research publication using two image datasets from Kaggle is under investigation in Scientific Reports. An article in Retraction Watch "‘Comically bad’ datasets used to train clinical models for stroke and diabetes" highlighted the images included famous actors such as Sylvester Stallone as Rambo, George Clooney, Angelina Jolie and Daniel Craig as well as children. It would be unethical for the use of these child images in medical research without consent. Reverse searching images saw some of the images were not for stroke but for bell's palsy. One of the datasets is no longer available on Kaggle while the other one still remains and mentions the images may be subject to copyright. Kaggle relies on the community self-reporting metadata and provenance and mentions the stroke and diabetes dataset identified in "Evidence of unreliable data and poor data provenance in clinical prediction model research and clinical practice" does not violate their terms of service and they would have been removed if they had.

    Read more →
  • Unfold (app)

    Unfold (app)

    Unfold is a mobile application that allows users to create social media content using a variety of templates and other tools. It was founded in 2018 by Alfonso Cobo and Andy McCune. It enables users to add photos, video, and text with a variety of tools. In 2019, Unfold was acquired by Squarespace. == History == In January 2017, Alfonso Cobo was studying at Parsons School of Design when he realized there was no software or app that could create a portfolio of his work on an iPad. Cobo created an app called Portfolio, a basic version of a portfolio layout app, and the first one to exist for iPad. He launched it in 2017. After launching the first version of Portfolio, Cobo realized the more popular market and use case was on mobile. Around that time, Instagram was launching Stories. As a result, Cobo pivoted the app away from portfolios and instead focused on an app to showcase one's stories. Cobo later contacted Andy McCune, founder of social media account Earth, to collaborate with Unfold. Unfold also partnered with various companies to create custom templates. These include Equinox, Tommy Hilfiger, NARS, Billboard Music Awards, and Product Red. Unfold also launched a collection of Product Red templates to help eliminate HIV/AIDS in several African countries. In 2019, Squarespace acquired Unfold. The Unfold app has been downloaded over 60 million times and has been used to create over 1 billion Instagram stories. == Features == With Unfold, users can utilize hundreds of templates to make social content for social media platforms such as Instagram, Snapchat, and Facebook. The free app offers users basic templates and standard fonts, filters, and stickers, and there are also premium templates available for a monthly subscription. With Unfold+ and Unfold Pro (previously Unfold for Brands), users can access premium templates and tools, as well as upload custom brand assets and fonts. In 2020, Unfold launched Bio Sites, which allows users to link to multiple sites and platforms.

