Deep learning

Deep learning is een deel van een grotere familie van methodes van machinaal leren, gebaseerd op kunstmatige neurale netwerken. Het leren kan gesuperviseerd gebeuren, semi-gesuperviseerd, of niet gesuperviseerd.[1]

Deep learning kan toegepast worden in domeinen zoals beeldherkenning, spraakherkenning, natural language processing, audioherkenning, social network-filtering, machinevertaling, bioinformatica, samenstelling van medicijnen, medische beeldherkenning en bordspelprogramma's. Ze kunnen soms resultaten bekomen vergelijkbaar met of soms beter dan menselijke specialisten.[2][3][4]

Bibliografie

(en) Goodfellow, Ian; Bengio, Yoshua; Courville, Aaron, Deep Learning. MIT Press (2016). ISBN 978-0-26203561-3.

Bronnen, noten en/of referenties

(2015) . Deep Learning. Nature 521 (7553): 436–444 . PMID: 26017442. DOI: 10.1038/nature14539.
Ciresan, Dan (June 2012) . Multi-column deep neural networks for image classification. 2012 IEEE Conference on Computer Vision and Pattern Recognition: 3642–3649 . DOI: 10.1109/cvpr.2012.6248110.
(2012) . ImageNet Classification with Deep Convolutional Neural Networks. NIPS 2012: Neural Information Processing Systems, Lake Tahoe, Nevada .
Google's AlphaGo AI wins three-match series against the world's best Go player. TechCrunch (25 May 2017).

This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.

[NatureBengio-1] (2015) . Deep Learning. Nature 521 (7553): 436–444 . PMID: 26017442. DOI: 10.1038/nature14539.

[:9-2] Ciresan, Dan (June 2012) . Multi-column deep neural networks for image classification. 2012 IEEE Conference on Computer Vision and Pattern Recognition: 3642–3649 . DOI: 10.1109/cvpr.2012.6248110.

[krizhevsky2012-3] (2012) . ImageNet Classification with Deep Convolutional Neural Networks. NIPS 2012: Neural Information Processing Systems, Lake Tahoe, Nevada .

[4] Google's AlphaGo AI wins three-match series against the world's best Go player. TechCrunch (25 May 2017).