Kym. Wong et al., ORDER-PARAMETER EVOLUTION IN A FEEDFORWARD NEURAL-NETWORK, Journal of physics. A, mathematical and general, 28(6), 1995, pp. 1603-1614
We consider layered neural networks in which the weights are trained w
ith the pseudoinverse rule to store a set of random patterns. Using ma
ny-body diagrammatic techniques, the evolution in the network can be d
escribed by the overlap order parameter m and the noise parameter Delt
a. Looping effects are shown to be significant, in contrast to a previ
ous conjecture. Order parameter pairs corresponding to various input c
onditions are found to collapse on a universal curve.