Machine Learning Glossary
Key Terminology in Machine Learning
machine learning terminology
Find below the Machine learning terminology or Machine learning glossary of terms journal to help readers understand
common terms in machine learning and artificial intelligence (AI), statistics, and data mining.
Here we provide a glossary/terminology of common terms journal.
The machine learning definitions are not designed to be completely general, but instead are aimed at the most common case/issue on
applications of machine learning and the knowledge discovery process.
| Journal of Machine Learning | "JOURNAL OF MACHINE LEARNING RESEACH DESCRIPTION 2018" |
|---|---|
| AI accelerator | Ai accelerator coprocessor designed to accelerate artificial neural networks, machine vision and other machine learning algorithms for robotics, internet of things and other |
| Action model learning | Action model learning (sometimes abbreviated action learning) is an area of machine learning concerned with creation and modification of software agent's |
| Active learning | Active learning is about a machine learning method. For active learning in the context of education, see active learning. Active learning is a special case of |
| Adobe eLearning Suite | Communication Suite Adobe eLearning Suite FAQ Authorware FAQ Archived July 6, 2011, at the Wayback Machine. Captivate 5 and Adobe eLearning Suite 2 launch announcement: |
| Adversarial machine learning | Adversarial machine learning is a research field that lies at the intersection of machine learning and computer security. It aims to enable the safe adoption |
| Agent mining | interdisciplinary area that synergizes multiagent systems with data mining and machine learning. The interaction and integration between multiagent systems and data |
| AlchemyAPI | AlchemyAPI is a company that uses machine learning (specifically, deep learning) to do natural language processing (specifically, semantic text analysis |
| Algorithm Selection | cost-sensitive hierarchical clustering (CSHC) in machine learning, algorithm selection is better known as meta-learning. The portfolio of algorithms consists of machine learning algorithms |
| Algorithmic learning theory | Algorithmic learning theory is a mathematical framework for analyzing machine learning problems and algorithms. Synonyms include formal learning theory and |
| Andrew McCallum | University of Massachusetts Amherst. His primary specialties are in machine learning, natural language processing, information extraction, information integration |
| Andrew Ng | an online education platform. Ng researches primarily in machine learning and deep learning. His early work includes the Stanford Autonomous Helicopter |
| Apache Mahout | produce free implementations of distributed or otherwise scalable machine learning algorithms focused primarily in the areas of collaborative filtering |
| Apache Singa | algorithms for machine learning models, e.g., layers for neural network models, optimizers/initializer/metric/loss for general machine learning models. |
| Apache Spark | the class of iterative algorithms are the training algorithms for machine learning systems, which formed the initial impetus for developing Apache Spark |
| Apprenticeship learning | Apprenticeship learning, or apprenticeship via inverse reinforcement learning (AIRP), is a concept in the field of artificial intelligence and machine learning, developed |
| Apptek | human language technology (automatic speech recognition, machine translation, NLP, machine learning and artificial intelligence), headquartered in McLean |
| Arff | Aircraft Rescue and Firefighting (ARFF) Attribute-Relation File Format (ARFF), an input file format used by the machine learning tool Weka (machine learning) |
| Arthur Samuel | He coined the term |
| Artificial intelligence | when a machine mimics |
| Artificial intelligence marketing | database marketing techniques as well as AI concept and model such as machine learning and Bayesian Network. The main difference resides in the reasoning |
| Artificial neural network | publication of machine learning research by Marvin Minsky and Seymour Papert (1969), who discovered two key issues with the computational machines that processed |
| Association rule learning | filmmaking technique, see Long take. Association rule learning is a rule-based machine learning method for discovering interesting relations between variables |
| Auditory learning | (2004). Learning styles and pedagogy in post-16 learning. A systematic and critical review Archived December 5, 2008, at the Wayback Machine.. London: |
| Augmented learning | Reality Architecture for Learning Augmented Reality Archived April 7, 2014, at the Wayback Machine. Computer Augmented Learning: The Basis of Sustained |
| Autoencoder | belief network. Representation learning Restricted Boltzmann machine Sparse dictionary learning Bengio, Y. (2009). |
| Avrim Blum | computer science, with particular activity in the fields of machine learning, computational learning theory, algorithmic game theory, and algorithms. Avrim |
| Ayasdi | the target data set, runs many different unsupervised and supervised machine learning algorithms on the data, automatically finds and ranks best fits, and |
| Backpropagation | AI portal Machine learning portal Artificial neural network Biological neural network Catastrophic interference Ensemble learning AdaBoost Overfitting |
| Bag-of-words model | some problems. (For instance, this option is implemented in the WEKA machine learning software system.) Bag-of-word model is an orderless document representation-only |
| Balabit | the development of IT security systems and related services using machine learning to secure risky privileged accounts. Balabit was founded in 2000 |
| Barney Pell | knowledge management, machine learning, artificial intelligence, and scheduling systems. In computer game playing and machine learning, he was a pioneer in |
| Bayes error rate | finds important use in the study of patterns and machine learning techniques. In terms of machine learning and pattern classification, the labels of a set |
| Bayesian optimization | including learning to rank, interactive animation, robotics, sensor networks, automatic algorithm configuration, automatic machine learning toolboxes |
| Ben Taskar | - November 18, 2013) was a professor and researcher in the area of machine learning and applications to computational linguistics and computer vision. |
| Bernhard Scholkopf | Department of Empirical Inference. He is a leading researcher in the machine learning community, where he is particularly active in the field of kernel methods |
| Bias-variance tradeoff | In statistics and machine learning, the bias-variance tradeoff (or dilemma) is the problem of simultaneously minimizing two sources of error that prevent |
| Boltzmann machine | discussed below, Boltzmann machines with unconstrained connectivity have not proven useful for practical problems in machine learning or inference, but if the |
| Boosting | a machine learning ensemble meta-algorithm for primarily reducing bias, and also variance in supervised learning, and a family of machine learning algorithms |
| Bootstrap aggregating | called bagging, is a machine learning ensemble meta-algorithm designed to improve the stability and accuracy of machine learning algorithms used in statistical |
| Brendan Frey | Canadian-born machine learning and genome biology researcher, known mainly for his work on factor graphs, the wake-sleep algorithm for deep learning, and using |
| BrownBoost | boosting algorithms, BrownBoost is used in conjunction with other machine learning methods. BrownBoost was introduced by Yoav Freund in 2001. AdaBoost |
| CART | Classification and regression tree, a type of decision tree learning, used in machine learning, data mining and predictive analytics Clermont Area Rural |
| CBCL | how the human brain works and for making intelligent machines. CBCL studies the problem of learning within a multidisciplinary approach. Its main goal is |
| CIML community portal | The computational intelligence and machine learning (CIML) community portal is an international multi-university initiative. Its primary purpose is to |
| CNTK | The Microsoft Cognitive Toolkit, or previously known as CNTK, is a deep learning framework developed by Microsoft Research. Microsoft Cognitive Toolkit |
| Cengage Learning | Cengage Learning, Inc. is an educational content, technology, and services company for the higher education, K-12, professional, and library markets worldwide |
| Chaos Machine | stunts, and generally have a good time learning and problem-solving. Over time more sets are added, so the machine grows larger with each appearance. Recently |
| Chih-Jen Lin | in machine learning, optimization, and data mining. He is best known for the open source library LIBSVM, an implementation of support vector machines. |
| Christopher G. Atkeson | work in humanoid robots, soft robotics, and machine learning, most notably on locally weighted learning. Atkeson graduated summa cum laude from Harvard |
| Classifier chains | Classifier chains is a machine learning method for problem transformation in multi-label classification. It combines the computational efficiency of the |
