Storage capacity of non-monotonic neurons.

Crespi, B · Neural Netw · 1999

basic_science · Level V

Where this comes from

Abstract

Non-monotonic neurons have been shown to enhance the storage capacity of auto-associative memories. This work investigates the retrieval capacities of different types of non-monotonic neurons. It is found that storage capacity is maximized when the neuron response is a function with well defined geometrical characteristics. Numerical experiments demonstrate that storage capacity is directly related to the dynamical property of the iterative map, x(i)-->g( summation operator jT(ij)x(j)), that describes the network evolution. Maximum capacity is reached when the neuron dynamics are subdivided into two non-overlapping "erratic bands" around points x(i)=+/-1. The capacity improvements are explained in terms of the energy function associated with the network dynamics.