In search of an optimal dilution algorithm for feedforward networks

Abstract

In a recent paper the authors presented a dilution algorithm that yields a storage capacity per synapse alpha eff larger than 2. In this letter, two new algorithms with even higher alpha eff values are introduced. They study a one-step dilution algorithm, where the perceptron is used to select a fraction of the couplings to be removed. For the remaining bonds the perceptron of optimal stability is relearned. They further compare simulation data from an iterative version of the one-step dilution algorithm with phase-space volume calculations.