Using noise to form a minimal overcomplete basis

Colin Fyfe, Darryl Charles

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

5 Citations (Scopus)


We have recently developed an extension of a Principal Component Analysis Artificial Neural Network which we have linked to the statistical technique of Factor Analysis. We have shown that the resulting network can identify the independent components of visual scenes. We now show that, in cases where the Factor Analysis network identifies factors of greater number than the inherent dimensionality of the input space, the addition of noise leads to an optimally sparse representation of the input data which we link to a minimal overcomplete basis. We show that in cases in which the data set is not itself inherently sparse, the method induces a very sparse description of the data set.

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

Publication series

NameIEEE Conference Publication
ISSN (Print)0537-9989


ConferenceProceedings of the 1999 the 9th International Conference on 'Artificial Neural Networks (ICANN99)'
CityEdinburgh, UK


Dive into the research topics of 'Using noise to form a minimal overcomplete basis'. Together they form a unique fingerprint.

Cite this