ML Anthology

A Fast Learning Algorithm for Deep Belief Nets

Geoffrey E. Hinton, Simon Osindero, Yee-Whye Teh
Notable Works 2006 pp. 1527-1554
doi:10.1162/neco.2006.18.7.1527 /misc/2006/hinton2006misc-fast/

Abstract

We derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of handwritten digit images and their labels.

PDF Semantic Scholar

Cite

Text

Hinton et al. "A Fast Learning Algorithm for Deep Belief Nets." Neural Computation, 2006. doi:10.1162/neco.2006.18.7.1527

Markdown

[Hinton et al. "A Fast Learning Algorithm for Deep Belief Nets." Neural Computation, 2006.](https://mlanthology.org/misc/2006/hinton2006misc-fast/) doi:10.1162/neco.2006.18.7.1527

BibTeX

@misc{hinton2006misc-fast,
  title     = {{A Fast Learning Algorithm for Deep Belief Nets}},
  author    = {Hinton, Geoffrey E. and Osindero, Simon and Teh, Yee-Whye},
  howpublished = {Neural Computation},
  year      = {2006},
  pages     = {1527-1554},
  doi       = {10.1162/neco.2006.18.7.1527},
  volume    = {18},
  number    = {7},
  url       = {https://mlanthology.org/misc/2006/hinton2006misc-fast/}
}