Pruning Strategies for the MTiling Constructive Learning Algorithm

We present a framework for incorporating pruning strategies in the MTiling constructive neural network learn-ing algorithm. Pruning involves elimination of redundant elements (connection weights or neurons) from a network and is of considerable practical interest. We describe three elementary sensitivity based strategies for pruning neurons. Experimental results demonstrate a moderate to significant reduction in the network size without compromising the net-work’s generalization performance. 1