Prehistory — From Neural Networks to the TransformerYoshua Bengio, Aaron Courville, Pascal VincentYoshua Bengio

Representation Learning: A Review and New Perspectives

Representation Learning: A Review and New Perspectives released on arXiv

Why it matters

Framed representation learning as a single problem, becoming the field's standard reference from then on

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/1206.5538

Added in Week 35, 2026 · See that week

Nearby on the same axis

Improving neural networks by preventing co-adaptation of feature detectorsPaperSuperVision wins ILSVRC 2012 with a 15.3% top-5 error rateOfficialImageNet Classification with Deep Convolutional Neural Networks (AlexNet)PaperDeep Neural Networks for Acoustic Modeling in Speech RecognitionOfficial