| Claude Sammut | a member of the editorial boards of the Journal of Machine Learning Research, the Machine Learning Journal and New Generation Computing. He was the program |
| Cluster hypothesis | In machine learning and information retrieval, the cluster hypothesis is an assumption about the nature of the data handled in those fields, which takes |
| Collective Tuning Initiative | and machine-learning techniques and improve the quality and reproducibility of the compiler (and architecture research) Online machine learning-based |
| Committee machine | A committee machine is a type of artificial neural network using a divide and conquer strategy in which the responses of multiple neural networks (experts) |
| Comparison of deep learning software | memory model Deep learning#Software libraries List of datasets for machine learning research Comparison of datasets in machine learning Comparison of numerical |
| Comparison of deep learning software/Resources | Distributed Deep LEarning |
| Computational learning theory | of machine learning algorithms. Theoretical results in machine learning mainly deal with a type of inductive learning called supervised learning. In |
| Computer-assisted language learning | video game publisher, see English Software. Computer-assisted language learning (CALL) is succinctly defined in a seminal work by Levy (1997: p.1) as |
| Concept drift | In predictive analytics and machine learning, the concept drift means that the statistical properties of the target variable, which the model is trying |
| Concept learning | contain concept-relevant features. Concept learning also refers to a learning task in which a human or machine learner is trained to classify objects by |
| Conceptual clustering | Conceptual clustering is a machine learning paradigm for unsupervised classification developed mainly during the 1980s. It is distinguished from ordinary |
| Conference on Neural Information Processing Systems | and Workshop on Neural Information Processing Systems (NIPS) is a machine learning and computational neuroscience conference held every December. The |
| Confusion matrix | In the field of machine learning and specifically the problem of statistical classification, a confusion matrix, also known as an error matrix, is a specific |
| Constructivism | Constructing Learning for as well as with others, |
| Contemporary Learning Center | Overview, |
| Corinna Cortes | Cortes is a Danish computer scientist known for her contributions to machine learning. She is currently the Head of Google Research, New York. Cortes is |
| Coupled pattern learner | Coupled Pattern Learner (CPL) is a machine learning algorithm which couples the semi-supervised learning of categories and relations to forestall the |
| Dalle Molle Institute for Artificial Intelligence Research | institute won eight international competitions in pattern recognition and machine learning. IDSIA is one of four Swiss research organisations founded by the Dalle |
| Dan Roth | of which is the idea that learning has a central role in intelligence. His work centers around the study of machine learning and inference methods to facilitate |
| Dana Ron | 73-205, 2009. D. Ron. Property Testing: A Learning Theory Perspective, Foundations and Trends in Machine Learning: vol. 1, no. 3, pages 307-402, 2008. N |
| Data analysis techniques for fraud detection | rely on systems that have been based around machine learning, rather than later incorporating machine learning into an existing system. These companies include |
| Data classification | classification (business intelligence) Classification (machine learning), classification of data using machine learning algorithms Assigning a level of sensitivity |
| Data mining | involving methods at the intersection of artificial intelligence, machine learning, statistics, and database systems. It is an interdisciplinary subfield |
| Data pre-processing | |
| Data stream mining | class membership or values of previous instances in the data stream. Machine learning techniques can be used to learn this prediction task from labeled examples |
| David Blei | Computer Science at Princeton University. His work is primarily in machine learning. His research interests include topic models and he was one of the |
| David Cournapeau | is the original author of the scikit-learn package, an open source machine learning library in the Python programming language. He works as a developer |
| David E. Goldberg | and rule learning, PhD thesis. University of Michigan. Ann Arbor, MI. 1989. Genetic algorithms in search, optimization and machine learning. Addison-Wesley |
| Decision list | variable or its negation. Ronald L. Rivest (Nov 1987). |
| Decision stump | A decision stump is a machine learning model consisting of a one-level decision tree. That is, it is a decision tree with one internal node (the root) |
| Decision tree | trees in decision analysis. For the use of the term in machine learning, see Decision tree learning. A decision tree is a decision support tool that |
| Decision tree learning | about decision trees in machine learning. For the use of the term in decision analysis, see Decision tree. Decision tree learning uses a decision tree as |
| Declara | platform learns how users interact through the use of semantic search, machine learning algorithms, and recommendations to deliver personalized suggestions |
| Deep belief network | In machine learning, a deep belief network (DBN) is a generative graphical model, or alternatively a type of deep neural network, composed of multiple |
| Deep feature synthesis | (ed.), European Working Session on Learning, Porto, Portugal, March 6-8, 1991 ; Y. Kodratoff (1991). Machine learning--EWSL-91 : proceedings. Berlin: Springer-Verlag |
| Deep learning | structured learning, hierarchical learning or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model |
| DeepMind | combining |
| Deeplearning4j | deep learning programming library written for Java and the Java virtual machine (JVM) and a computing framework with wide support for deep learning algorithms |
| Developmental robotics | allow lifelong and open-ended learning of new skills and new knowledge in embodied machines. As in human children, learning is expected to be cumulative |
| Dimensionality reduction | For dimensional reduction in physics, see Dimensional reduction. In machine learning and statistics, dimensionality reduction or dimension reduction is |
| Discretization of continuous features | In statistics and machine learning, discretization refers to the process of converting or partitioning continuous attributes, features or variables to |
| Distributed R | data loaders. It is mostly used to implement distributed versions of machine learning tasks. Distributed R is written in C++ and R, and retains the familiar |
| Dlib | creating a broad set of statistical machine learning tools and in 2009 dlib was published in the Journal of Machine Learning Research. Since then it has been |
| Domain adaptation | Adaptation is a field associated with machine learning and transfer learning. This scenario arises when we aim at learning from a source data distribution a |
| Drew Conway | book Machine Learning for Hackers, a book of case studies that illustrates data science from a hacker's perspective. He is also co-author of Machine Learning |
| E-learning | E-learning theory describes the cognitive science principles of effective multimedia learning using electronic educational technology. Cognitive research |
| EBL | Estimated blood loss European Bridge League Explanation-based learning, a form of machine learning Exploits Block List Extragalactic background light EBL of |
| ECML PKDD | on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, is one of the leading academic conferences on machine learning and |
| Eager learning | Iris; Van den Bosch, Antal (October 2005). |
| Early stopping | In machine learning, early stopping is a form of regularization used to avoid overfitting when training a learner with an iterative method, such as gradient |
| Educational technology | |
| Empirical risk minimization | statistical learning theory which defines a family of learning algorithms and is used to give theoretical bounds on the performance of learning algorithms |
| Encog | Encog is a machine learning framework available for Java, .Net, and C++. Encog supports different learning algorithms such as Bayesian Networks, Hidden |
| Ensemble | averaging (machine learning) Distribution ensemble or probability ensemble (cryptography) Ensemble learning (statistics and machine learning) Neural ensemble |
| Ensemble averaging | to be confused with Ensemble averaging (statistical mechanics). In machine learning, particularly in the creation of artificial neural networks, ensemble |
| Ensemble learning | variational Bayesian methods. In statistics and machine learning, ensemble methods use multiple learning algorithms to obtain better predictive performance |
| Ensembles of classifiers | Recently in the area of machine learning the concept of combining classifiers is proposed as a new direction for the improvement of the performance of |
