imported>Citation bot: Add: bibcode, pmid, issue, authors 1-1. Removed URL that duplicated identifier. Removed parameters. Some additions/deletions were parameter name changes. | Use this bot. Report bugs. | Suggested by Abductive | #UCB_toolbar

2025-12-23T15:11:31Z

Add: bibcode, pmid, issue, authors 1-1. Removed URL that duplicated identifier. Removed parameters. Some additions/deletions were parameter name changes. | Use this bot. Report bugs. | Suggested by Abductive | #UCB_toolbar

Show changes

imported>Zefr: Reverted 1 edit by Iamchriswalter (talk): Better written before

2025-06-25T01:31:15Z

Reverted 1 edit by Iamchriswalter (talk): Better written before

← Previous revision		Revision as of 01:31, 25 June 2025
Line 39:		Line 39:

	=== Artificial intelligence ===		=== Artificial intelligence ===
	[[File:AI hierarchy.svg\|thumb\|~~Machine~~ learning ~~as subfield~~ of AI<ref name="journalimcms.org">{{cite journal \|vauthors=Sindhu V, Nivedha S, Prakash M \|date=February 2020\|title=An Empirical Science Research on Bioinformatics in Machine Learning \|journal=Journal of Mechanics of Continua and Mathematical Sciences \|issue=7 \|doi=10.26782/jmcms.spl.7/2020.02.00006 \|doi-access=free}}</ref>]]		[[File:AI hierarchy.svg\|thumb\|[[Deep learning]] is a subset of machine learning, which is itself a subset of [[artificial intelligence]].<ref name="journalimcms.org">{{cite journal \|vauthors=Sindhu V, Nivedha S, Prakash M \|date=February 2020\|title=An Empirical Science Research on Bioinformatics in Machine Learning \|journal=Journal of Mechanics of Continua and Mathematical Sciences \|issue=7 \|doi=10.26782/jmcms.spl.7/2020.02.00006 \|doi-access=free}}</ref>]]
	As a scientific endeavour, machine learning grew out of the quest for [[artificial intelligence]] (AI). In the early days of AI as an [[Discipline (academia)\|academic discipline]], some researchers were interested in having machines learn from data. They attempted to approach the problem with various symbolic methods, as well as what were then termed "[[Artificial neural network\|neural network]]s"; these were mostly [[perceptron]]s and [[ADALINE\|other models]] that were later found to be reinventions of the [[generalised linear model]]s of statistics.<ref>{{cite book \|last1=Sarle \|first1=Warren S.\|chapter=Neural Networks and statistical models \|pages=1538–50 \|year=1994 \|title=SUGI 19: proceedings of the Nineteenth Annual SAS Users Group International Conference \|publisher=SAS Institute \|isbn=9781555446116 \|oclc=35546178}}</ref> [[Probabilistic reasoning]] was also employed, especially in [[automated medical diagnosis]].<ref name="aima">{{cite AIMA\|edition=2}}</ref>{{rp\|488}}		As a scientific endeavour, machine learning grew out of the quest for [[artificial intelligence]] (AI). In the early days of AI as an [[Discipline (academia)\|academic discipline]], some researchers were interested in having machines learn from data. They attempted to approach the problem with various symbolic methods, as well as what were then termed "[[Artificial neural network\|neural network]]s"; these were mostly [[perceptron]]s and [[ADALINE\|other models]] that were later found to be reinventions of the [[generalised linear model]]s of statistics.<ref>{{cite book \|last1=Sarle \|first1=Warren S.\|chapter=Neural Networks and statistical models \|pages=1538–50 \|year=1994 \|title=SUGI 19: proceedings of the Nineteenth Annual SAS Users Group International Conference \|publisher=SAS Institute \|isbn=9781555446116 \|oclc=35546178}}</ref> [[Probabilistic reasoning]] was also employed, especially in [[automated medical diagnosis]].<ref name="aima">{{cite AIMA\|edition=2}}</ref>{{rp\|488}}

Line 82:		Line 82:

