Parallel Neural Network Training
Ed P. Andert, Thomas J. Bartolac · 1993
Our neural network training approach produces networks that are superior to the limited accuracy of typical connectionist applications. The approach addresses function complexity, network capacity, and training algorithm aggressiveness. Symbolic computing tools are used to develop algebraic representations for the gradient and Hessian of the least-squares cost functions for feed-forward network topologies, with fully~ected and locally-connected layers. These representations are then transformed into block-structured form. They are then integrated with a full-Newton network training algorithm and executed on vector/parallel computers.