Journal article icon

Journal article

Unsupervised discovery of nonlinear structure using contrastive backpropagation.

Abstract:

We describe 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. The connection weights that determine how the activity of each unit depends on the activities in earlier layers are learned by minimizing the energy assigned to data vectors that are actually observed and ma...

Expand abstract
Publication status:
Published

Actions


Access Document


Publisher copy:
10.1207/s15516709cog0000_76

Authors


Osindero, S More by this author
Welling, M More by this author
More by this author
Institution:
University of Oxford
Department:
Oxford, MPLS, Statistics
Journal:
Cognitive science
Volume:
30
Issue:
4
Pages:
725-731
Publication date:
2006-07-05
DOI:
EISSN:
1551-6709
ISSN:
0364-0213
URN:
uuid:7e696a80-79be-4bc6-a78c-834b6ef1a1ce
Source identifiers:
352652
Local pid:
pubs:352652

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP