论文信息 - Analytical and numerical study of internal representations in multilayer neural networks with binary weights.

Analytical and numerical study of internal representations in multilayer neural networks with binary weights.

We study the weight space structure of the parity machine with binary weights by deriving the distribution of volumes associated to the internal representations of the learning examples. The learning behavior and the symmetry breaking transition are analyzed and the results are found to be in very good agreement with the extended numerical simulations. @S1063-651X~96!01207-X#

Monasson | Zecchina | Cocco

[1] M. Mézard,et al. Spin Glass Theory and Beyond , 1987 .

[2] Anders Krogh,et al. Introduction to the theory of neural computation , 1994, The advanced book program.

[3] Riccardo Zecchina,et al. Learning and Generalization Theories of Large Committee-Machines , 1995, cond-mat/9601122.

[4] Andreas Engel. Correlation of internal representations in feed-forward neural networks , 1996 .