한국어EN
Prehistory — From Neural Networks to the TransformerYoshua Bengio et al.Yoshua Bengio

Greedy Layer-Wise Training of Deep Networks

Greedy Layer-Wise Training of Deep Networks — presented at NIPS 2006

Why it matters

Showed experimentally that layer-wise unsupervised pretraining eases the difficulty of training

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

Paperpapers.nips.cchttps://papers.nips.cc/paper_files/paper/2006/hash/5da713a690c067105aeb2fae32403405-Abstract.html

Added in Week 35, 2026 · See that week

Nearby on the same axis

A Fast Learning Algorithm for Deep Belief NetsOfficialImageNet: A Large-Scale Hierarchical Image DatabaseOfficialLarge-scale Deep Unsupervised Learning using Graphics ProcessorsOfficialDeep Big Simple Neural Nets Excel on Handwritten Digit RecognitionPaper