	{{Anchor\|Algorithm types}}		{{Anchor\|Algorithm types}}
	[[File:Supervised_and_unsupervised_learning.png\|thumb\|upright=1.3\|In supervised learning, the training data is labelled with the expected answers, while in [[unsupervised learning]], the model identifies patterns or structures in unlabelled data.]]		[[File:Supervised_and_unsupervised_learning.png\|thumb\|upright=1.3\|In [[supervised learning]], the training data is labelled with the expected answers, while in [[unsupervised learning]], the model identifies patterns or structures in unlabelled data.]]
	Machine learning approaches are traditionally divided into three broad categories, which correspond to learning paradigms, depending on the nature of the "signal" or "feedback" available to the learning system:		Machine learning approaches are traditionally divided into three broad categories, which correspond to learning paradigms, depending on the nature of the "signal" or "feedback" available to the learning system:
	* [[Supervised learning]]: The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that [[Map (mathematics)\|maps]] inputs to outputs.		* [[Supervised learning]]: The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that [[Map (mathematics)\|maps]] inputs to outputs.
Line 327:		Line 327:
	{{colend}}		{{colend}}

	In 2006, the media-services provider [[Netflix]] held the first "[[Netflix Prize]]" competition to find a program to better predict user preferences and improve the accuracy of its existing Cinematch movie recommendation algorithm by at least 10%. A joint team made up of researchers from [[AT&T Labs]]-Research in collaboration with the teams Big Chaos and Pragmatic Theory built an [[Ensemble Averaging\|ensemble model]] to win the Grand Prize in 2009 for $1 million.<ref>[https://web.archive.org/web/20151110062742/http://www2.research.att.com/~volinsky/netflix/ "BelKor Home Page"] research.att.com</ref> Shortly after the prize was awarded, Netflix realised that viewers' ratings were not the best indicators of their viewing patterns ("everything is a recommendation") and they changed their recommendation engine accordingly.<ref>{{cite web\|url=http://techblog.netflix.com/2012/04/netflix-recommendations-beyond-5-stars.html\|title=The Netflix Tech Blog: Netflix Recommendations: Beyond the 5 stars (Part 1)\|access-date=8 August 2015\|date=6 April 2012\|archive-url=https://web.archive.org/web/20160531002916/http://techblog.netflix.com/2012/04/netflix-recommendations-beyond-5-stars.html\|archive-date=31 May 2016}}</ref> In 2010, an article in ~~the~~ ''[[The Wall Street Journal]]'' noted the use of machine learning by Rebellion Research to predict the [[2008 financial crisis]].<ref>{{cite web\|url=https://www.wsj.com/articles/SB10001424052748703834604575365310813948080\|title=Letting the Machines Decide\|author=Scott Patterson\|date=13 July 2010\|publisher=[[The Wall Street Journal]]\|access-date=24 June 2018\|archive-date=24 June 2018\|archive-url=https://web.archive.org/web/20180624151019/https://www.wsj.com/articles/SB10001424052748703834604575365310813948080\|url-status=live}}</ref> In 2012, co-founder of [[Sun Microsystems]], [[Vinod Khosla]], predicted that 80% of medical doctors jobs would be lost in the next two decades to automated machine learning medical diagnostic software.<ref>{{cite web\|url=https://techcrunch.com/2012/01/10/doctors-or-algorithms/\|author=Vinod Khosla\|publisher=Tech Crunch\|title=Do We Need Doctors or Algorithms?\|date=10 January 2012\|access-date=20 October 2016\|archive-date=18 June 2018\|archive-url=https://web.archive.org/web/20180618175811/https://techcrunch.com/2012/01/10/doctors-or-algorithms/\|url-status=live}}</ref> In 2014, it was reported that a machine learning algorithm had been applied in the field of art history to study fine art paintings and that it may have revealed previously unrecognised influences among artists.