    Read more →
  • Lumpers and splitters

    Lumpers and splitters

    Lumpers and splitters are opposing factions in any academic discipline that has to place individual examples into rigorously defined categories. The lumper–splitter problem occurs when there is the desire to create classifications and assign examples to them, for example, schools of literature, biological taxa, and so on. A "lumper" is a person who assigns examples broadly, judging that differences are not as important as signature similarities. A "splitter" makes precise definitions, and creates new categories to classify samples that differ in key ways. == Origin of the terms == The earliest known use of these terms was thought to be by Charles Darwin, in a letter to Joseph Dalton Hooker in 1857: "It is good to have hair-splitters & lumpers". But according to research done by the deputy director at NCSE, Glenn Branch, the credit is due to naturalist Edward Newman who wrote in 1845, "The time has arrived for discarding imaginary species, and the duty of doing this is as imperative as the admission of new ones when such are really discovered. The talents described under the respective names of 'hair-splitting' and 'lumping' are unquestionably yielding their power to the mightier power of Truth." They were then introduced more widely by George G. Simpson in his 1945 work The Principles of Classification and a Classification of Mammals. As he put it: splitters make very small units – their critics say that if they can tell two animals apart, they place them in different genera ... and if they cannot tell them apart, they place them in different species. ... Lumpers make large units – their critics say that if a carnivore is neither a dog nor a bear, they call it a cat. A later use can be found in the title of a 1969 paper "On lumpers and splitters ..." by the medical geneticist Victor McKusick. Reference to lumpers and splitters in the humanities appeared in a debate in 1975 between J. H. Hexter and Christopher Hill, in the Times Literary Supplement. It followed from Hexter's detailed review of Hill's book Change and Continuity in Seventeenth Century England, in which Hill developed Max Weber's argument that the rise of capitalism was facilitated by Calvinist Puritanism. Hexter objected to Hill's "mining" of sources to find evidence that supported his theories. Hexter argued that Hill plucked quotations from sources in a way that distorted their meaning. Hexter explained this as a mental habit that he called "lumping". According to him, "lumpers" rejected differences and chose to emphasise similarities. Any evidence that did not fit their arguments was ignored as aberrant. Splitters, by contrast, emphasised differences, and resisted simple schemes. While lumpers consistently tried to create coherent patterns, splitters preferred incoherent complexity. == Usage in various fields == === Biology === The categorisation and naming of a particular species should be regarded as a hypothesis about the evolutionary relationships and distinguishability of that group of organisms. As further information comes to hand, the hypothesis may be confirmed or refuted. Sometimes, especially in the past when communication was more difficult, taxonomists working in isolation have given two distinct names to individual organisms later identified as the same species. When two named species are agreed to be of the same species, the older species name is almost always retained dropping the newer species name honouring a convention known as "priority of nomenclature". This form of lumping is technically called synonymisation. Dividing a taxon into multiple, often new, taxa is called splitting. Taxonomists are often referred to as "lumpers" or "splitters" by their colleagues, depending on their personal approach to recognizing differences or commonalities between organisms. For example, the number of genera used in Pteridophyte Phylogeny Group I (PPG I) has proved controversial. PPG I uses 18 lycophyte and 319 fern genera. The earlier system put forward by Smith et al. (2006) had suggested a range of 274 to 312 genera for ferns alone. By contrast, the system of Christenhusz & Chase (2014) used 5 lycophyte and about 212 fern genera. The number of fern genera was further reduced to 207 in a subsequent publication. Defending PPG I, Schuettpelz et al. (2018) argue that the larger number of genera is a result of "the gradual accumulation of new collections and new data" and hence "a greater appreciation of fern