Dossier de preuve de méthode

AlexNet

AlexNet is a deep convolutional neural network (CNN) introduced by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton in 2012. It won the ImageNet Large Scale Visual Recognition Challenge (ILSVRC 2012) with a top-5 error rate of 15.3%, outstripping the runner-up by more than 10 percentage points and reigniting broad interest in deep learning. The architecture introduced or popularised several techniques — ReLU activations, dropout regularisation, and multi-GPU training — that became standard practice across the field.

Sources recorded, not reviewed

Dossier source

Citations copiées telles quelles du dossier source de la méthode. Aucune vérification au niveau de la revendication n'en est déduite.

AlexNet (Krizhevsky–Sutskever–Hinton Deep Convolutional Neural Network)

Dossier de méthode taxonomique · ml-model / deep-learning

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, 25, 1097–1105. (Republished: Communications of the ACM, 60(6), 84–90, 2017.) · DOI 10.1145/3065386
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Ch. 9: Convolutional Networks). MIT Press. · ISBN 978-0-262-03561-3
LeCun, Y., Bengio, Y., & Hinton, G. E. (2015). Deep Learning. Nature, 521, 436–444. · DOI 10.1038/nature14539

Ouvrir la méthode complète

Revendications organisées

Revendications enregistrées dans le registre de preuves, chacune avec sa propre évaluation.

Pas encore de revendications organisées

Cette vue n'invente pas d'évaluation de revendication lorsque le registre n'en contient aucune.

Méthodes apparentées

Généré à partir du graphe de méthodes et présenté comme des relations suggérées par la machine — aucune revendication de preuve n'est déduite.

Same method familyBatch Normalizationmachine-suggested · Relational suggestion, not evidence.Same method familyDropoutmachine-suggested · Relational suggestion, not evidence.Same method familyResNetmachine-suggested · Relational suggestion, not evidence.