<ref>[https://medium.com/the-physics-arxiv-blog/when-a-machine-learning-algorithm-studied-fine-art-paintings-it-saw-things-art-historians-had-never-b8e4e7bf7d3e When A Machine Learning Algorithm Studied Fine Art Paintings, It Saw Things Art Historians Had Never Noticed] {{Webarchive\|url=https://web.archive.org/web/20160604072143/https://medium.com/the-physics-arxiv-blog/when-a-machine-learning-algorithm-studied-fine-art-paintings-it-saw-things-art-historians-had-never-b8e4e7bf7d3e \|date=4 June 2016 }}, ''The Physics at [[ArXiv]] blog''</ref> In 2019 [[Springer Nature]] published the first research book created using machine learning.<ref>{{Cite web\|url=https://www.theverge.com/2019/4/10/18304558/ai-writing-academic-research-book-springer-nature-artificial-intelligence\|title=The first AI-generated textbook shows what robot writers are actually good at\|last=Vincent\|first=James\|date=10 April 2019\|website=The Verge\|access-date=5 May 2019\|archive-date=5 May 2019\|archive-url=https://web.archive.org/web/20190505200409/https://www.theverge.com/2019/4/10/18304558/ai-writing-academic-research-book-springer-nature-artificial-intelligence\|url-status=live}}</ref> In 2020, machine learning technology was used to help make diagnoses and aid researchers in developing a cure for COVID-19.<ref>{{Cite journal\|title=Artificial Intelligence (AI) applications for COVID-19 pandemic\|date=1 July 2020\|journal=Diabetes & Metabolic Syndrome: Clinical Research & Reviews\|volume=14\|issue=4\|pages=337–339\|doi=10.1016/j.dsx.2020.04.012\|doi-access=free\|last1=Vaishya\|first1=Raju\|last2=Javaid\|first2=Mohd\|last3=Khan\|first3=Ibrahim Haleem\|last4=Haleem\|first4=Abid\|pmid=32305024\|pmc=7195043}}</ref> Machine learning was recently applied to predict the pro-environmental behaviour of travellers.<ref>{{Cite journal\|title=Application of machine learning to predict visitors' green behavior in marine protected areas: evidence from Cyprus\|first1=Hamed\|last1=Rezapouraghdam\|first2=Arash\|last2=Akhshik\|first3=Haywantee\|last3=Ramkissoon\|date=10 March 2021\|journal=Journal of Sustainable Tourism\|volume=31 \|issue=11 \|pages=2479–2505\|doi=10.1080/09669582.2021.1887878\|doi-access=free\|hdl=10037/24073\|hdl-access=free}}</ref> Recently, machine learning technology was also applied to optimise smartphone's performance and thermal behaviour based on the user's interaction with the phone.<ref>{{Cite book\|last1=Dey\|first1=Somdip\|last2=Singh\|first2=Amit Kumar\|last3=Wang\|first3=Xiaohang\|last4=McDonald-Maier\|first4=Klaus\|title=2020 Design, Automation & Test in Europe Conference & Exhibition (DATE) \|chapter=User Interaction Aware Reinforcement Learning for Power and Thermal Efficiency of CPU-GPU Mobile MPSoCs \|date=15 June 2020\|chapter-url=https://ieeexplore.ieee.org/document/9116294\|pages=1728–1733\|doi=10.23919/DATE48585.2020.9116294\|isbn=978-3-9819263-4-7\|s2cid=219858480\|url=http://repository.essex.ac.uk/27546/1/User%20Interaction%20Aware%20Reinforcement%20Learning.pdf \|access-date=20 January 2022\|archive-date=13 December 2021\|archive-url=https://web.archive.org/web/20211213192526/https://ieeexplore.ieee.org/document/9116294/\|url-status=live}}</ref><ref>{{Cite news\|last=Quested\|first=Tony\|title=Smartphones get smarter with Essex innovation\|work=Business Weekly\|url=https://www.businessweekly.co.uk/news/academia-research/smartphones-get-smarter-essex-innovation\|access-date=17 June 2021\|archive-date=24 June 2021\|archive-url=https://web.archive.org/web/20210624200126/https://www.businessweekly.co.uk/news/academia-research/smartphones-get-smarter-essex-innovation\|url-status=live}}</ref><ref>{{Cite news\|last=Williams\|first=Rhiannon\|date=21 July 2020\|title=Future smartphones 'will prolong their own battery life by monitoring owners' behaviour'\|url=https://inews.co.uk/news/technology/future-smartphones-prolong-battery-life-monitoring-behaviour-558689\|access-date=17 June 2021\|newspaper=[[i (British newspaper)\|i]]\|language=en\|archive-date=24 June 2021\|archive-url=https://web.archive.org/web/20210624201153/https://inews.co.uk/news/technology/future-smartphones-prolong-battery-life-monitoring-behaviour-558689\|url-status=live}}</ref> When applied correctly, machine learning algorithms (MLAs) can utilise a wide range of company characteristics to predict stock returns without [[overfitting]]. By employing effective feature engineering and combining forecasts, MLAs can generate results that far surpass those obtained from basic linear techniques like [[Ordinary least squares\|OLS]].