Generalization transitions in hidden-layer neural networks for third-order feature discrimination
Open Access
- 1 March 1993
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 47 (3) , 2162-2171
- https://doi.org/10.1103/physreve.47.2162
Abstract
Stochastic learning processes for a specific feature detector are studied. This technique is applied to nonsmooth multilayer neural networks requested to perform a discrimination task of order 3 based on the ssT-block–ssC-block problem. Our system proves to be capable of achieving perfect generalization, after presenting finite numbers of examples, by undergoing a phase transition. The corresponding annealed theory, which involves the Ising model under external field, shows good agreement with Monte Carlo simulations.Keywords
This publication has 9 references indexed in Scilit:
- Generalization of Rules by Neural NetsEurophysics Letters, 1992
- GENERALIZATION ERROR AND DYNAMICAL EFFECTS IN A TWO-DIMENSIONAL PATCHES DETECTORInternational Journal of Neural Systems, 1991
- Learning in a Two-Layer Neural Network of Edge DetectorsEurophysics Letters, 1990
- Learning from examples in large neural networksPhysical Review Letters, 1990
- First-order transition to perfect generalization in a neural network with binary synapsesPhysical Review A, 1990
- Learning from Examples in a Single-Layer Neural NetworkEurophysics Letters, 1990
- Three unfinished works on the optimal storage capacity of networksJournal of Physics A: General Physics, 1989
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- Applications of the Monte Carlo Method in Statistical PhysicsPublished by Springer Nature ,1984