NEURBT: A Program for Computing Neural Networks for Classification using Batch Learning

NEURBT, a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. NEURBT is based on Møller’s scaled conjugate gradient algorithm which is a variation of the traditional conjugate gradient method, better suited for the nonquadratic nature of neural networks. Different aspects of the imple­ mentation are discussed such as the efficient computation of gradients and multiplication of vectors by Hessian matrices that are required by Møller’s algorithm, and the stochastic (re)initialization of weights.