Storage capacity of the fully-connected committee machine

Journal of Physics A: Mathematical and General

Volumn 30, Issue 11, 1997, Pages

  Urbanczik, R ^a  

^a UNIVERSITY OF WÜRZBURG   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0039325414     PISSN: 03054470     EISSN: None     Source Type: Journal    
DOI: 10.1088/0305-4470/30/11/007     Document Type: Article

References (10)

1. Barkai E, Hansel D and Kanter 1990 Statistical mechanics of a multilayered neural network Phys. Rev. Lett. 65 2312-15
2. Barkai E, Hansel D and Sompolinsky H 1992 Broken symmetries in multilayered perceptrons Phys. Rev. A 45 4146-61
3. Engel A, Köhler H M, Tschepke F, Vollmayr H and Zippelius A 1992 Storage capacity and learning algorithms for two layer neural networks. Phys. Rev. A 45 7590-607
4. Opper M 1994 Learning and generalization in a two-layer neural network: the role of the Vapnik-Chervonenkis dimension Phys. Rev. Lett. 72 2113-16
5. Schwarze H 1993 Learning a rule in a multilayer neural network J. Phys. A: Math. Gen. 26 5781-94
6. Monasson R and Zecchina R 1995 Weight space structure and internal representations: a direct approach to learning and generalization in multilayer neural networks Phys. Rev. Lett. 75 2432-5
7. Monasson R and Zecchina R 1996 Learning and generalization theories of large committee machines Mod. Phys. Lett. B 9 1887-97
8. Kwon C, Park Y and Oh J 1995 Storage capacity of a fully connected committee machine Neural Networks: The Statistical Mechanics Perspective ed J Oh, C Kwon and S Cho et al (Singapore: World Scientific) pp 191-7
9. Urbanczik R 1995 A fully connected committee machine learning unrealizable rules J. Phys. A: Math. Gen. 28 7097-104
10. Urbanczik R 1996 A large committee machine learning noisy rules Neural Comput. 8 1267-76