Statistical mechanics of temporal association in neural networks with delayed interactions
Andreas V. M. Herz, Li Zhaoping, J. Leo van Hemmen · Neural Information Processing Systems · 1990
We study the representation of static patterns and temporal associations in neural networks with a broad distribution of signal delays. For a certain class of such systems, a simple intuitive understanding of the spatio-temporal computation becomes possible with the help of a novel Lyapunov functional. It allows a quantitative study of the asymptotic network behavior through a statistical mechanical analysis. We present analytic calculations of both retrieval quality and storage capacity and compare them with simulation results.