<ref>{{Cite journal \|last1=Rasekhschaffe \|first1=Keywan Christian \|last2=Jones \|first2=Robert C. \|date=1 July 2019 \|title=Machine Learning for Stock Selection \|url=https://www.tandfonline.com/doi/full/10.1080/0015198X.2019.1596678 \|journal=Financial Analysts Journal \|language=en \|volume=75 \|issue=3 \|pages=70–88 \|doi=10.1080/0015198X.2019.1596678 \|s2cid=108312507 \|issn=0015-198X \|access-date=26 November 2023 \|archive-date=26 November 2023 \|archive-url=https://web.archive.org/web/20231126160605/https://www.tandfonline.com/doi/full/10.1080/0015198X.2019.1596678 \|url-status=live \|url-access=subscription }}</ref>		In 2006, the media-services provider [[Netflix]] held the first "[[Netflix Prize]]" competition to find a program to better predict user preferences and improve the accuracy of its existing Cinematch movie recommendation algorithm by at least 10%. A joint team made up of researchers from [[AT&T Labs]]-Research in collaboration with the teams Big Chaos and Pragmatic Theory built an [[Ensemble Averaging\|ensemble model]] to win the Grand Prize in 2009 for $1 million.<ref>[https://web.archive.org/web/20151110062742/http://www2.research.att.com/~volinsky/netflix/ "BelKor Home Page"] research.att.com</ref> Shortly after the prize was awarded, Netflix realised that viewers' ratings were not the best indicators of their viewing patterns ("everything is a recommendation") and they changed their recommendation engine accordingly.<ref>{{cite web\|url=http://techblog.netflix.com/2012/04/netflix-recommendations-beyond-5-stars.html\|title=The Netflix Tech Blog: Netflix Recommendations: Beyond the 5 stars (Part 1)\|access-date=8 August 2015\|date=6 April 2012\|archive-url=https://web.archive.org/web/20160531002916/http://techblog.netflix.com/2012/04/netflix-recommendations-beyond-5-stars.html\|archive-date=31 May 2016}}</ref> In 2010, an article in ''[[The Wall Street Journal]]'' noted the use of machine learning by Rebellion Research to predict the [[2008 financial crisis]].<ref>{{cite web\|url=https://www.wsj.com/articles/SB10001424052748703834604575365310813948080\|title=Letting the Machines Decide\|author=Scott Patterson\|date=13 July 2010\|publisher=[[The Wall Street Journal]]\|access-date=24 June 2018\|archive-date=24 June 2018\|archive-url=https://web.archive.org/web/20180624151019/https://www.wsj.com/articles/SB10001424052748703834604575365310813948080\|url-status=live}}</ref> In 2012, co-founder of [[Sun Microsystems]], [[Vinod Khosla]], predicted that 80% of medical doctors jobs would be lost in the next two decades to automated machine learning medical diagnostic software.<ref>{{cite web\|url=https://techcrunch.com/2012/01/10/doctors-or-algorithms/\|author=Vinod Khosla\|publisher=Tech Crunch\|title=Do We Need Doctors or Algorithms?\|date=10 January 2012\|access-date=20 October 2016\|archive-date=18 June 2018\|archive-url=https://web.archive.org/web/20180618175811/https://techcrunch.com/2012/01/10/doctors-or-algorithms/\|url-status=live}}</ref> In 2014, it was reported that a machine learning algorithm had been applied in the field of art history to study fine art paintings and that it may have revealed previously unrecognised influences among artists.<ref>[https://medium.com/the-physics-arxiv-blog/when-a-machine-learning-algorithm-studied-fine-art-paintings-it-saw-things-art-historians-had-never-b8e4e7bf7d3e When A Machine Learning Algorithm Studied Fine Art Paintings, It Saw Things Art Historians Had Never Noticed] {{Webarchive\|url=https://web.archive.org/web/20160604072143/https://medium.com/the-physics-arxiv-blog/when-a-machine-learning-algorithm-studied-fine-art-paintings-it-saw-things-art-historians-had-never-b8e4e7bf7d3e \|date=4 June 2016 }}, ''The Physics at [[ArXiv]] blog''</ref> In 2019 [[Springer Nature]] published the first research book created using machine learning.<ref>{{Cite web\|url=https://www.theverge.com/2019/4/10/18304558/ai-writing-academic-research-book-springer-nature-artificial-intelligence\|title=The first AI-generated textbook shows what robot writers are actually good at\|last=Vincent\|first=James\|date=10 April 2019\|website=The Verge\|access-date=5 May 2019\|archive-date=5 May 2019\|archive-url=https://web.archive.org/web/20190505200409/https://www.theverge.com/2019/4/10/18304558/ai-writing-academic-research-book-springer-nature-artificial-intelligence\|url-status=live}}</ref> In 2020, machine learning technology was used to help make diagnoses and aid researchers in developing a cure for COVID-19.