Many-body approach to the dynamics of batch learning
arXiv:cond-mat/9909004 · doi:10.1103/PhysRevE.62.4036
Abstract
Using the cavity method and diagrammatic methods, we model the dynamics of batch learning of restricted sets of examples, widely applicable to general learning cost functions, and fully taking into account the temporal correlations introduced by the recycling of the examples.
4 pages
Cited by in corpus (4)
- Eigenvalue spectrum of neural networks with arbitrary Hebbian length
- Supervised Learning with Restricted Training Sets: a Generating Functional Analysis
- Dynamical and Stationary Properties of On-line Learning from Finite Training Sets
- Dynamics of on-line Hebbian learning with structurally unrealizable restricted training sets