Phase transitions in dilute, locally connected neural networks
Katherine J. Strandburg, Michael A. Peshkin, Daniel F. Boyd, Christopher Chambers, Brennan O’Keefe · Physical Review A · 1992
We report numerical studies of the ``memory-loss'' phase transition in Hopfield-like symmetric neural networks in which the neurons are connected to all other neurons within a local neighborhood (dense, short-range connectivity). The number of connections per neuron K scales as the number of neurons N raised to a power less than 1 (i.e., K\ensuremath{\sim}${\mathit{N}}^{\mathrm{\ensuremath{\eta}}}$, \ensuremath{\eta}1). We use the recently developed Lee-Kosterlitz finite-size scaling technique to determine the critical value of \ensuremath{\eta} below which the first-order phase transition disappears.