Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

September 1, 2003, Vol. 15, No. 9, Pages 2147-2177
(doi: 10.1162/089976603322297331)
© 2003 Massachusetts Institute of Technology
Slow Feature Analysis: A Theoretical Analysis of Optimal Free Responses
Article PDF (378.12 KB)
Abstract

Temporal slowness is a learning principle that allows learning of invariant representations by extracting slowly varying features from quickly varying input signals. Slow feature analysis (SFA) is an efficient algorithm based on this principle and has been applied to the learning of translation, scale, and other invariances in a simple model of the visual system. Here, a theoretical analysis of the optimization problem solved by SFA is presented, which provides a deeper understanding of the simulation results obtained in previous studies.