Return to search

Learning Linear, Sparse, Factorial Codes

In previous work (Olshausen & Field 1996), an algorithm was described for learning linear sparse codes which, when trained on natural images, produces a set of basis functions that are spatially localized, oriented, and bandpass (i.e., wavelet-like). This note shows how the algorithm may be interpreted within a maximum-likelihood framework. Several useful insights emerge from this connection: it makes explicit the relation to statistical independence (i.e., factorial coding), it shows a formal relationship to the algorithm of Bell and Sejnowski (1995), and it suggests how to adapt parameters that were previously fixed.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7184
Date01 December 1996
CreatorsOlshausen, Bruno A.
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format5 p., 233466 bytes, 268006 bytes, application/postscript, application/pdf
RelationAIM-1580, CBCL-138

Page generated in 0.0019 seconds