论文信息 - Learning and forgetting on asymmetric, diluted neural networks

Learning and forgetting on asymmetric, diluted neural networks

It is possible to construct diluted asymmetric models of neural networks for which the dynamics can be calculated exactly. We test several learning schemes, in particular, models for which the values of the synapses remain bounded and depend on the history. Our analytical results on the relative efficiencies of the various learning schemes are qualitatively similar to the corresponding ones obtained numerically on fully connected symmetric networks.

J. Nadal | B. Derrida

[1] J J Hopfield,et al. Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[2] Sompolinsky,et al. Storing infinite numbers of patterns in a spin-glass model of neural networks. , 1985, Physical review letters.

[3] Marc Mézard,et al. Solvable models of working memories , 1986 .

[4] Néstor Parga,et al. The ultrametric organization of memories in a neural network , 1986 .

[5] Stanislas Dehaene,et al. Networks of Formal Neurons and Memory Palimpsests , 1986 .

[6] P. Peretto,et al. Collective Properties of Neural Networks , 1986 .

[7] G. Parisi. A memory which forgets , 1986 .

[8] G. Parisi,et al. Asymmetric neural networks and the process of learning , 1986 .

[9] Françoise Fogelman-Soulié,et al. Disordered Systems and Biological Organization , 1986, NATO ASI Series.

[10] Sompolinsky,et al. Neural networks with nonlinear synapses and a static noise. , 1986, Physical review. A, General physics.

[11] E. Gardner,et al. An Exactly Solvable Asymmetric Neural Network Model , 1987 .