Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
5500248 | Physica D: Nonlinear Phenomena | 2017 | 24 Pages |
Abstract
We first study the properties of the network activity depending on the distribution of synaptic weights and in particular its discrimination capacity. Then, we consider simple learning rules and determine the synaptic weight distribution it generates. We outline the role of noise as a selection principle and the capacity to memorize a learned signal.
Related Topics
Physical Sciences and Engineering
Mathematics
Applied Mathematics
Authors
Benoît Perthame, Delphine Salort, Gilles Wainrib,