Optimal storage of a neural network model: a replica symmetry-breaking solution

Abstract
A break in replica symmetry is found above the critical line alpha c( kappa ) for storage with a finite minimal fraction of errors, within the first stage of the Parisi scheme, for noiseless networks with continuous synapses. The replica symmetry breaking solution yields the highest (most stable) minimal fraction of errors everywhere above alpha c( kappa ).

This publication has 10 references indexed in Scilit: