Temporal Association in Asymmetric Neural Networks

Haim Sompolinsky, Ido Kanter

Physical Review Letters · 1986 · 575 citations · 6 references

Concepts

TL;DR

The model may also help explain rhythmic pattern generation in biological motor systems. The study introduces a neural network capable of recalling time sequences and cycles of patterns. The network uses asymmetric, slowly adapting synaptic connections and incorporates thermal noise to generate sequences. Simulations demonstrate the network’s ability to produce and recall temporal patterns.

Abstract

A neural network model which is capable of recalling time sequences and cycles of patterns is introduced. In this model, some of the synaptic connections, ${J}_{\mathrm{ij}}$, between pairs of neurons are asymmetric (${J}_{\mathrm{ij}}\ensuremath{\ne}{J}_{\mathrm{ji}}$) and have slow dynamic response. The effects of thermal noise on the generated sequences are discussed. Simulation results demonstrating the performance of the network are presented. The model may be also useful in understanding the generation of rhythmic patterns in biological motor systems.

References

6