Diluted neural networks with adapting and correlated synapses

Abstract

We consider the dynamics of diluted neural networks with clipped and adapting synapses. Unlike previous studies, the learning rate is kept constant as the connectivity tends to infinity: the synapses evolve on a time scale intermediate between the quenched and annealing limits and all orders of synaptic correlations must be taken into account. The dynamics is solved by mean-field theory, the order parameter for synapses being a function. We describe the effects, in the double dynamics, due to synaptic correlations.

6 pages, 3 figures. Accepted for publication in PRE

References in corpus (2)

• Coupled dynamics of fast spins and slow exchange interactions in the XY spin-glass
• Cluster derivation of Parisi's RSB solution for disordered systems

Cited by in corpus (2)

• Hierarchical Self-Programming in Recurrent Neural Networks
• Slowly evolving random graphs II: Adaptive geometry in finite-connectivity Hopfield models