Self-organized annealing in laterally inhibited neural networks shows power law decay
| dc.creator | Emmert-Streib, Frank | |
| dc.date | 2004-01-30 | |
| dc.date | 2005-07-15 | |
| dc.date.accessioned | 2026-07-07T02:56:12Z | |
| dc.date.available | 2026-07-07T02:56:12Z | |
| dc.description | In this paper we present a method which assigns to each layer of a multilayer neural network, whose network dynamics is governed by a noisy winner-take-all mechanism, a neural temperature. This neural temperature is obtained by a least mean square fit of the probability distribution of the noisy winner-take-all mechanism to the distribution of a softmax mechanism, which has a well defined temperature as free parameter. We call this approximated temperature resulting from the optimization step the neural temperature. We apply this method to a multilayer neural network during learning the XOR-problem with a Hebb-like learning rule and show that after a transient the neural temperature decreases in each layer according to a power law. This indicates a self-organized annealing behavior induced by the learning rule itself instead of an external adjustment of a control parameter as in physically motivated optimization methods e.g. simulated annealing. | |
| dc.description | 10 pages, 4 figures | |
| dc.identifier | https://arxiv.org/abs/cond-mat/0401633 | |
| dc.identifier | http://arxiv.org/abs/cond-mat/0401633 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/23228 | |
| dc.subject | Disordered Systems and Neural Networks | |
| dc.title | Self-organized annealing in laterally inhibited neural networks shows power law decay | |
| dc.type | text |