arXiv · cond-mat/9601122
Learning and generalization theories of large committee--machines
Abstract
The study of the distribution of volumes associated to the internal representations of learning examples allows us to derive the critical learning capacity ($α_c=\frac{16}π \sqrt{\ln K}$) of large committee machines, to verify the stability of the solution in the limit of a large number $K$ of hidden units and to find a Bayesian generalization cross--over at $α=K$.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Remi Monasson, Riccardo Zecchina. 1996-01-25. Learning and generalization theories of large committee--machines. https://arxiv.org/abs/cond-mat/9601122
Cite the original work for its findings. Save a collection to share your selection of sources.