Symbolic approximation of feedforward networks (original) (raw)

Abstract

Multiple layer f eedforward n eural networks are often v iewed as black box es as the knowledge stored in the c onnection weights of these networks is generally considered incomprehensible. This paper suggests a solution to this deficiency o f neural networks by proposing a backtracking tree search procedure for converting the weights of a neuron into a symbolic representation and demonstrating its use for understanding and symbolic approximation of feedforward neural networks. Several examples are presented to illustrate the proposed symbolic mapping of neurons.

Ishwar Sethi hasn't uploaded this paper.

Let Ishwar know you want this paper to be uploaded.

Ask for this paper to be uploaded.