| Eric Xing | Xing is a professor at Carnegie Mellon University and researcher in machine learning, computational biology, and statistical methodology. Xing received |
| Error Tolerance | intelligence portal Machine learning portal Machine learning Data mining Probably approximately correct learning Adversarial machine learning Valiant, |
| Error-driven learning | Error-driven learning is a sub-area of machine learning concerned with how an agent ought to take actions in an environment so as to minimize some error |
| Evolving classification function | classifiers are used for classifying and clustering in the field of machine learning and artificial intelligence, typically employed for data stream mining |
| Example-based machine translation | implementation of a case-based reasoning approach to machine learning. At the foundation of example-based machine translation is the idea of translation by analogy |
| Expectation propagation | Expectation propagation (EP) is a technique in Bayesian machine learning. EP finds approximations to a probability distribution. It uses an iterative approach |
| Explanation-based learning | Explanation-based learning (EBL) is a form of machine learning that exploits a very strong, or even perfect, domain theory to make generalizations or form |
| Extreme learning machine | Extreme learning machines are feedforward neural network for classification or regression with a single layer of hidden nodes, where the weights connecting |
| Feature | In machine learning and pattern recognition, a feature is an individual measurable property of a phenomenon being observed. Choosing informative, discriminating |
| Feature Selection Toolbox | Selection Toolbox (FST) is software primarily for feature selection in the machine learning domain, written in C++, developed at the Institute of Information Theory |
| Feature engineering | create features that make machine learning algorithms work. Feature engineering is fundamental to the application of machine learning, and is both difficult |
| Feature hashing | In machine learning, feature hashing, also known as the hashing trick (by analogy to the kernel trick), is a fast and space-efficient way of vectorizing |
| Feature learning | In machine learning, feature learning or representation learning is a set of techniques that learn a feature: a transformation of raw data input to a |
| Feature scaling | step. Since the range of values of raw data varies widely, in some machine learning algorithms, objective functions will not work properly without normalization |
| Feature vector | redirects here. For feature spaces in kernel machines, see Kernel method. In pattern recognition and machine learning, a feature vector is an n-dimensional vector |
| Features from accelerated segment test | (DoG) used by the SIFT, SUSAN and Harris detectors. Moreover, when machine learning techniques are applied, superior performance in terms of computation |
| Feedzai | detects fraud in omnichannel commerce. The company uses real-time, machine-based learning to analyze big data to identify fraudulent payment transactions |
| Finite-state machine | |
| First Order Inductive Learner | In machine learning, First Order Inductive Learner (FOIL) is a rule-based learning algorithm. Developed in 1990 by Ross Quinlan, FOIL learns function-free |
| Foster Provost | Editor-in-Chief of the journal Machine Learning after 6 years. He is a member of the editorial boards of the Journal of Machine Learning Research (JMLR) and the |
| Gaussian process | continuous domain, e.g. time or space. Viewed as a machine-learning algorithm, a Gaussian process uses lazy learning and a measure of the similarity between points |
| Generalization error | In supervised learning applications in machine learning and statistical learning theory, generalization error (also known as the out-of-sample error) is |
| Geoff Webb | association rule learning. His early work included advocating the use of machine learning to create black box user models; interactive machine learning; and one |
| Geoffrey Hinton | at the University of Toronto. He holds a Canada Research Chair in Machine Learning. He is the director of the program on |
| Geometric feature learning | Geometric feature learning is a technique combining machine learning and computer vision to solve visual tasks. The main goal of this method is to find |
| GloVe | GloVe is an unsupervised learning algorithm for obtaining vector representations for words. Training is performed on aggregated global word-word co-occurrence |
| Glossary of artificial intelligence | programming - Machine vision - Markov chain - Markov decision process - Mathematical optimization - Machine learning - Machine listening - Machine perception |
| Google Brain | Andrew Ng (26 June 2012). |
| Google Neural Machine Translation | based (EBMT) machine translation method in which the system |
| Gordon Hunter | Reinforcement Learning, Sports Analysis, Statistical Learning and Modelling. His current research interests include machine learning applications in |
| Grammar induction | in machine learning of learning a formal grammar (usually as a collection of re-write rules or productions or alternatively as a finite state machine or |
| Graph kernel | article is about machine learning. For the graph-theoretical notion, see Glossary of graph theory. In structure mining, a domain of learning on structured |
| GraphLab | using an Apache License. While GraphLab was originally developed for Machine Learning tasks, it has found great success at a broad range of other data-mining |
| Graphical model | probability theory, statistics-particularly Bayesian statistics-and machine learning. Generally, probabilistic graphical models use a graph-based |
| Godel machine | mathematical theories. The Godel machine is often discussed when dealing with issues of meta-learning, also known as |
| H2O | of Arno Candel; after H2O was rated as the best |
| HPCC Systems | |
| Hartmut Neven | work in face and object recognition and his contributions to quantum machine learning. He is currently Director of Engineering at Google where he is leading |
| Helmholtz machine | itself. Helmholtz machines are usually trained using an unsupervised learning algorithm, such as the wake-sleep algorithm. Helmholtz machines may also be used |
| Hierarchical temporal memory | temporal memory (HTM) is an unsupervised to semi-supervised online machine learning model developed by Jeff Hawkins and Dileep George of Numenta, Inc. |
| Higher Learning | For other uses, see Higher Learning (disambiguation). Higher Learning is a 1995 American drama film written and directed by John Singleton, and starring |
| Hinge loss | In machine learning, the hinge loss is a loss function used for training classifiers. The hinge loss is used for |
| Hug machine | |
| Hype Machine | Volodkin: Why Steep Learning Curves Are Worth It The 99 Percent. Bloggers' banquet: For new and old music believe the Hype Machine The Guardian. March |
| Hyperparameter optimization | hyperparameters in machine learning. For hyperparameters in Bayesian statistics, see Hyperparameter. In the context of machine learning, hyperparameter optimization |
| IEEE Transactions on Pattern Analysis and Machine Intelligence | image understanding, pattern analysis and recognition, and machine intelligence. machine learning, search techniques, document and handwriting analysis, medical |
| Ian Goodfellow | working in machine learning, currently employed as a research scientist at OpenAI. He has made several contributions to the field of deep learning. Goodfellow |
| Ilya Sutskever | Ilya Sutskever is a Computer Scientist working in Machine Learning and currently serving as the research director of OpenAI. Sutskever obtained his B.S |
| Incremental decision tree | An incremental decision tree algorithm is an online machine learning algorithm that outputs a decision tree. Many decision tree methods, such as C4.5, |
| Incremental learning | Incremental learning is a method of machine learning algorithms, which input data is been reading consecutively and is used to extend the existing model |
| Inductive bias | In machine learning, one aims to construct algorithms that are able to learn to predict a certain target output. To achieve this, the learning algorithm |
| Inductive programming | programs but on machine learning of symbolic hypotheses from logical representations. However, there were some encouraging results on learning recursive Prolog |
| Inductive transfer | Inductive transfer, or transfer learning, is a research problem in machine learning that focuses on storing knowledge gained while solving one problem |
| Inferential theory of learning | Inferential theory of learning (ITL) is an area of machine learning which describes inferential processes performed by learning agents. ITL has been developed |
| Instance-based learning | In machine learning, instance-based learning (sometimes called memory-based learning) is a family of learning algorithms that, instead of performing explicit |