diversity and ... an improved ability to distinguish taxa". They also argue that the number of species per genus in the PPG I system is already higher than in other groups of organisms (about 33 species per genus for ferns as opposed to about 22 species per genus for angiosperms) and that reducing the number of genera as Christenhusz and Chase propose yields the excessive number of about 50 species per genus for ferns. In response, Christenhusz and Chase (2018) argue that the excessive splitting of genera destabilises the usage of names and will lead to greater instability in future, and that the highly split genera have few if any characters that can be used to recognise them, making identification difficult, even to generic level. They further argue that comparing numbers of species per genus in different groups is "fundamentally meaningless". === History === In history, lumpers are those who tend to create broad definitions that cover large periods of time and many disciplines, whereas splitters want to assign names to tight groups of inter-relationships. Lumping tends to create a more and more unwieldy definition, with members having less and less mutually in common. This can lead to definitions which are little more than conventionalities, or groups which join fundamentally different examples. Splitting often leads to "distinctions without difference", ornate and fussy categories, and failure to see underlying similarities. For example, in the arts, "Romantic" can refer specifically to a period of German poetry roughly from 1780 to 1810, but would exclude the later work of Goethe, among other writers. In music it can mean every composer from Hummel through Rachmaninoff, plus many that came after. === Software modelling === Software engineering often proceeds by building models (sometimes known as model-driven architecture). A lumper is keen to generalise, and produces models with a small number of broadly defined objects. A splitter is reluctant to generalise, and produces models with a large number of narrowly defined objects. Conversion between the two styles is not necessarily symmetrical. For example, if error messages in two narrowly defined classes behave in the same way, the classes can be easily combined. But if some messages in a broad class behave differently, every object in the class must be examined before the class can be split. This illustrates the principle that "splits can be lumped more easily than lumps can be split". === Language classification === There is no agreement among historical linguists about what amount of evidence is needed for two languages to be safely classified in the same language family. For this reason, many proposed language families have had lumper–splitter controversies, including Altaic, Pama–Nyungan, Nilo-Saharan, and most of the larger families of the Americas. At a completely different level, the splitting of a mutually intelligible dialect continuum into different languages, or lumping them into one, is also an issue that continually comes up, though the consensus in contemporary linguistics is that there is no completely objective way to settle the question. Splitters regard the comparative method (meaning not comparison in general, but only reconstruction of a common ancestor or protolanguage) as the only valid proof of kinship, and consider genetic relatedness to be the question of interest. American linguists of recent decades tend to be splitters. Lumpers are more willing to admit techniques like mass lexical comparison or lexicostatistics, and mass typological comparison, and to tolerate the uncertainty of whether relationships found by these methods are the result of linguistic divergence (descent from common ancestor) or language convergence (borrowing). Much long-range comparison work has been from Russian linguists belonging to the Moscow School of Comparative Linguistics, most notably Vladislav Illich-Svitych and Sergei Starostin. In the United States, Greenberg and Ruhlen's work has been met with little acceptance from linguists. Earlier American linguists like Morris Swadesh and Edward Sapir also pursued large-scale classifications like Sapir's 1929 scheme for the Americas, accompanied by controversy similar to that today. === Religious studies === Paul F. Bradshaw suggests that the same principles of lumping and splitting apply to the study of early Christian liturgy. Lumpers, who tend to predominate in this field, try to find a single line of successive texts from the apostolic age to the

