Rectified Gaussian distributions and the identification of multiple cause structure in data

Darryl Charles, Colin Fyfe

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We investigate the use of an unsupervised artificial neural network to form a sparse representation of the underlying causes in a data set. By using fixed lateral connections that are derived from the Rectified Generalized Gaussian distribution, we form a network that is capable of identifying the multiple cause structure of the data. We further show that some topology preservation of the input data is possible using this network and that related features may be coded in separate areas of the output space.

Original languageEnglish
Title of host publicationIEEE Conference Publication
PublisherPubl by IEEE
Pages192-197
Number of pages6
Edition470
ISBN (Print)0852967217, 9780852967218
DOIs
Publication statusPublished (in print/issue) - 1999
EventProceedings of the 1999 the 9th International Conference on 'Artificial Neural Networks (ICANN99)' - Edinburgh, UK
Duration: 7 Sep 199910 Sep 1999

Publication series

NameIEE Conference Publication
Number470
Volume1
ISSN (Print)0537-9989

Conference

ConferenceProceedings of the 1999 the 9th International Conference on 'Artificial Neural Networks (ICANN99)'
CityEdinburgh, UK
Period7/09/9910/09/99

Fingerprint

Dive into the research topics of 'Rectified Gaussian distributions and the identification of multiple cause structure in data'. Together they form a unique fingerprint.

Cite this