| Instantaneously trained neural networks | Projection and for deep learning, International Conference on Machine Learning and Cybernetics, Dalin, 2006 Schmidhuber, J. Deep Learning in Neural Networks: |
| Intelligent control | approaches like neural networks, Bayesian probability, fuzzy logic, machine learning, evolutionary computation and genetic algorithms. Intelligent control |
| International Conference on Machine Learning | International Conference on Machine Learning (ICML) is the leading international academic conference in machine learning, attracting annually more than |
| International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics | Biostatistics (CIBB) is a preeminent yearly conference focused on machine learning and computational intelligence applied to bioinformatics and biostatistics |
| Jaime Carbonell | and related tasks. He also works on machine translation, both high-accuracy knowledge-based MT and machine learning for corpus-based MT (such as generalized |
| Jeremy Howard | and entrepreneur. He is the CEO and Founder at Enlitic, an advanced machine learning company in San Francisco, California. Previously, Howard was the President |
| John D. Lafferty | Block Professor at the University of Chicago and leading researcher in machine learning. He is best known for proposing the Conditional Random Fields with |
| John Langford | John Langford, see John Langford (disambiguation). John Langford is a machine learning research scientist, a field which he says |
| John Shawe-Taylor | Computational Statistics and Machine Learning at University College, London (UK). His main research area is statistical learning theory. He has written with |
| Journal of Machine Learning Research | The Journal of Machine Learning Research (usually abbreviated JMLR), is a scientific journal focusing on machine learning, a subfield of artificial intelligence |
| Jubatus | Jubatus is an open source online machine learning and distributed computing framework that is developed at Nippon Telegraph and Telephone and Preferred |
| K-means clustering | loose relationship to the k-nearest neighbor classifier, a popular machine learning technique for classification that is often confused with k-means because |
| K-nearest neighbors algorithm | until classification. The k-NN algorithm is among the simplest of all machine learning algorithms. Both for classification and regression, it can be useful |
| KNIME | and integration platform. KNIME integrates various components for machine learning and data mining through its modular data pipelining concept. A graphical |
| Kernel method | In machine learning, kernel methods are a class of algorithms for pattern analysis, whose best known member is the support vector machine (SVM). The general |
| Kernel methods for vector output | algorithms to easily swap functions of varying complexity. In typical machine learning algorithms, these functions produce a scalar output. Recent development |
| Kernel perceptron | In machine learning, the kernel perceptron is a variant of the popular perceptron learning algorithm that can learn kernel machines, i.e. non-linear classifiers |
| Kernel random forest | In machine learning, kernel random forests establish the connection between random forests and kernel methods. By slightly modifying their definition, |
| Klaus-Robert Müller | German physicist and computer scientist, most noted for his work in Machine Learning and Brain-Computer Interfaces. Klaus-Robert Müller received his Diplom |
| Knitting machine | time but does require learning to operate the machines correctly. Most if not all hand knitting patterns can be worked up on a machine, either identically |
| Knowledge Engineering and Machine Learning Group | The Knowledge Engineering and Machine Learning group (KEMLg) is a research group belonging to the Technical University of Catalonia (UPC) - BarcelonaTech |
| Knowledge integration | exploiting these learning opportunities the learning agent is able to learn beyond the explicit content of the new information. The machine learning program KI |
| Krzysztof Cios | University (VCU), located in Richmond, Virginia. His research is focused on machine learning, data mining, and biomedical informatics. Krzysztof J. Cios, a Polish-American |
| LIBSVM | LIBSVM and LIBLINEAR are two popular open source machine learning libraries, both developed at the National Taiwan University and both written in C++ though |
| LIONsolver | a software system is running. Learning and Intelligent OptimizatioN refers to the integration of online machine learning schemes into the optimization |
| Large margin nearest neighbor | nearest neighbor (LMNN) classification is a statistical machine learning algorithm for metric learning. It learns a pseudometric designed for k-nearest neighbor |
| Larry A. Wasserman | statistician and a professor in the Department of Statistics and the Machine Learning Department at Carnegie Mellon University. Wasserman received his |
| Lazy learning | In machine learning, lazy learning is a learning method in which generalization beyond the training data is delayed until a query is made to the system |
| Learnable evolution model | non-Darwinian methodology for evolutionary computation that employs machine learning to guide the generation of new individuals (candidate problem solutions) |
| Learnable function class | regularization in machine learning, and provides large sample justifications for certain learning algorithms. See also: Statistical learning theory Let |
| Learning | possessed by humans, animals, plants and some machines. Progress over time tends to follow a learning curve. Learning does not happen all at once, but it builds |
| Learning Tree International | Learning Tree International Inc. (OTCQX: LTRE), is an American multinational training company that has provided skills-enhancement training to over 2.4 |
| Learning analytics | Learning analytics is the measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and |
| Learning automata | of regular languages. Learning automata is one type of Machine Learning algorithm studied since 1970s. Compared to other learning scheme, a branch of the |
| Learning classifier system | Learning classifier systems, or LCS, are a paradigm of rule-based machine learning methods that combine a discovery component (e.g. typically a genetic |
| Learning curve | For other uses, see Learning curve (disambiguation). A learning curve is a graphical representation of the increase of learning (vertical axis) with experience |
| Learning object metadata | Learning Object Metadata is a data model, usually encoded in XML, used to describe a learning object and similar digital resources used to support learning |
| Learning rule | main models of machine learning: Unsupervised learning Supervised learning Reinforcement learning Machine learning Decision tree learning Pattern recognition |
| Learning theory | a mathematical theory to analyze machine learning algorithms. Online machine learning, the process of teaching a machine. Statistical learning theory |
| Learning to rank | Learning to rank or machine-learned ranking (MLR) is the application of machine learning, typically supervised, semi-supervised or reinforcement learning |
| Learning vector quantization | for the WEKA Machine Learning Workbench. GMLVQ toolbox: An easy-to-use implementation of Generalized Matrix LVQ (matrix relevance learning) in (c) matlab |
| Learning with errors | Learning with errors (LWE) is a problem in machine learning that is conjectured to be hard to solve. Introduced by Oded Regev in 2005, it is a generalization |
| Leo Breiman | between statistics and computer science, particularly in the field of machine learning. His most important contributions were his work on classification and |
| Leslie Valiant | |
| Linear separability | hyperplane if they are arises in several areas. In statistics and machine learning, classifying certain types of data is a problem for which good algorithms |
| Lise Getoor | University of Maryland, College Park. Her primary research interests are in machine learning and reasoning with uncertainty, applied to graphs and structured data |
| List of artificial intelligence projects | processing, speech recognition, machine vision, probabilistic logic, planning, reasoning, many forms of machine learning) into an AI assistant that learns |
| List of datasets for machine learning research | of the field of machine learning. Major advances in this field can result from advances in learning algorithms (such as deep learning), computer hardware |
| List of machine learning concepts | correct learning (PAC) learning Ripple down rules, a knowledge acquisition methodology Symbolic machine learning algorithms Support vector machines Random |
| List of programming languages for artificial intelligence | Smalltalk has been used extensively for simulations, neural networks, machine learning and genetic algorithms. It implements the purest and most elegant form |
| List of statistical packages | Torch (machine learning) - a deep learning software library written in Lua (programming language) Weka (machine learning) - a suite of machine learning software |
| Logic learning machine | Logic Learning Machine (LLM) is a machine learning method based on the generation of intelligible rules. LLM is an efficient implementation of the Switching |
