Stochastic trapping in a solvable model of on-line independent component analysis
| dc.creator | Rattray, Magnus | |
| dc.date | 2001-05-03 | |
| dc.date.accessioned | 2026-07-07T02:41:17Z | |
| dc.date.available | 2026-07-07T02:41:17Z | |
| dc.description | Previous analytical studies of on-line Independent Component Analysis (ICA) learning rules have focussed on asymptotic stability and efficiency. In practice the transient stages of learning will often be more significant in determining the success of an algorithm. This is demonstrated here with an analysis of a Hebbian ICA algorithm which can find a small number of non-Gaussian components given data composed of a linear mixture of independent source signals. An idealised data model is considered in which the sources comprise a number of non-Gaussian and Gaussian sources and a solution to the dynamics is obtained in the limit where the number of Gaussian sources is infinite. Previous stability results are confirmed by expanding around optimal fixed points, where a closed form solution to the learning dynamics is obtained. However, stochastic effects are shown to stabilise otherwise unstable sub-optimal fixed points. Conditions required to destabilise one such fixed point are obtained for the case of a single non-Gaussian component, indicating that the initial learning rate ηrequired to successfully escape is very low (η= O(N^{-2}) where N is the data dimension) resulting in very slow learning typically requiring O(N^3) iterations. Simulations confirm that this picture holds for a finite system. | |
| dc.description | 17 pages, 3 figures. To appear in Neural Computation | |
| dc.identifier | https://arxiv.org/abs/cond-mat/0105057 | |
| dc.identifier | http://arxiv.org/abs/cond-mat/0105057 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/17684 | |
| dc.subject | Disordered Systems and Neural Networks | |
| dc.title | Stochastic trapping in a solvable model of on-line independent component analysis | |
| dc.type | text |