The retrieval phase of the Hopfield model: A rigorous analysis of the overlap distribution
- Bovier, Anton
- Gayrard, Véronique
2010 Mathematics Subject Classification
- 60K35 82C32 82B44
- Hopfield model, neural networks, storage capacity, Gibbs measures, self-averaging, random matrices
Standard large deviation estimates or the use of the Hubbard-Stratonovich transformation reduce the analysis of the distribution of the overlap parameters essentially to that of an explicitly known random function ΦN,β on ℝM. In this article we present a rather careful study of the structure of the minima of this random function related to the retrieval of the stored patterns. We denote by m* (β) the modulus of the spontaneous magnetization in the Curie-Weiss model and by α the ratio between the number of the stored patterns and the system size. We show that there exist strictly positive numbers 0 < γα < γc such that 1) If √α ≤ γα (m*(β))2, then the absolute minima Φ are located within small balls around the points ±m*eµ , where eµ denotes the µ-th unit vector while 2) if √α ≤ γc (m*(β))2 at least a local minimum surrounded by extensive energy barriers exists near these points. The random location of these minima is given within precise bounds. These are used to prove sharp estimates on the support of the Gibbs measures.
- Probab. Theory Related Fields, 107 (1997), pp. 61-98