| Logistic model tree | Landwehr, N.; Hall, M.; Frank, E. (2005). |
| LogitBoost | In machine learning and computational learning theory, LogitBoost is a boosting algorithm formulated by Jerome Friedman, Trevor Hastie, and Robert Tibshirani |
| Louis-Philippe Morency | a French Canadian researcher interested in human communication and machine learning applied to a better understanding of human behavior. Dr. Louis-Philippe |
| Lyle Ungar | Lyle H. Ungar is a machine learning researcher and professor of Computer and Information Science at the University of Pennsylvania, and is also affiliated |
| Leon Bottou | known for his work in machine learning and data compression. His work presents stochastic gradient descent as a fundamental learning algorithm. He is also |
| M-Theory | article is about machine learning. For the physics term, see M-theory. In Machine Learning and Computer Vision, M-Theory is a learning framework inspired |
| MILEPOST GCC | stable production-quality GCC, Interactive Compilation Interface and machine learning plugins to adapt to any given architecture and program automatically |
| MLPACK | mlpack is a machine learning software library for C++, built on top of the Armadillo library. mlpack has an emphasis on scalability, speed, and ease-of-use |
| MNIST database | database is also widely used for training and testing in the field of machine learning. It was created by |
| Machine | perform tasks. For other uses, see Machine (disambiguation). Further information: Equipment (disambiguation) A machine is a tool containing one or more |
| Machine Learning | Machine Learning is a peer-reviewed scientific journal, published since 1986. In 2001, forty editors and members of the editorial board of Machine Learning |
| Machine learning | For the journal, see Machine Learning (journal). Machine learning is the subfield of computer science that gives computers the ability to learn without |
| Machine listening | analysis, filtering, and audio transforms); artificial intelligence (machine learning and sound classification); psychoacoustics (sound perception); cognitive |
| Machine translation | when translating. Main article: Neural machine translation A deep learning based approach to MT, neural machine translation has made rapid progress in |
| Machine-dependent software | and Xie, M., 2015, An empirical analysis of data preprocessing for machine learning-based software cost estimation, Information and Software Technology |
| Mallet | MALLET is a Java |
| Manifold alignment | Manifold alignment is a class of machine learning algorithms that produce projections between sets of data, given that the original data sets lie on a |
| Manifold regularization | In machine learning, Manifold regularization is a technique for using the shape of a dataset to constrain the functions that should be learned on that |
| Mann & Machine | Mann and Machine is an American science fiction/police drama series that aired for nine episodes on NBC from April 5 to July 14, 1992. Created by Dick |
| Margin | In machine learning the margin of a single data point is defined to be the distance from the data point to a decision boundary. Note that there are many |
| Margin classifier | In machine learning, a margin classifier is a classifier which is able to give an associated distance from the decision boundary for each example. For |
| Massive Online Analysis | open-source framework software that allows to build and run experiments of machine learning or data mining on evolving data streams. It includes a set of learners |
| Matrix regularization | feature learning. Machine Learning, 73(3):243-272, 2008. Huang, Zhang, and Metaxas. Learning with Structured Sparsity. Journal of Machine Learning Research |
| MatrixNet | MatrixNet is a proprietary machine learning algorithm developed by Yandex and used widely throughout the company products. The algorithm is based on gradient |
| MeeMix | |
| Mehryar Mohri | Mathematical Sciences at New York University known for his work in machine learning, automata theory and algorithms, speech recognition and natural language |
| Metafor Software | Using machine learning techniques inspired by how the human brain works, Metafor detects unexpected changes and behavioral anomalies in Machine-generated |
| Michael Collins | processing as well as machine learning and he has made important contributions in statistical parsing and in statistical machine learning. In his studies Collins |
| Michael I. Jordan | at the University of California, Berkeley and leading researcher in machine learning and artificial intelligence. Jordan received his BS magna cum laude |
| Michael Kearns | leading researcher in computational learning theory and algorithmic game theory, and interested in machine learning, artificial intelligence, computational |
| Michael L. Littman | computer scientist. He works mainly in reinforcement learning, but has done work in machine learning, game theory, computer networking, partially observable |
| Microsoft Azure | State Configuration.[1] Microsoft SMA (software) Microsoft Azure Machine Learning (Azure ML) service is part of Cortana Intelligence Suite that enables |
| Microsoft Research | Hardware and Devices Health and Well-being Human-computer interaction Machine learning and Artificial intelligence Mobile computing Quantum computing Search |
| Mike Phillips | writer Mike Phillips (speech recognition) (born 1961), pioneer in machine learning and speech recognition Michael Brandon (pornographic actor) (born 1965) |
| Mind machine | A mind machine (aka brain machine or light and sound machine) uses pulsing rhythmic sound, flashing light, electrical or magnetic fields, or a combination |
| Mlpy | mlpy is a Python, open source, machine learning library built on top of NumPy/SciPy, the GNU Scientific Library and it makes an extensive use of the Cython |
| Multi-armed bandit | expected payoffs of the other machines. The trade-off between exploration and exploitation is also faced in reinforcement learning. The multi-armed bandit |
| Multi-task learning | Multi-task learning (MTL) is a subfield of machine learning in which multiple learning tasks are solved at the same time, while exploiting commonalities |
| Multiclass classification | Not to be confused with multi-label classification. In machine learning, multiclass or multinomial classification is the problem of classifying instances |
| Multilayer perceptron | popular machine learning solution in the 1980s, finding applications in diverse fields such as speech recognition, image recognition, and machine translation |
| Multilinear subspace learning | subspace learning for tensor data (open access version). Lecture: Video lecture on UMPCA at the 25th International Conference on Machine Learning (ICML 2008) |
| Multiple instance learning | data, machine learning can be roughly categorized into three frameworks: supervised learning, unsupervised learning, and reinforcement learning. Multiple |
| Multiple kernel learning | Multiple kernel learning refers to a set of machine learning methods that use a predefined set of kernels and learn an optimal linear or non-linear combination |
| Multiple-instance learning | In machine learning, multiple-instance learning (MIL) is a variation on supervised learning. Instead of receiving a set of instances which are individually |
| Music information retrieval | in musicology, psychology, academic music study, signal processing, machine learning or some combination of these. MIR is being used by businesses and |
| Nando de Freitas | field of machine learning, and in particular in the subfields of neural networks, Bayesian inference and Bayesian optimization, and deep learning. De Freitas |
| Natural language processing | NLP algorithms are based on machine learning, especially statistical machine learning. The paradigm of machine learning is different from that of most |
| Nello Cristianini | analysis; machine learning and artificial intelligence; machine translation; bioinformatics. As a practitioner of data-driven AI and Machine Learning, Cristianini |
| Nest Learning Thermostat | cooling of homes and businesses to conserve energy. It is based on a machine learning algorithm: For the first weeks users have to regulate the thermostat |
| Neural Designer | Neural Designer is a software tool for data mining based on machine learning techniques, a main area of artificial intelligence research. It has been developed |
| Neural machine translation | Neural machine translation (NMT) is an approach to machine translation in which a large neural network is trained by deep learning techniques. It is a |
| Never-Ending Language Learning | Never-Ending Language Learning system (NELL) is a semantic machine learning system developed by a research team at Carnegie Mellon University, and supported |
| Nir Friedman | Hebrew University of Jerusalem. His research combines Machine Learning and Statistical Learning with Systems Biology, specifically in the fields of Gene |
| Novelty detection | that a machine learning system has not been trained with and was not previously aware of, with the help of either statistical or machine learning based |