<ref>{{Cite journal\|title=Artificial Intelligence (AI) applications for COVID-19 pandemic\|date=1 July 2020\|journal=Diabetes & Metabolic Syndrome: Clinical Research & Reviews\|volume=14\|issue=4\|pages=337–339\|doi=10.1016/j.dsx.2020.04.012\|doi-access=free\|last1=Vaishya\|first1=Raju\|last2=Javaid\|first2=Mohd\|last3=Khan\|first3=Ibrahim Haleem\|last4=Haleem\|first4=Abid\|pmid=32305024\|pmc=7195043}}</ref> Machine learning was recently applied to predict the pro-environmental behaviour of travellers.<ref>{{Cite journal\|title=Application of machine learning to predict visitors' green behavior in marine protected areas: evidence from Cyprus\|first1=Hamed\|last1=Rezapouraghdam\|first2=Arash\|last2=Akhshik\|first3=Haywantee\|last3=Ramkissoon\|date=10 March 2021\|journal=Journal of Sustainable Tourism\|volume=31 \|issue=11 \|pages=2479–2505\|doi=10.1080/09669582.2021.1887878\|doi-access=free\|hdl=10037/24073\|hdl-access=free}}</ref> Recently, machine learning technology was also applied to optimise smartphone's performance and thermal behaviour based on the user's interaction with the phone.<ref>{{Cite book\|last1=Dey\|first1=Somdip\|last2=Singh\|first2=Amit Kumar\|last3=Wang\|first3=Xiaohang\|last4=McDonald-Maier\|first4=Klaus\|title=2020 Design, Automation & Test in Europe Conference & Exhibition (DATE) \|chapter=User Interaction Aware Reinforcement Learning for Power and Thermal Efficiency of CPU-GPU Mobile MPSoCs \|date=15 June 2020\|chapter-url=https://ieeexplore.ieee.org/document/9116294\|pages=1728–1733\|doi=10.23919/DATE48585.2020.9116294\|isbn=978-3-9819263-4-7\|s2cid=219858480\|url=http://repository.essex.ac.uk/27546/1/User%20Interaction%20Aware%20Reinforcement%20Learning.pdf \|access-date=20 January 2022\|archive-date=13 December 2021\|archive-url=https://web.archive.org/web/20211213192526/https://ieeexplore.ieee.org/document/9116294/\|url-status=live}}</ref><ref>{{Cite news\|last=Quested\|first=Tony\|title=Smartphones get smarter with Essex innovation\|work=Business Weekly\|url=https://www.businessweekly.co.uk/news/academia-research/smartphones-get-smarter-essex-innovation\|access-date=17 June 2021\|archive-date=24 June 2021\|archive-url=https://web.archive.org/web/20210624200126/https://www.businessweekly.co.uk/news/academia-research/smartphones-get-smarter-essex-innovation\|url-status=live}}</ref><ref>{{Cite news\|last=Williams\|first=Rhiannon\|date=21 July 2020\|title=Future smartphones 'will prolong their own battery life by monitoring owners' behaviour'\|url=https://inews.co.uk/news/technology/future-smartphones-prolong-battery-life-monitoring-behaviour-558689\|access-date=17 June 2021\|newspaper=[[i (British newspaper)\|i]]\|language=en\|archive-date=24 June 2021\|archive-url=https://web.archive.org/web/20210624201153/https://inews.co.uk/news/technology/future-smartphones-prolong-battery-life-monitoring-behaviour-558689\|url-status=live}}</ref> When applied correctly, machine learning algorithms (MLAs) can utilise a wide range of company characteristics to predict stock returns without [[overfitting]]. By employing effective feature engineering and combining forecasts, MLAs can generate results that far surpass those obtained from basic linear techniques like [[Ordinary least squares\|OLS]].<ref>{{Cite journal \|last1=Rasekhschaffe \|first1=Keywan Christian \|last2=Jones \|first2=Robert C. \|date=1 July 2019 \|title=Machine Learning for Stock Selection \|url=https://www.tandfonline.com/doi/full/10.1080/0015198X.2019.1596678 \|journal=Financial Analysts Journal \|language=en \|volume=75 \|issue=3 \|pages=70–88 \|doi=10.1080/0015198X.2019.1596678 \|s2cid=108312507 \|issn=0015-198X \|access-date=26 November 2023 \|archive-date=26 November 2023 \|archive-url=https://web.archive.org/web/20231126160605/https://www.tandfonline.com/doi/full/10.1080/0015198X.2019.1596678 \|url-status=live \|url-access=subscription }}</ref>

