MAXIMALLY FAULT TOLERANT NEURAL NETWORKS

An application of neural network modeling is described for generating hypotheses about the relationships between response properties of neurons and information processing in the auditory system. Specifically, the goal is to study response properties that are useful for extracting sound localization information from directionally selective spectral filtering provided by the pinna. For studying sound localization based on spectral cues provided by the pinna, a feedforward neural network model with a guaranteed level of fault tolerance is introduced. The notions of fault tolerance and uniform fault tolerance in a neural network are formally defined and a method is described to ensure that the estimated network exhibits fault tolerance. The problem of estimating weights for such a network is formulated as a large-scale nonlinear optimization problem. Numerical experiments indicate that solutions with uniform fault tolerance exist for the pattern recognition problem considered in this paper. Furthermore, solutions derived by introducing fault tolerance constraints have better generalization properties than solutions obtained via unconstrained back-propagation.