Masjienleer

Masjienleer (ML) is 'n oorkoepelende term vir die oplossing van probleme waarvoor die ontwikkeling van algoritmes deur menslike programmeerders duur sou wees. In plaas daarvan word die probleme opgelos deur masjiene te help om hul "eie" algoritmes te "ontdek",^[1] sonder dat dit nodig is om uitdruklik aangesê te word wat om te doen deur enige mens-ontwikkelde algoritmes.^[2] Onlangs kon generatiewe kunsmatige neurale netwerke die resultate van baie vorige benaderings oortref.^[3]^[4] Masjienleerbenaderings is gebaseer op groot taalmodelle, rekenaarvisie, spraakherkenning, e-posfiltrering, landbou en medisyne, waar dit ook te duur sou wees om algoritmes te ontwikkel om die nodige take uit te voer.^[5]^[6]

Die wiskundige fondamente van ML word verskaf deur wiskundige optimering (wiskundige programmering) metodes. Data-ontginning is 'n verwante (parallelle) studieveld, wat fokus op verkennende data-analise deur leer sonder toesig.^[8]^[9]

ML word veral gebruik vir die oplossing van besigheidsprobleme, wat bekend staan as voorspellings-analise. Alhoewel nie alle masjienleer statisties gebaseer is nie, is rekenaarstatistiek 'n belangrike bron vir die veld se metodes.

Verwysings

↑ Ethem Alpaydin (2020). Introduction to Machine Learning (Fourth uitg.). MIT. pp. xix, 1–3, 13–18. ISBN 978-0262043793.
↑ TDie definisie "sonder om eksplisiet geprogrammeer te word" word dikwels toegeskryf aan Arthur Samuel, wat die term "masjienleer" in 1959 geskep het, maar die frase word nie woordeliks in hierdie publikasie gevind nie, en kan 'n parafrase wees wat later verskyn het. Confer "Paraphrasing Arthur Samuel (1959), the question is: How can computers learn to solve problems without being explicitly programmed?" in (1996) "Artificial Intelligence in Design '96" in Artificial Intelligence in Design '96.: 151–170, Springer, Dordrecht. doi:10.1007/978-94-009-0279-4_9.
↑ "What is Machine Learning?". IBM (in Engels (VSA)). Besoek op 27 Junie 2023.
↑ Zhou, Victor (20 Desember 2019). "Machine Learning for Beginners: An Introduction to Neural Networks". Medium (in Engels). Geargiveer vanaf die oorspronklike op 9 Maart 2022. Besoek op 15 Augustus 2021.
↑ Hu, Junyan; Niu, Hanlin; Carrasco, Joaquin; Lennox, Barry; Arvin, Farshad (2020). "Voronoi-Based Multi-Robot Autonomous Exploration in Unknown Environments via Deep Reinforcement Learning". IEEE Transactions on Vehicular Technology. 69 (12): 14413–14423. doi:10.1109/tvt.2020.3034800. ISSN 0018-9545. S2CID 228989788. Geargiveer vanaf die oorspronklike op 16 April 2023. Besoek op 16 April 2023.
↑ Yoosefzadeh-Najafabadi, Mohsen; Hugh, Earl; Tulpan, Dan; Sulik, John; Eskandari, Milad (2021). "Application of Machine Learning Algorithms in Plant Breeding: Predicting Yield From Hyperspectral Reflectance in Soybean?". Front. Plant Sci. 11: 624273. doi:10.3389/fpls.2020.624273. PMC 7835636. PMID 33510761.
↑ Bishop, C. M. (2006), Pattern Recognition and Machine Learning, Springer, ISBN 978-0-387-31073-2
↑ Machine learning and pattern recognition "can be viewed as two facets of the same field".^[7]</ref>^:vii
↑ Friedman, Jerome H. (1998). "Data Mining and Statistics: What's the connection?". Computing Science and Statistics. 29 (1): 3–9.

[Alpaydin2020-1] Ethem Alpaydin (2020). Introduction to Machine Learning (Fourth uitg.). MIT. pp. xix, 1–3, 13–18. ISBN 978-0262043793.

[2] TDie definisie "sonder om eksplisiet geprogrammeer te word" word dikwels toegeskryf aan Arthur Samuel, wat die term "masjienleer" in 1959 geskep het, maar die frase word nie woordeliks in hierdie publikasie gevind nie, en kan 'n parafrase wees wat later verskyn het. Confer "Paraphrasing Arthur Samuel (1959), the question is: How can computers learn to solve problems without being explicitly programmed?" in (1996) "Artificial Intelligence in Design '96" in Artificial Intelligence in Design '96.: 151–170, Springer, Dordrecht. doi:10.1007/978-94-009-0279-4_9.

[ibm-3] "What is Machine Learning?". IBM (in Engels (VSA)). Besoek op 27 Junie 2023.

[:6-4] Zhou, Victor (20 Desember 2019). "Machine Learning for Beginners: An Introduction to Neural Networks". Medium (in Engels). Geargiveer vanaf die oorspronklike op 9 Maart 2022. Besoek op 15 Augustus 2021.

[tvt-5] Hu, Junyan; Niu, Hanlin; Carrasco, Joaquin; Lennox, Barry; Arvin, Farshad (2020). "Voronoi-Based Multi-Robot Autonomous Exploration in Unknown Environments via Deep Reinforcement Learning". IEEE Transactions on Vehicular Technology. 69 (12): 14413–14423. doi:10.1109/tvt.2020.3034800. ISSN 0018-9545. S2CID 228989788. Geargiveer vanaf die oorspronklike op 16 April 2023. Besoek op 16 April 2023.

[:7-6] Yoosefzadeh-Najafabadi, Mohsen; Hugh, Earl; Tulpan, Dan; Sulik, John; Eskandari, Milad (2021). "Application of Machine Learning Algorithms in Plant Breeding: Predicting Yield From Hyperspectral Reflectance in Soybean?". Front. Plant Sci. 11: 624273. doi:10.3389/fpls.2020.624273. PMC 7835636. PMID 33510761.

[bishop2006-7] Bishop, C. M. (2006), Pattern Recognition and Machine Learning, Springer, ISBN 978-0-387-31073-2

[8] Machine learning and pattern recognition "can be viewed as two facets of the same field".^[7]</ref>^:vii

[9] Friedman, Jerome H. (1998). "Data Mining and Statistics: What's the connection?". Computing Science and Statistics. 29 (1): 3–9.

[1]

[2]

[3]

[4]

[5]

[6]

[8]

[9]

[7]