• Publications
  • Influence
The "wake-sleep" algorithm for unsupervised neural networks.
TLDR
An unsupervised learning algorithm for a multilayer network of stochastic neurons is described. Expand
  • 920
  • 40
  • PDF
Lesioning an attractor network: investigations of acquired dyslexia
A recurrent connectionist network was trained to output semantic feature vectors when presented with letter strings. When damaged, the network exhibited characteristics that resembled several of theExpand
  • 551
  • 14
Lesioning an attractor network: investigations of acquired dyslexia.
A recurrent connectionist network was trained to output semantic feature vectors when presented with letter strings. When damaged, the network exhibited characteristics that resembled several of theExpand
  • 182
  • 12
  • PDF
Generative models for discovering sparse distributed representations.
TLDR
We describe a hierarchical, generative model that can be viewed as a nonlinear generalization of factor analysis and can be implemented in a neural network. Expand
  • 256
  • 11
  • PDF
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition-' Washington , D . C . , June , 1983 OPTIMAL PERCEPTUAL INFERENCE
When a vision system creates an interpretation of some input data, it assigns truth values or probabilities to internal hypotheses about the world. \Ve present a non-deterministic method forExpand
  • 69
  • 5
  • PDF
A Hierarchical Community of Experts
TLDR
We describe a directed acyclic graphical model that contains a hierarchy of linear units and a mechanism for dynamically selecting an appropriate subset of these units to model each observation. Expand
  • 48
  • 5
  • PDF
Subclass Distillation
TLDR
We show that a teacher trained to produce subclasses is able to discover the original CIFAR-10 classes, despite receiving only binary supervision. Expand
  • 7
  • 3
  • PDF
...
1
2
3
...