	Recent advancements in machine learning have extended into the field of quantum chemistry, where novel algorithms now enable the prediction of solvent effects on chemical reactions, thereby offering new tools for chemists to tailor experimental conditions for optimal outcomes.<ref>{{Cite journal \|last1=Chung \|first1=Yunsie \|last2=Green \|first2=William H. \|date=2024 \|title=Machine learning from quantum chemistry to predict experimental solvent effects on reaction rates \|journal=Chemical Science \|language=en \|volume=15 \|issue=7 \|pages=2410–2424 \|doi=10.1039/D3SC05353A \|issn=2041-6520 \|pmc=10866337 \|pmid=38362410 }}</ref>		Recent advancements in machine learning have extended into the field of quantum chemistry, where novel algorithms now enable the prediction of solvent effects on chemical reactions, thereby offering new tools for chemists to tailor experimental conditions for optimal outcomes.<ref>{{Cite journal \|last1=Chung \|first1=Yunsie \|last2=Green \|first2=William H. \|date=2024 \|title=Machine learning from quantum chemistry to predict experimental solvent effects on reaction rates \|journal=Chemical Science \|language=en \|volume=15 \|issue=7 \|pages=2410–2424 \|doi=10.1039/D3SC05353A \|issn=2041-6520 \|pmc=10866337 \|pmid=38362410 }}</ref>

imported>Forever; wherever: /* physical neural networks */ Capitalize sub-section title's first letter

2025-06-20T00:51:59Z

physical neural networks: Capitalize sub-section title's first letter

Show changes

Machine learning - Revision history

imported>Citation bot: Add: bibcode, pmid, issue, authors 1-1. Removed URL that duplicated identifier. Removed parameters. Some additions/deletions were parameter name changes. | Use this bot. Report bugs. | Suggested by Abductive | #UCB_toolbar

imported>Zefr: Reverted 1 edit by Iamchriswalter (talk): Better written before

imported>Forever; wherever: /* physical neural networks */ Capitalize sub-section title's first letter

2001:67C:10EC:578F:8000:0:0:216 at 14:43, 28 May 2025