• Publications
  • Influence
Neural network design
This book, by the authors of the Neural Network Toolbox for MATLAB, provides a clear and detailed coverage of fundamental neural network architectures and learning rules, as well as methods for training them and their applications to practical problems.
Neutral network toolbox for use with Matlab
This research presents a meta-modelling framework that automates the very labor-intensive and therefore time-heavy and expensive and therefore expensive and expensive process of manually cataloging and updating reference records for this type of research.
A procedure for training recurrent networks
A batch training method based on a modified version of the Levenberg-Marquardt algorithm that uses the information of gradients of individual sequences to mitigate the effect of spurious valleys in the error surface of recurrent networks.
Identification of the connections in biologically inspired neural networks
An identification method to find the strength of the connections between neurons from their behavior in small biologically-inspired artificial neural networks, given the network external inputs and the temporal firing pattern of the neurons, which determines directly if there is a solution to a particular neural network problem.