    Read more →
  • CoDi

    CoDi

    CoDi is a cellular automaton (CA) model for spiking neural networks (SNNs). CoDi is an acronym for Collect and Distribute, referring to the signals and spikes in a neural network. CoDi uses a von Neumann neighborhood modified for a three-dimensional space; each cell looks at the states of its six orthogonal neighbors and its own state. In a growth phase a neural network is grown in the CA-space based on an underlying chromosome. There are four types of cells: neuron body, axon, dendrite and blank. The growth phase is followed by a signaling- or processing-phase. Signals are distributed from the neuron bodies via their axon tree and collected from connection dendrites. These two basic interactions cover every case, and they can be expressed simply, using a small number of rules. == Cell interaction during signaling == The neuron body cells collect neural signals from the surrounding dendritic cells and apply an internally defined function to the collected data. In the CoDi model the neurons sum the incoming signal values and fire after a threshold is reached. This behavior of the neuron bodies can be modified easily to suit a given problem. The output of the neuron bodies is passed on to its surrounding axon cells. Axonal cells distribute data originating from the neuron body. Dendritic cells collect data and eventually pass it to the neuron body. These two types of cell-to-cell interaction cover all kinds of cell encounters. Every cell has a gate, which is interpreted differently depending on the type of the cell. A neuron cell uses this gate to store its orientation, i.e. the direction in which the axon is pointing. In an axon cell, the gate points to the neighbor from which the neural signals are received. An axon cell accepts input only from this neighbor, but makes its own output available to all its neighbors. In this way axon cells distribute information. The source of information is always a neuron cell. Dendritic cells collect information by accepting information from any neighbor. They give their output, (e.g. a Boolean OR operation on the binary inputs) only to the neighbor specified by their own gate. In this way, dendritic cells collect and sum neural signals, until the final sum of collected neural signals reaches the neuron cell. Each axonal and dendritic cell belongs to exactly one neuron cell. This configuration of the CA-space is guaranteed by the preceding growth phase. == Synapses == The CoDi model does not use explicit synapses, because dendrite cells that are in contact with an axonal trail (i.e. have an axon cell as neighbor) collect the neural signals directly from the axonal trail. This results from the behavior of axon cells, which distribute to every neighbor, and from the behavior of the dendrite cells, which collect from any neighbor. The strength of a neuron-neuron connection (a synapse) is represented by the number of their neighboring axon and dendrite cells. The exact structure of the network and the position of the axon-dendrite neighbor pairs determine the time delay and strength (weight) of a neuron-neuron connection. This principle infers that a single neuron-neuron connection can consist of several synapse with different time delays with independent weights. == Genetic encoding and growth of the network == The chromosome is initially distributed throughout the CA-space, so that every cell in the CA-space contains one instruction of the chromosome, i.e. one growth instruction, so that the chromosome belongs to the network as a whole. The distributed chromosome technique of the CoDi model makes maximum use of the available CA-space and enables the growth of any type of network connectivity. The local connection of the grown circuitry to its chromosome, allows local learning to be combined with the evolution of grown neural networks. Growth signals are passed to the direct neighbors of the neuron cell according to its chromosome information. The blank neighbors, which receive a neural growth signal, turn into either an axon cell or a dendrite cell. The growth signals include information containing the cell type of the cell that is to be grown from the signal. To decide in which directions axonal or dendritic trails should grow, the grown cells consult their chromosome information which encodes the growth instructions. These growth instructions can have an absolute or a relative directional encoding. An absolute encoding masks the six neighbors (i.e. directions) of a 3D cell with six bits. After a cell is grown, it accepts growth signals only from the direction from which it received its first signal. This reception direction information is stored in the gate position of each cell's state. == Implementation as a partitioned CA == The states of our CAs have two parts, which are treated in different ways. The first part of the cell-state contains the cell's type and activity level and the second part serves as an interface to the cell's neighborhood by containing the input signals from the neighbors. Characteristic of our CA is that only part of the state of a cell is passed to its neighbors, namely the signal and then only to those neighbors specified in the fixed part of the cell state. This CA is called partitioned, because the state is partitioned into two parts, the first being fixed and the second is variable for each cell. The advantage of this partitioning-technique is that the amount of information that defines the new state of a CA cell is kept to a minimum, due to its avoidance of redundant information exchange. == Implementation in hardware == Since CAs are only locally connected, they are ideal for implementation on purely parallel hardware. When designing the CoDi CA-based neural networks model, the objective was to implement them directly in hardware (FPGAs). Therefore, the CA was kept as simple as possible, by having a small number of bits to specify the state, keeping the CA rules few in number, and having few cellular neighbors. The CoDi model was implemented in the FPGA based CAM-Brain Machine (CBM) by Korkin. == History == CoDi was introduced by Gers et al. in 1998. A specialized parallel machine based on FPGA Hardware (CAM) to run the CoDi model on a large scale was developed by Korkin et al. De Garis conducted a series of experiments on the CAM-machine evaluating the CoDi model. The original model, where learning is based on evolutionary algorithms, has been augmented with a local learning rule via feedback from dendritic spikes by Schwarzer.

