Storage capacity and dynamics of nonmonotonic networks

Abstract

This work investigates the retrieval capacities of di erent types of nonmonotonic neurons. Storage capacity is maximized when the neuron response is a function with well de ned geometrical characteristics. Numerical experiments demonstrate that storage capacity is directly related to the dynamical property of the iterative map that describes the network evolution. Maximum capacity is reached when the neuron dynamics are subdivided into two non-overlapping \erratic bands" around points xi = 1.

Extracted Key Phrases

4 Figures and Tables

Cite this paper

@inproceedings{Crespi1999StorageCA, title={Storage capacity and dynamics of nonmonotonic networks}, author={Bruno Crespi and Ignazio Lazzizzera}, booktitle={ESANN}, year={1999} }