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 Mφller's scaled conjugate gradient algorithm which is a variation of the traditional conjugate gradient method, better suited for the non-quadratic nature of neural networks. Different aspects of the implementation are discussed such as the efficient computation of gradients and multiplication by Hessian matrices that are required by Mφller's algorithm, and the stochastic (re)initialization of weights.
NEURBT: A Program for Computing Neural Networks for Classification using Batch Learning, NIST Interagency/Internal Report (NISTIR), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.IR.8037
(Accessed December 4, 2023)