    Read more →
  • Pattern language

    Pattern language

    A pattern language is an organized and coherent set of patterns, each of which describes a problem and the core of a solution that can be used in many ways within a specific field of expertise. The term was coined by architect Christopher Alexander and popularized by his 1977 book A Pattern Language. A pattern language can also be an attempt to express the deeper wisdom of what brings aliveness within a particular field of human endeavor, through a set of interconnected patterns. Aliveness is one placeholder term for "the quality that has no name": a sense of wholeness, spirit, or grace, that while of varying form, is precise and empirically verifiable. Alexander claims that ordinary people can use this design approach to successfully solve very large, complex design problems. == What is a pattern? == When a designer designs something – whether a house, computer program, or lamp – they must make many decisions about how to solve problems. A single problem is documented with its typical place (the syntax), and use (the grammar) with the most common and recognized good solution seen in the wild, like the examples seen in dictionaries. Each such entry is a single design pattern. Each pattern has a name, a descriptive entry, and some cross-references, much like a dictionary entry. A documented pattern should explain why that solution is good in the pattern's contexts. Elemental or universal patterns such as "door" or "partnership" are versatile ideals of design, either as found in experience or for use as components in practice, explicitly described as holistic resolutions of the forces in recurrent contexts and circumstances, whether in architecture, medicine, software development or governance, etc. Patterns might be invented or found and studied, such as the naturally occurring patterns of design that characterize human environments. Like all languages, a pattern language has vocabulary, syntax, and grammar – but a pattern language applies to some complex activity other than communication. In pattern languages for design, the parts break down in this way: The language description – the vocabulary – is a collection of named, described solutions to problems in a field of interest. These are called design patterns. So, for example, the language for architecture describes items like: settlements, buildings, rooms, windows, latches, etc. Each solution includes syntax, a description that shows where the solution fits in a larger, more comprehensive or more abstract design. This automatically links the solution into a web of other needed solutions. For example, rooms have ways to get light, and ways to get people in and out. The solution includes grammar that describes how the solution solves a problem or produces a benefit. So, if the benefit is unneeded, the solution is not used. Perhaps that part of the design can be left empty to save money or other resources; if people do not need to wait to enter a room, a simple doorway can replace a waiting room. In the language description, grammar and syntax cross index (often with a literal alphabetic index of pattern names) to other named solutions, so the designer can quickly think from one solution to related, needed solutions, and document them in a logical way. In Christopher Alexander's book A Pattern Language, the patterns are in decreasing order by size, with a separate alphabetic index. The web of relationships in the index of the language provides many paths through the design process. This simplifies the design work because designers can start the process from any part of the problem they understand and work toward the unknown parts. At the same time, if the pattern language has worked well for many projects, there is reason to believe that even a designer who does not completely understand the design problem at first will complete the design process, and the result will be usable. For example, skiers coming inside must shed snow and store equipment. The messy snow and boot cleaners should stay outside. The equipment needs care, so the racks should be inside. == Many patterns form a language == Just as words must have grammatical and semantic relationships to each other in order to make a spoken language useful, design patterns must be related to each other in position and utility order to form a pattern language. Christopher Alexander's work describes a process of decomposition, in which the designer has a problem (perhaps a commercial assignment), selects a solution, then discovers new, smaller problems resulting from the larger solution. Occasionally, the smaller problems have no solution, and a different larger solution must be selected. Eventually all of the remaining design problems are small enough or routine enough to be solved by improvisation by the builders, and the "design" is done. The actual organizational structure (hierarchical, iterative, etc.) is left to the discretion of the designer, depending on the problem. This explicitly lets a designer explore a design, starting from some small part. When this happens, it's common for a designer to realize that the problem is actually part of a larger solution. At this point, the design almost always becomes a better design. In the language, therefore, each pattern has to indicate its relationships to other patterns and to the language as a whole. This gives the designer using the language a great deal of guidance about the related problems that must be solved. The most difficult part of having an outside expert apply a pattern language is in fact to get a reliable, complete list of the problems to be solved. Of course, the people most familiar with the problems are the people that need a design. So, Alexander famously advocated on-site improvisation by concerned, empowered users, as a powerful way to form very workable large-scale initial solutions, maximizing the utility of a design, and minimizing the design rework. The desire to empower users of architecture was, in fact, what led Alexander to undertake a pattern language project for architecture in the first place. == Design problems in a context == An important aspect of design patterns is to identify and document the key ideas that make a good system different from a poor system (that may be a house, a computer program or an object of daily use), and to assist in the design of future systems. The idea expressed in a pattern should be general enough to be applied in very different systems within its context, but still specific enough to give constructive guidance. The range of situations in which the problems and solutions addressed in a pattern apply is called its context. An important part in each pattern is to describe this context. Examples can further illustrate how the pattern applies to very different situation. For instance, Alexander's pattern "A PLACE TO WAIT" addresses bus stops in the same way as waiting rooms in a surgery, while still proposing helpful and constructive solutions. The "Gang-of-Four" book Design Patterns by Gamma et al. proposes solutions that are independent of the programming language, and the program's application domain. Still, the problems and solutions described in a pattern can vary in their level of abstraction and generality on the one side, and specificity on the other side. In the end this depends on the author's preferences. However, even a very abstract pattern will usually contain examples that are, by nature, absolutely concrete and specific. Patterns can also vary in how far they are proven in the real world. Alexander gives each pattern a rating by zero, one or two stars, indicating how well they are proven in real-world examples. It is generally claimed that all patterns need at least some existing real-world examples. It is, however, conceivable to document yet unimplemented ideas in a pattern-like format. The patterns in Alexander's book also vary in their level of scale – some describing how to build a town or neighbourhood, others dealing with individual buildings and the interior of rooms. Alexander sees the low-scale artifacts as constructive elements of the large-scale world, so they can be connected to a hierarchic network. === Balancing of forces === A pattern must characterize the problems that it is meant to solve, the context or situation where these problems arise, and the conditions under which the proposed solutions can be recommended. Often these problems arise from a conflict of different interests or "forces". A pattern emerges as a dialogue that will then help to balance the forces and finally make a decision. For instance, there could be a pattern suggesting a wireless telephone. The forces would be the need to communicate, and the need to get other things done at the same time (cooking, inspecting the bookshelf). A very specific pattern would be just "WIRELESS TELEPHONE". More general patterns would be "WIRELESS DEVICE" or "SECONDARY ACTIVITY", suggesting that a secondary activity (such as talking on t

