Robustness analysis and design of a class of neural networks with sparse interconnecting structure
Derong Liu, Anthony N. MICHEL · Neurocomputing · 1996
We first conduct an analysis of the robustness properties of a class of neural networks with applications to associative memories. Specifically, for a network with nominal parameters which stores a set of desired bipolar memories, we establish sufficient conditions under which the same set of bipolar memories is also stored in the network with perturbed parameters. This result enables us to establish a synthesis procedure for neural networks whose stored memories are invariant under perturbations. Our synthesis procedure is capable of generating artificial neural networks with prespecified sparsity constraints (on the interconnecting structure) and with nonsymmetric and symmetric interconnection matrices. To demonstrate the applicability of the present results, we consider several specific examples.