POTENTIAL FUNCTION-BASED NEURAL NETWORKS AND ITS APPLICATION TO THE CLASSIFICATION OF COMPLEX CHEMICAL-PATTERNS

A new neural network (NN) using potential function (PF); named PFNN, i s proposed for classifying the complex chemical patterns. Correspondin gly, a new algorithm called the '' + delta'' algorithm is proposed to train the networks. With a benchmark classification problem the conven tional multilayer feedforward (MLF) neural networks is tested and comp ared with PFNN. Furthermore, the experiments on classifying complex ch emical patterns are performed. The results of these experiments demons trate that PFNN is good in dealing with classification due to its prec iseness and quickness. (C) 1998 Elsevier Science Ltd. All rights reser ved.