Perturbation method for deleting redundant inputs of perceptron networks

Abstract

Multilayer feedforward networks are often used for modeling complex functional relationships between data sets. Should a measurable redundancy in training data exist, deleting unimportant data components in the training sets could lead to smallest networks due to reduced-size data vectors. This reduction can be achieved by analyzing the total disturbance of network outputs due to perturbed inputs. The search for redundant input data components proposed in the paper is based on the concept of sensitivity in linearized models. The mappings considered are R I → R K with continuous and differentiable outputs. Criteria and algorithm for inputs' pruning are formulated and illustrated with examples.