Yoshio Izui, Alex Pentland

Abstract

Biological systems have a large degree of redundancy, a fact that is usually thought to have little effect beyond providing reliable function despite the death of individual neurons. We have discovered, however, that redundancy can qualitatively change the computations carried out by a network. We prove that for both feedforward and feedback networks the simple duplication of nodes and connections results in more accurate, faster, and more stable computation.