    Read more →
  • Inception score

    Inception score

    The Inception Score (IS) is an algorithm used to assess the quality of images created by a generative image model such as a generative adversarial network (GAN). The score is calculated based on the output of a separate, pretrained Inception v3 image classification model applied to a sample of (typically around 30,000) images generated by the generative model. The Inception Score is maximized when the following conditions are true: The entropy of the distribution of labels predicted by the Inceptionv3 model for the generated images is minimized. In other words, the classification model confidently predicts a single label for each image. Intuitively, this corresponds to the desideratum of generated images being "sharp" or "distinct". The predictions of the classification model are evenly distributed across all possible labels. This corresponds to the desideratum that the output of the generative model is "diverse". It has been somewhat superseded by the related Fréchet inception distance. While the Inception Score only evaluates the distribution of generated images, the FID compares the distribution of generated images with the distribution of a set of real images ("ground truth"). == Definition == Let there be two spaces, the space of images Ω X {\displaystyle \Omega _{X}} and the space of labels Ω Y {\displaystyle \Omega _{Y}} . The space of labels is finite. Let p g e n {\displaystyle p_{gen}} be a probability distribution over Ω X {\displaystyle \Omega _{X}} that we wish to judge. Let a discriminator be a function of type p d i s : Ω X → M ( Ω Y ) {\displaystyle p_{dis}:\Omega _{X}\to M(\Omega _{Y})} where M ( Ω Y ) {\displaystyle M(\Omega _{Y})} is the set of all probability distributions on Ω Y {\displaystyle \Omega _{Y}} . For any image x {\displaystyle x} , and any label y {\displaystyle y} , let p d i s ( y | x ) {\displaystyle p_{dis}(y|x)} be the probability that image x {\displaystyle x} has label y {\displaystyle y} , according to the discriminator. It is usually implemented as an Inception-v3 network trained on ImageNet. The Inception Score of p g e n {\displaystyle p_{gen}} relative to p d i s {\displaystyle p_{dis}} is I S ( p g e n , p d i s ) := exp ⁡ ( E x ∼ p g e n [ D K L ( p d i s ( ⋅ | x ) ‖ ∫ p d i s ( ⋅ | x ) p g e n ( x ) d x ) ] ) {\displaystyle IS(p_{gen},p_{dis}):=\exp \left(\mathbb {E} _{x\sim p_{gen}}\left[D_{KL}\left(p_{dis}(\cdot |x)\|\int p_{dis}(\cdot |x)p_{gen}(x)dx\right)\right]\right)} Equivalent rewrites include ln ⁡ I S ( p g e n , p d i s ) := E x ∼ p g e n [ D K L ( p d i s ( ⋅ | x ) ‖ E x ∼ p g e n [ p d i s ( ⋅ | x ) ] ) ] {\displaystyle \ln IS(p_{gen},p_{dis}):=\mathbb {E} _{x\sim p_{gen}}\left[D_{KL}\left(p_{dis}(\cdot |x)\|\mathbb {E} _{x\sim p_{gen}}[p_{dis}(\cdot |x)]\right)\right]} ln ⁡ I S ( p g e n , p d i s ) := H [ E x ∼ p g e n [ p d i s ( ⋅ | x ) ] ] − E x ∼ p g e n [ H [ p d i s ( ⋅ | x ) ] ] {\displaystyle \ln IS(p_{gen},p_{dis}):=H[\mathbb {E} _{x\sim p_{gen}}[p_{dis}(\cdot |x)]]-\mathbb {E} _{x\sim p_{gen}}[H[p_{dis}(\cdot |x)]]} ln ⁡ I S {\displaystyle \ln IS} is nonnegative by Jensen's inequality. Pseudocode:INPUT discriminator p d i s {\displaystyle p_{dis}} . INPUT generator g {\displaystyle g} . Sample images x i {\displaystyle x_{i}} from generator. Compute p d i s ( ⋅ | x i ) {\displaystyle p_{dis}(\cdot |x_{i})} , the probability distribution over labels conditional on image x i {\displaystyle x_{i}} . Sum up the results to obtain p ^ {\displaystyle {\hat {p}}} , an empirical estimate of ∫ p d i s ( ⋅ | x ) p g e n ( x ) d x {\displaystyle \int p_{dis}(\cdot |x)p_{gen}(x)dx} . Sample more images x i {\displaystyle x_{i}} from generator, and for each, compute D K L ( p d i s ( ⋅ | x i ) ‖ p ^ ) {\displaystyle D_{KL}\left(p_{dis}(\cdot |x_{i})\|{\hat {p}}\right)} . Average the results, and take its exponential. RETURN the result. === Interpretation === A higher inception score is interpreted as "better", as it means that p g e n {\displaystyle p_{gen}} is a "sharp and distinct" collection of pictures. ln ⁡ I S ( p g e n , p d i s ) ∈ [ 0 , ln ⁡ N ] {\displaystyle \ln IS(p_{gen},p_{dis})\in [0,\ln N]} , where N {\displaystyle N} is the total number of possible labels. ln ⁡ I S ( p g e n , p d i s ) = 0 {\displaystyle \ln IS(p_{gen},p_{dis})=0} iff for almost all x ∼ p g e n {\displaystyle x\sim p_{gen}} p d i s ( ⋅ | x ) = ∫ p d i s ( ⋅ | x ) p g e n ( x ) d x {\displaystyle p_{dis}(\cdot |x)=\int p_{dis}(\cdot |x)p_{gen}(x)dx} That means p g e n {\displaystyle p_{gen}} is completely "indistinct". That is, for any image x {\displaystyle x} sampled from p g e n {\displaystyle p_{gen}} , discriminator returns exactly the same label predictions p d i s ( ⋅ | x ) {\displaystyle p_{dis}(\cdot |x)} . The highest inception score N {\displaystyle N} is achieved if and only if the two conditions are both true: For almost all x ∼ p g e n {\displaystyle x\sim p_{gen}} , the distribution p d i s ( y | x ) {\displaystyle p_{dis}(y|x)} is concentrated on one label. That is, H y [ p d i s ( y | x ) ] = 0 {\displaystyle H_{y}[p_{dis}(y|x)]=0} . That is, every image sampled from p g e n {\displaystyle p_{gen}} is exactly classified by the discriminator. For every label y {\displaystyle y} , the proportion of generated images labelled as y {\displaystyle y} is exactly E x ∼ p g e n [ p d i s ( y | x ) ] = 1 N {\displaystyle \mathbb {E} _{x\sim p_{gen}}[p_{dis}(y|x)]={\frac {1}{N}}} . That is, the generated images are equally distributed over all labels.