| Numenta | NuPIC is to build and support a community, that is interested in machine learning and machine intelligence based on modeling the neocortex and its principles |
| Observational learning | learning (disambiguation). Observational learning is learning that occurs through observing the behavior of others. It is a form of social learning which |
| Occam learning | In computational learning theory, Occam learning is a model of algorithmic learning where the objective of the learner is to output a succinct representation |
| Ofer Dekel | see Ofer Dekel. Ofer Dekel is a computer science researcher in the Machine Learning Department of Microsoft Research. He obtained his PhD in Computer Science |
| Offline learning | In machine learning, systems which employ offline learning do not change their approximation of the target function when the initial training phase has |
| Omniscien Technologies | statistical and / or neuronal techniques from cryptography, applying machine learning algorithms that automatically acquire statistical models from existing |
| One-class classification | In machine learning, one-class classification, also known as unary classification, tries to identify objects of a specific class amongst all objects, by |
| Online | (ONLine), proposed electrical power line in Nevada Online (machine learning) a method of machine learning in which data becomes available in a sequential order |
| Online learning | Online learning may refer to E-learning, in education E-learning (theory) Online machine learning, in computer science and statistics Online learning in |
| Online machine learning | In computer science, online machine learning is a method of machine learning in which data becomes available in a sequential order and is used to update |
| OpenNN | Designer, also developed by Artelnics Artificial intelligence Machine learning Deep learning Artificial neural network |
| Orange | other uses, see Orange (disambiguation). Orange is a free software machine learning and data mining package (written in Python). It has a visual programming |
| Ordinal regression | as well as in information retrieval. In machine learning, ordinal regression may also be called ranking learning. Ordinal regression can be performed |
| Osmar R. Zaiane | professor at the University of Alberta specializing in data mining and machine learning. He was the secretary treasurer of the Association for Computing Machinery |
| Out-of-bag error | prediction error of random forests, boosted decision trees, and other machine learning models utilizing bootstrap aggregating to sub-sample data sampled used |
| Outline of machines | topical guide to machines: Machine - mechanical system that provides the useful application of power to achieve movement. A machine consists of a power |
| Overfitting | In statistics and machine learning, one of the most common tasks is to fit a |
| Oxford-Man Institute | applications of machine learning and data analytics. The current Director of the Oxford-Man Institute is Stephen Roberts, a Professor of Machine Learning in Information |
| Pachinko allocation | In machine learning and natural language processing, the pachinko allocation model (PAM) is a topic model. Topic models are a suite of algorithms to uncover |
| Padhraic Smyth | Science Initiative, and Associate Director for UC Irvine's Center for Machine Learning and Intelligent Systems. |
| Parity learning | Parity learning is a problem in machine learning. An algorithm that solves this problem must guess the function ƒ, given some samples (x, ƒ(x)) and the |
| Pattern recognition | This article is about pattern recognition as a branch of machine learning. For the cognitive process, see Pattern recognition (psychology). For other uses |
| Pedro Domingos | Domingos is Professor at University of Washington. He is a researcher in machine learning and known for markov logic network enabling uncertain inference. |
| Perceptron | 1969 book, see Perceptrons (book). In machine learning, the perceptron is an algorithm for supervised learning of binary classifiers (functions that can |
| Perceptual learning | Perceptual learning is the process of learning improved skills of perception. These improvements range from simple sensory discriminations (e.g., distinguishing |
| Personalized learning | Personalized learning, individualized instruction, personal learning environment and direct instruction all refer to efforts to tailor education to meet |
| Peter Dayan | Computational Neuroscience). He is known for applying Bayesian methods from Machine Learning and Artificial Intelligence to understand neural function, and is particularly |
| Peter Richtarik | Slovak mathematician working in the area of big data optimization and machine learning, known for his work on randomized coordinate descent algorithms. He |
| Pierre Baldi | Pierre Baldi's research include artificial intelligence, statistical machine learning, and data mining, and their applications to problems in the life sciences |
| Platt scaling | In machine learning, Platt scaling or Platt calibration is a way of transforming the outputs of a classification model into a probability distribution |
| Ply | used the term in its game-theoretic sense in his seminal paper on machine learning in checkers in 1959. In computing, the concept of ply is important |
| Polynomial kernel | This article is about machine learning. For polynomial kernels in complexity theory, see Kernelization. In machine learning, the polynomial kernel |
| Population-based incremental learning | In computer science and machine learning, population-based incremental learning (PBIL) is an optimization algorithm, and an estimation of distribution |
| Predictive learning | Predictive learning is a technique of machine learning in which an agent tries to build a model of its environment by trying out different actions in |
| Preference learning | Preference learning is a subfield in machine learning in which the goal is to learn a predictive preference model from observed preference information |
| Prior knowledge for pattern recognition | recognition is a very active field of research intimately bound to machine learning. Also known as classification or statistical classification, pattern |
| Prismatic | for various Web browsers and mobile devices running iOS. It combined machine learning, user experience design, and interaction design to create a new way |
| Proactive Discovery of Insider Threats Using Graph Analysis and Learning | is for two years and the budget $9 million. It uses graph theory, machine learning, statistical anomaly detection, and high-performance computing to scan |
| Proactive learning | learning is a generalization of active learning designed to relax unrealistic assumptions and thereby reach practical applications. |
| Probabilistic classification | In machine learning, a probabilistic classifier is a classifier that is able to predict, given a sample input, a probability distribution over a set of |
| Probably approximately correct learning | computational learning theory, probably approximately correct learning (PAC learning) is a framework for mathematical analysis of machine learning. It was proposed |
| Product of experts | Product of experts (PoE) is a machine learning technique. It models a probability distribution by combining the output from several simpler distributions |
| Programmed learning | of applied psychologists and educators. The learning material is in a kind of textbook or teaching machine or computer. The medium presents the material |
| Pruning | Pruning is a technique in machine learning that reduces the size of decision trees by removing sections of the tree that provide little power to classify |
| Q-learning | Q-learning is a model-free reinforcement learning technique. Specifically, Q-learning can be used to find an optimal action-selection policy for any given |
| Quadratic classifier | This article is about machine learning and statistical classification. For other uses of the word |
| Quantum machine learning | Quantum machine learning is a newly emerging interdisciplinary research area between quantum physics and computer science that summarises efforts to combine |
| Rademacher complexity | In computational learning theory (machine learning and theory of computation), Rademacher complexity, named after Hans Rademacher, measures richness of |
| Radford M. Neal | University of Toronto, where he holds a Research Chair in statistics and machine learning. He studied computer science at the University of Calgary (B.Sc. 1977 |
| Radial basis function kernel | In machine learning, the (Gaussian) radial basis function kernel, or RBF kernel, is a popular kernel function used in various kernelized learning algorithms |
| Rage Against the Machine | Not to be confused with Race Against the Machine. Rage Against the Machine (also known as RATM or simply Rage) is an American rock band from Los Angeles |
| Random forest | This article is about the machine learning technique. For other kinds of random tree, see Random tree (disambiguation). Random forests or random decision |
