Active Training of Backpropagation Nerual Networds Using the Learning by Experimentation Methodology

Abstract

This paper proposes the learning by experimentation methodology (LEM) to facilitate the active training of neural networks. In an active learning paradigm, a learning mechanism can actively interact with its environment to acquire new knowledge and revise it. The learning by experimentation is an active learning strategy. Experiments are conducted to form the hypotheses, and the performance of those hypotheses feeds back to the learning mechanism to revise knowledge. We use a backpropagation neural network as the learning mechamism. We also adopt a weight space analysis method and a heuristic to select salient attributes to perform new experiments in order to revise the network.