论文信息 - Prototype extraction in material attractor neural networks with stochastic dynamic learning

Prototype extraction in material attractor neural networks with stochastic dynamic learning

Dynamic learning of random stimuli can be described as a random walk among the stable synaptic values. It is shown that prototype extraction can take place in material attractor neural networks when the stimuli are correlated and hierarchically organized. The network learns a set of attractors representing the prototypes in a completely unsupervised fashion and is able to modify its attractors when the input statistics change. Learning and forgetting rates are computed.

Stefano Fusi | Stefano Fusi

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

[2] M. A. Moore,et al. Neural network models of list learning , 1991 .

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

[4] Nicolas Brunel,et al. Learning internal representations in an attractor neural network with analogue neurons , 1995 .

[5] D. Amit,et al. Constraints on learning in dynamic synapses , 1992 .

[6] D Sherrington,et al. A neural network model of working memory exhibiting primacy and recency , 1991 .

[7] Daniel J. Amit,et al. Learning in Neural Networks with Material Synapses , 1994, Neural Computation.

[8] J AmitDaniel,et al. Learning in neural networks with material synapses , 1994 .