Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation

Explore this paper's citation graph

Summary

A way of modeling high-dimensional data vectors by using an unsupervised, nonlinear, multilayer neural network in which the activity of each neuron-like unit makes an additive contribution to a global energy score that indicates how surprised the network is by the data vector.

Type
article
Published
2006-07-08
Cited by
155
References
13

Keywords

Artificial neural network, Energy (signal processing), Nonlinear system, Backpropagation, Computer science

References

Cited by

Related papers