    Read more →
  • UMBEL

    UMBEL

    UMBEL (Upper Mapping and Binding Exchange Layer) is a logically organized knowledge graph of 34,000 concepts and entity types that can be used in information science for relating information from disparate sources to one another. It was retired at the end of 2019. UMBEL was first released in July 2008. Version 1.00 was released in February 2011. Its current release is version 1.50. The grounding of this information occurs by common reference to the permanent URIs for the UMBEL concepts; the connections within the UMBEL upper ontology enable concepts from sources at different levels of abstraction or specificity to be logically related. Since UMBEL is an open-source extract of the OpenCyc knowledge base, it can also take advantage of the reasoning capabilities within Cyc. UMBEL has two means to promote the semantic interoperability of information:. It is: An ontology of about 35,000 reference concepts, designed to provide common mapping points for relating different ontologies or schema to one another, and A vocabulary for aiding that ontology mapping, including expressions of likelihood relationships distinct from exact identity or equivalence. This vocabulary is also designed for interoperable domain ontologies. UMBEL is written in the Semantic Web languages of SKOS and OWL 2. It is a class structure used in Linked Data, along with OpenCyc, YAGO, and the DBpedia ontology. Besides data integration, UMBEL has been used to aid concept search, concept definitions, query ranking, ontology integration, and ontology consistency checking. It has also been used to build large ontologies and for online question answering systems. Including OpenCyc, UMBEL has about 65,000 formal mappings to DBpedia, PROTON, GeoNames, and schema.org, and provides linkages to more than 2 million Wikipedia pages (English version). All of its reference concepts and mappings are organized under a hierarchy of 31 different "super types", which are mostly disjoint from one another. Each of these "super types" has its own typology of entity classes to provide flexible tie-ins for external content. 90% of UMBEL is contained in these entity classes.

    Read more →
  • Computational Intelligence (journal)

    Computational Intelligence (journal)

    Computational Intelligence Journal is a peer-reviewed scientific journal covering research on artificial intelligence and computer science. The journal published novel research as well as innovative applications in a broad range of AI, covering Computational Intelligence is an artificial intelligence journal publishing novel research on a broad range of experimental and theoretical topics in AI and computer science. With a broad scope, the journal covers machine learning, knowledge mining, web intelligence, AI language, and philosophical implications. The journal was established in 1985 and is published by Wiley-Blackwell. Currently, the editors-in-chief is Diane Inkpen. The quality of the journal as an academic publishing venue is evaluated according to public citation impact metrics. in 2022, the Computational Intelligence Journal CiteScore of Scopus was 5.3, while Clarivate's Web of Science gives it 0.39 in the Journal Citation Indicator and 2,8 in the Journal Impact Factor.

    Read more →