论文信息 - TAGGING RARE EVENTS WITH SPARSELY ENCODED DATA

TAGGING RARE EVENTS WITH SPARSELY ENCODED DATA

I give a review of recent results obtained on the associative properties of a simple perceptron in the sparse coding limit : simple Hebbian rules allow to reach optimal or near optimal performances, and these performances may be obtained in the regime where the network makes errors.

Jean-Pierre Nadal

[1] Shun-ichi Amari,et al. Characteristics of sparsely encoded associative memory , 1989, Neural Networks.

[2] H. Horner. Neural networks with low levels of activity: Ising vs. McCulloch-Pitts neurons , 1989 .

[3] W. Krauth,et al. Storage capacity of memory networks with binary couplings , 1989 .

[4] H. C. LONGUET-HIGGINS,et al. Non-Holographic Associative Memory , 1969, Nature.

[5] G. Palm,et al. On associative memory , 2004, Biological Cybernetics.

[6] H. Gutfreund,et al. Capacity of neural networks with discrete synaptic couplings , 1990 .

[7] M. Tsodyks,et al. The Enhanced Storage Capacity in Neural Networks with Low Activity Level , 1988 .

[8] Günther Palm,et al. On the asymptotic information storage capacity of neural networks , 1988 .

[9] M. Tsodyks. Associative Memory in Asymmetric Diluted Network with Low Level of Activity , 1988 .

[10] D. Amit,et al. Optimised network for sparsely coded patterns , 1989 .

[11] J. Nadal,et al. Associative memory: on the (puzzling) sparse coding limit , 1991 .