| Random subspace method | In machine learning. the random subspace method, also called attribute bagging or feature bagging, is an ensemble learning method that attempts to reduce |
| Randomized weighted majority algorithm | The randomized weighted majority algorithm is an algorithm in machine learning theory. It improves the mistake bound of the weighted majority algorithm |
| Rayid Ghani | his graduate studies in the Machine Learning Department at Carnegie Mellon University with Tom M. Mitchell on Machine Learning and Text Classification and |
| Recurrent neural network | (2002). Learning precise timing with LSTM recurrent networks. Journal of Machine Learning Research 3:115-143. Jürgen Schmidhuber (2015). Deep learning in |
| Regularization | Regularization, in mathematics and statistics and particularly in the fields of machine learning and inverse problems, refers to a process of introducing additional |
| Regularization perspectives on support vector machines | perspectives on support vector machines provide a way of interpreting support vector machines (SVMs) in the context of other machine learning algorithms. SVM algorithms |
| Reinforcement learning | reinforcement learning in psychology, see Reinforcement and Operant conditioning. Reinforcement learning is an area of machine learning inspired by behaviorist |
| Relevance vector machine | In mathematics, a Relevance Vector Machine (RVM) is a machine learning technique that uses Bayesian inference to obtain parsimonious solutions for regression |
| Restricted Boltzmann machine | Boltzmann machines, in particular the gradient-based contrastive divergence algorithm. Restricted Boltzmann machines can also be used in deep learning networks |
| Reza Zadeh | Reza Zadeh is a Canadian Computer Scientist working on Machine Learning. He is faculty at Stanford University and serves on the technical advisory board |
| Richard S. Sutton | Press, 1991. Sutton, R. S. (Ed.), Reinforcement Learning. Reprinting of a special issue of Machine Learning Journal. Kluwer Academic Press, 1992 Sutton |
| Richard Zemel | Department of Computer Science, and a leading figure in the field of Machine Learning and Computer Vision. Zemel obtained his Ph.D under Geoffrey Hinton |
| Robert Schapire | theoretical and applied machine learning. His work led to the development of the boosting ensemble algorithm used in machine learning. Together with Yoav |
| Roberto Battiti | Search Optimization, which aims at embodying solvers with internal machine learning techniques, data mining and visualization. Battiti was elected Fellow |
| Robot learning | Robot learning is a research field at the intersection of machine learning and robotics. It studies techniques allowing a robot to acquire novel skills |
| Robustness | many areas of computer science, such as robust programming, robust machine learning, and Robust Security Network. Formal techniques, such as fuzz testing |
| Ross D. King | Manchester working at the Manchester Institute of Biotechnology and Machine Learning and Optimisation (MLO) group. King completed a Bachelor of Science |
| Ross Quinlan | specialist in artificial intelligence, particularly in the aspect involving machine learning and its application to data mining. Ross Quinlan invented the Iterative |
| Rote learning | rote learning, at least for the more able students.[citation needed] Rote learning is also used to describe a simple learning pattern used in machine learning |
| Rule induction | Rule induction is an area of machine learning in which formal rules are extracted from a set of observations. The rules extracted may represent a full |
| Rule-based machine learning | Rule-based machine learning (RBML) is a term in computer science intended to encompass any machine learning method that identifies, learns, or evolves |
| Russell Greiner | in Machine Learning and Bioinformatics. Professor Greiner is one of the principal investigators at the Alberta Innovates Centre for Machine Learning (AICML) |
| Ryszard S. Michalski | Professor at George Mason University and a pioneer in the field of machine learning. Michalski was born in Kalusz near Lvov on 7 May 1937. He received |
| SVM | modulating technique to give power to a load Support vector machine, in machine learning SVM (company) Saskatchewan Volunteer Medal Schuylkill Valley |
| Sample complexity | The sample complexity of a machine learning algorithm represents the number of training-samples that it needs in order to successfully learn a target function |
| Scikit-learn | Scikit-learn (formerly scikits.learn) is a free software machine learning library for the Python programming language. It features various classification |
| Search space | input data in geometric search problems Version space, developed via machine learning, it is the subset of all hypotheses that are consistent with the observed |
| Self-learning | Self-learning can refer to: Learning Theory Autodidacticism unsupervised machine learning |
| Semantic analysis | In machine learning, semantic analysis of a corpus is the task of building structures that approximate concepts from a large set of documents. It generally |
| Semi-supervised learning | semi-supervised learning can be of great practical value. Semi-supervised learning is also of theoretical interest in machine learning and as a model for |
| Sepp Hochreiter | Mühldorf) is a German computer scientist working in the fields of machine learning and bioinformatics. Since 2006 he has been head of the Institute of |
| Sequence labeling | In machine learning, sequence labeling is a type of pattern recognition task that involves the algorithmic assignment of a categorical label to each member |
| Shane Legg | Shane Legg is a machine learning researcher and founder of DeepMind Technologies, acquired by Google in 2014. Legg attended Rotorua Lakes High School |
| Shattered set | the study of empirical processes as well as in statistical computational learning theory. Suppose A is a set and C is a class of sets. The class C shatters |
| Shogun | written in C++. It offers numerous algorithms and data structures for machine learning problems. Shogun is licensed under the terms of the GNU General Public |
| Similarity learning | Similarity learning is an area of supervised machine learning in artificial intelligence. It is closely related to regression and classification, but the |
| Simple machine | software, see Simple Machines Forum. For a broader coverage related to this topic, see Mechanism (engineering). A simple machine is a mechanical device |
| Skymind | software packages focused on machine learning that can be installed and used together. SKIL is an operating system for deep learning, integrating with Hadoop |
| Skytree | restaurant, and observation tower in Sumida, Tokyo, Japan Skytree, Inc, a machine learning start up based in San Jose, California, USA Skytree DAC, a company |
| Skytree, Inc | develops machine learning software for enterprise use. Skytree came out of stealth mode in February 2012. announcing Skytree Server, a machine learning system |
| Solomonoff's theory of inductive inference | 1023-1029. Burgin, M.; Klinger, A. Experience, Generations, and Limits in Machine Learning, Theoretical Computer Science, v. 317, No. 1/3, 2004, pp. 71-91 Davis |
| SpaCy | spaCy also supports deep learning workflows that allow connecting statistical models trained by popular machine learning libraries like TensorFlow, |
| Sparse dictionary learning | Sparse dictionary learning is a representation learning method which aims at finding a sparse representation of the input data (also known as sparse coding) |
| Stability | in computational learning theory of how a machine learning algorithm is perturbed by small changes to its inputs. A stable learning algorithm is one for |
| State-Action-Reward-State-Action | (SARSA) is an algorithm for learning a Markov decision process policy, used in the reinforcement learning area of machine learning. It was introduced in a |
| Statistical classification | For the unsupervised learning approach, see Cluster analysis. In machine learning and statistics, classification is the problem of identifying to which |
| Statistical learning theory | Computational learning theory This article is about statistical learning in machine learning. For its use in psychology, see Statistical learning in language |
| Statistical relational learning | Statistical relational learning (SRL) is a subdiscipline of artificial intelligence and machine learning that is concerned with domain models that exhibit |
| Stephen Muggleton | FREng (born 6 December 1959, son of Louis Muggleton) is Professor of Machine Learning and Head of the Computational Bioinformatics Laboratory at Imperial |
| Steve Omohundro | Hamiltonian physics, dynamical systems, programming languages, machine learning, machine vision, and the social implications of artificial intelligence |
| Stochastic gradient descent | M-estimation See also: Estimating equation Both statistical estimation and machine learning consider the problem of minimizing an objective function that has the |
| String kernel | In machine learning and data mining, a string kernel is a kernel function that operates on strings, i.e. finite sequences of symbols that need not be of |
