Iterative methods for neural network design

Summary form only given, as follows. Three iterative algorithms for designing Hopfield neural networks were investigated: the relaxation method, the Cimino method, and the primal-dual method. All three algorithms arise from iterative methods for solving systems of linear inequalities. Convergence results were obtained for all three algorithms. In addition, this approach to neural network design is seen to be both natural and flexible: besides guaranteeing storage of memories whenever possible they can incorporate, into the design stage, a minimum radius of attraction, restricted connectivity, and regular network topologies. Statistical results were obtained to demonstrate these claims as well as to illustrate the near-optimal capacities of these algorithms.<>