Generalization properties of multilayered neural networks
- 7 October 1992
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 25 (19) , 5047-5054
- https://doi.org/10.1088/0305-4470/25/19/017
Abstract
Generalization properties of multilayered neural networks with binary couplings are studied in the high-temperature limit. The transition to the perfect generalization phase is evaluated for systems with an arbitrary number of layers. It is found that the thermodynamic transition occurs for a number of examples lower than for the perceptron, but the opposite occurs for the transition in which the poor generalization solution disappears. The generalization error is also decomposed according to the contributions coming from different numbers of hidden neurons that have a wrong sign in the internal field. This allows the authors to describe the generalization behaviour of the hidden neurons.Keywords
This publication has 10 references indexed in Scilit:
- Storage Capacity of a Multilayer Neural Network with Binary WeightsEurophysics Letters, 1991
- 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
- Statistical mechanics of a multilayered neural networkPhysical Review Letters, 1990
- Learning from examples in large neural networksPhysical Review Letters, 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
- The space of interactions in neural network modelsJournal of Physics A: General Physics, 1988
- Learning Networks of Neurons with Boolean LogicEurophysics Letters, 1987
- Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern RecognitionIEEE Transactions on Electronic Computers, 1965