Neural Networks, IEEE - INNS - ENNS International Joint Conference on
Download PDF

Abstract

We analyze the effects of synaptic depression on the stability of patterns stored in neural networks with low activity level. Applying mean-field theory, we show that the stationary states remain unaffected by the synaptic depression. However, the stability of memory patterns changes drastically causing a reduction of memory capacity. Further, it is demonstrated and confirmed by numerical calculations that the sensitivity of the network to input changes is enhanced.
Like what you’re reading?
Already a member?
Get this article FREE with a new membership!