| Structural risk minimization | minimization (SRM) is an inductive principle of use in machine learning. Commonly in machine learning, a generalized model must be selected from a finite |
| Structured prediction | Structured prediction or structured (output) learning is an umbrella term for supervised machine learning techniques that involves predicting structured |
| Structured support vector machine | The structured support vector machine is a machine learning algorithm that generalizes the Support Vector Machine (SVM) classifier. Whereas the SVM classifier |
| Supervised learning | See also: Unsupervised learning Supervised learning is the machine learning task of inferring a function from labeled training data. The training data |
| Support vector machine | Virtual Machine. In machine learning, support vector machines (SVMs, also support vector networks) are supervised learning models with associated learning algorithms |
| Tanagra | Tanagra is a free suite of machine learning software for research and academic purposes developed by Ricco Rakotomalala at the Lumière University Lyon |
| Teaching machine | type of machine which used his ideas on how learning should be directed with positive reinforcement. Skinner advocated the use of teaching machines for a |
| Technology as a Service | Artificial Intelligence (AI) () and Machine Learning to deliver IT services utilizing Digital Labor . Cognitive learning () and policy based governance intelligence |
| Temporal difference learning | Temporal difference (TD) learning is a prediction-based machine learning method. It has primarily been used for the reinforcement learning problem, and is said |
| Tensor processing unit | application-specific integrated circuits developed specifically for machine learning. Compared to graphics processing units (which as of 2016 are frequently |
| Test set | relationship. Test and training sets are used in intelligent systems, machine learning, genetic programming and statistics. Regression analysis was one |
| The Doomsday Machine | disrupting communications with Starfleet and Constellation. On learning of the approach of the machine, Decker pulls rank on First Officer Spock, assumes command |
| The Master Algorithm | The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World is a book by Pedro Domingos released in 2015. Domingos wrote |
| The Time Machine | The Time Machine is a 2002 American science fiction film loosely adapted from the 1895 novel of the same name by H. G. Wells and the 1960 film screenplay |
| Theano | project primarily developed by a machine learning group at the Universite de Montreal. Comparison of deep learning software Bergstra, J.; O. Breuleux; |
| Theoretical computer science | complexity theory, distributed computation, parallel computation, VLSI, machine learning, computational biology, computational geometry, information theory |
| Thomas G. Dietterich | field of machine learning. He served as Executive Editor of Machine Learning (journal) (1992-98) and helped co-found the Journal of Machine Learning Research |
| Timeline of machine learning | intelligence Machine learning Timeline of artificial intelligence Timeline of machine translation Marr, Marr. |
| Timeline of machine translation | timeline of machine translation. For a more detailed qualitative account, see the history of machine translation page. Timeline of machine learning Hutchins |
| Tom M. Mitchell | the Chair of the Machine Learning Department at CMU. Mitchell is known for his contributions to the advancement of machine learning, artificial intelligence |
| Torch | Torch is an open source machine learning library, a scientific computing framework, and a script language based on the Lua programming language. It provides |
| Toyota Technological Institute at Chicago | primarily on theoretical computer science (algorithms and complexity), machine learning (and related AI applications), programming languages (and related areas |
| Transduction | semi-supervised learning, since Vapnik's motivation is quite different. An example of an algorithm in this category is the Transductive Support Vector Machine (TSVM) |
| Trevor Hastie | especially in the field of machine learning, data mining, and bioinformatics. He has authored several popular books in statistical learning, including The Elements |
| Ulisses Braga Neto | University. His main research areas are statistical pattern recognition, machine learning, signal and image processing, and systems biology. He has worked extensively |
| United Learning | income Archived March 2, 2009, at the Wayback Machine. United Learning. |
| Universal portfolio algorithm | portfolio algorithm is a portfolio selection algorithm from the field of machine learning and information theory. The algorithm learns adaptively from historical |
| Unsupervised learning | Unsupervised machine learning is the machine learning task of inferring a function to describe hidden structure from unlabeled data. Since the examples |
| Vanishing gradient problem | In machine learning, the vanishing gradient problem is a difficulty found in training artificial neural networks with gradient-based learning methods and |
| Vasant Honavar | Indian born American computer scientist, and Artificial Intelligence, Machine Learning, Bioinformatics and Health Informatics researcher and educator. In |
| Vending machine | Wikibooks Learning resources from Wikiversity In Praise of Vending Machines - slideshow by Life magazine World's Strangest Vending Machines:, From Florida |
| Version space learning | Version space learning is a logical approach to machine learning, specifically binary classification. Version space learning algorithms search a predefined |
| Virtual scientific community | Examples of such communities include the Computational Intelligence and Machine Learning Portal or the Biomedical Informatics Research Network. There are numerous |
| Vladimir Vapnik | the Vapnik-Chervonenkis theory of statistical learning, and the co-inventor of the support vector machine method. Vladimir Vapnik was born in the Soviet |
| Vowpal Wabbit | efficient scalable implementation of online machine learning and support for a number of machine learning reductions, importance weighting, and a selection |
| Waffle | bulletin board service software program Waffles (machine learning), an open source collection of machine learning algorithms and tools Waffles (John Kerry), |
| Waffles | Waffles is a collection of command-line tools for performing machine learning operations developed at Brigham Young University. These tools are written |
| Wake-sleep algorithm | variational Bayesian learning. After that, the algorithm was adapted to machine learning. It can be viewed as a way to train a Helmholtz Machine The wake-sleep |
| Walter Daelemans | Center (CLiPS). Daelemans pioneered the use of machine learning techniques, especially memory-based learning, in natural language processing in Europe in |
| War Machine | article is about the superhero. For other uses, see War Machine (disambiguation). War Machine (James |
| Weka | Waikato Environment for Knowledge Analysis (Weka) is a popular suite of machine learning software written in Java, developed at the University of Waikato, New |
| Winnow | The winnow algorithm is a technique from machine learning for learning a linear classifier from labeled examples. It is very similar to the perceptron |
| Word embedding | (2007). |
| Work output | engine's efficiency. NewPath Learning (1 March 2014). Work, Power and Simple Machines Science Learning Guide. NewPath Learning. pp.8. ISBN 978-1-63212-074-8 |
| Xgboost | of machine learning competitions. XGBoost initially started as a research project by Tianqi Chen as part of the Distributed (Deep) Machine Learning Community |
| Yann LeCun | Yann LeCun (born 1960) is a computer scientist with contributions in machine learning, computer vision, mobile robotics and computational neuroscience. He |
| Yaser Abu-Mostafa | and Chairman of Machine Learning Consultants LLC. He is known for his research and educational activities in the area of machine learning. Abu-Mostafa |
| Yasuo Matsuyama | Yasuo Matsuyama (born March 23, 1947) is a researcher in machine learning and human-aware information processing. He is a professor of Waseda University |
| Yoav Freund | science at the University of California, San Diego who mainly works on machine learning, probability theory and related fields and applications. He is best |
| Yoshua Bengio | the Learning in Machines and Brains project of the Canadian Institute for Advanced Research. Knight, Will (July 9, 2015). |
| Zeroth | API to interact with the platform. It makes a form of machine learning known as deep learning available to mobile devices. It is used for image and sound |
| Zhi-Hua Zhou | LAMDA Group. His research interests include artificial intelligence, machine learning and data mining. Zhi-Hua Zhou received his B.Sc., M.Sc. and Ph.D |
| Zoubin Ghahramani | Ghahramani has made significant contributions in the areas of Bayesian machine learning (particularly variational methods for approximate Bayesian inference) |