Symposium on Artificial Intelligence and Signal Processing (AISP) 2013

Keynote Speaker

Professor Abbas Edalat

Professor of Computer Science and Mathematics

Department of Computing
Imperial College London




Square law of attraction for strong patterns of Hopfield networks to model behavioural prototypes and psychotherapy



I will introduce the notion of strong, i.e., multiply learned, patterns in Hopfield networks and show that strong patterns have a large basin of attraction and their retrieval capacity, in the presence of simple patterns, rises proportional to the square of their degree or multiplicity. This square law of attraction, which is rigorously proved by solving the mean field equations for the stochastic Hopfield networks, enables us to use strong patterns to model cognitive and behavioural prototypes as well as attachment types in developmental psychology. Psychotherapy of an individual can then be modelled, at its most basic level, as the learning of a new strong pattern whose degree eventually exceeds that of the strong pathological neural pattern learned earlier in life. Finally I will explain how this neural model has motivated the development of the self-attachment protocol, a new and integrative psychotherapeutic method, which in a small number of case studies so far has shown to be more effective than current available techniques.