EXTRACTING MORE INFORMATION FROM DYNAMICS IN NEURAL NETWORKS
K. Y. Michael Wong · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · 1993
I propose tools to probe the nature of the retrieval attractors in neural networks. These include the activity distribution, the evolutions of the state damage, activity damage and temporal correlation damage. They enable us to demonstrate that the retrieval attractors in dilute asymmetric neural networks are not clouds of attractors, but consist of a single chaotic attractor for each stored pattern. Furthermore, they facilitate the devise of effective freezing procedures, which significantly improve the quality of retrieval in both dilute asymmetric and layered neural networks.