Machine learning
Statistical algorithms that learn from data without explicit programming.
Last updated
Machine learning is a field focused on developing computer systems that learn and adapt without following explicit instructions.[1] Its foundations lie in statistics and mathematical optimisation methods.[2]
Last updated 2026-10-07 from the source article.
Quick Facts
- Field
- Artificial intelligence
- statistics
- computer science
- Known for
- Statistical algorithms that learn from data
- deep learning
- empirical risk minimization
- Foundational concept
- Probably approximately correct learning
- Early program
- Checkers-playing program by Arthur Samuel (1950s)
Facts from the source article.
Key facts and history
Walter Pitts and Warren McCulloch proposed the first mathematical model of neural networks.[3][1] By the early 1960s, Raytheon Company had developed Cybertron, an experimental learning machine using punched tape memory and rudimentary reinforcement learning.[4] Tom M. Mitchell provided a widely quoted formal definition: a computer program learns from experience E with respect to tasks T and performance measure P if its performance improves with experience.[5] In 2012, AlexNet achieved substantially improved results in the ImageNet image recognition competition, contributing to wider adoption of deep neural networks.[6]
In 1959, Arthur Samuel, who worked at IBM and was a trailblazer in computer gaming and AI, first used the term "machine learning".[7] The 1949 book "The Organization of Behavior" by Canadian psychologist Donald Hebb put forward a theoretical neural structure arising from specific interactions between nerve cells.[3] Using deep neural networks and reinforcement learning, AlphaGo was the first computer program, in 2016, to beat a professional human Go player on a full-sized board with no handicaps.[6] During the 1990s, machine learning was restructured and acknowledged as a distinct field, moving its emphasis from symbolic approaches to techniques derived from statistics and probability theory.[8]
What the cited sources add
The WhatIs timeline notes that machine learning impacts daily operations in industries including e-commerce, manufacturing, finance, insurance services and pharmaceuticals.[1] Arthur Bryson and Yu-Chi Ho described a backpropagation learning algorithm enabling multilayer ANNs, a foundation for deep learning.[1] Christopher Watkins developed Q-learning, a model-free reinforcement algorithm that sought the best action in any current state.[1] Torch, the first open source machine learning library, was released, providing interfaces to deep learning algorithms implemented in C.[1]
Geoffrey Hinton coined the term deep learning to describe algorithms that help computers recognise objects and text characters in pictures and videos.[1] Anthony Goldbloom and Ben Hamner launched Kaggle as a platform for machine learning competitions.[1] A class of machine learning frameworks for generating photos and transforming images, known as generative adversarial networks, was invented by Ian Goodfellow and his team.[1]
References
- "History and Evolution of Machine Learning: A Timeline", WhatIs. facts only, no text reused. techtarget.com
- Wikipedia, "Machine learning" (CC BY-SA 4.0), which cites: Friedman, "Data Mining and Statistics: What's the connection?", Computing Science and Statistics, 1998, p. 3–9 (original not read by us) en.wikipedia.org
- Wikipedia, "Machine learning" (CC BY-SA 4.0), which cites: "History and Evolution of Machine Learning: A Timeline", WhatIs; Milner, "The Mind and Donald O. Hebb", Scientific American, 1993, p. 124–129; "History and Evolution of Machine Learning: A Timeline", WhatIs; "History and Evolution of Machine Learning: A Timeline", WhatIs (we also read that source) en.wikipedia.org
- Wikipedia, "Machine learning" (CC BY-SA 4.0), which cites: "Science: The Goof Button", Time, 18 August 1961.; Nilsson, "Learning Machines", McGraw-Hill, 1965; Duda, "Pattern Recognition and Scene Analysis", Wiley Interscience, 1973; S. Bozinovski, "Teaching space: A representation concept for adaptive pattern classification" COINS Technical Report No. 81-28, Computer and Information Science (original not read by us) en.wikipedia.org
- Wikipedia, "Machine learning" (CC BY-SA 4.0), which cites: Mitchell, T., "Machine Learning", McGraw Hill, 1997, p. 2 (we also read that source) en.wikipedia.org
- Wikipedia, "Machine learning" (CC BY-SA 4.0), which cites: LeCun, "Deep learning", Nature, 2015, p. 436–444; Mikolov, "Efficient Estimation of Word Representations in Vector Space", 2013; Mikolov, "Distributed Representations of Words and Phrases and their Compositionality", 2013; Goodfellow, "Generative Adversarial Nets", 2014, p. 2672–2680; Silver, "Mastering the game of Go with deep neural networks and tree search", Nature, 2016, p. 484–489; Vaswani, "Attention Is All You Need", 2017, p. 5998–6008 (original not read by us) en.wikipedia.org
- Wikipedia, "Machine learning" (CC BY-SA 4.0), which cites: Samuel, "Some Studies in Machine Learning Using the Game of Checkers", IBM Journal of Research and Development, 1959, p. 210–229; R. Kohavi and F. Provost, "Glossary of terms", Machine Learning, vol. 30, no. 2–3, pp. 271–274, 1998.; Gerovitch, "How the Computer Got Its Revenge on the Soviet Union", Nautilus, 9 April 2015; Lindsay, "The Impact of Automation On Public Administration", Western Political Quarterly, September 1964, p. 78–81 (original not read by us) en.wikipedia.org
- Wikipedia, "Machine learning" (CC BY-SA 4.0), which cites: Langley, "The changing science of machine learning", Machine Learning, 2011, p. 275–9 (we also read that source) en.wikipedia.org
Each numbered sentence above was checked against the source it cites before publication. Sentences citing Wikipedia adapt text from the English Wikipedia article Machine learning (contributors), used under CC BY-SA 4.0; this entry is available under the same licence. Other sources were used for facts only; no text or images are copied from them.
More in Science & Measurement
Sources
Compiled from Wikipedia and the sources listed below. Text from Wikipedia is available under CC BY-SA 4.0; this entry is adapted from it.
- Wikipedia: Machine learning (CC BY-SA 4.0).
Spotted an error? Know more?
Reader corrections go straight into our review queue. Suggest an edit · How this site is sourced