A METHOD TO REDUCE REDUNDANT HIDDEN NODES

The number of nodes in a hidden layer of a feed-forward layered networ k reflects an optimality condition of the network in coding a function . It also affects the computation time and the ability of the network to generalize. When an arbitrary number of hidden nodes is used in des igning the network, redundancy of hidden nodes often can be seen. In t his paper, a method of reducing hidden nodes is.proposed on the condit ion that a reduced network maintains the performances of the original network within an accepted level of tolerance. This method can be appl ied to estimate the performances of a network with fewer hidden nodes. The estimated performances indicate the lower bounds of the actual pe rformances of the network. Experiments were performed using the Fisher 's IRIS data, a set of SONAR data, and the XOR data for classification . The results suggest that sufficient number of hidden nodes, fewer th an the original number, can be estimated by the proposed method.