Prototype Extraction in Material Attractor Neural Network with Stochastic Dynamic Learning

@inproceedings{Elena1995PrototypeEI,
  title={Prototype Extraction in Material Attractor Neural Network with Stochastic Dynamic Learning},
  author={Regina Elena},
  year={1995}
}
  • Regina Elena
  • Published 1995
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. 
5 Citations
5 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-5 of 5 references

Constraints on learning in dynamic synapses

  • J. AmitD.
  • 1992

A neural network model of working memory exhibitingprimacy and recency

  • M. WongK.Y., E. KahnP., D Sherrington
  • J . Phys A
  • 1991

A memory which forgets

  • N. Burgess, L. ShapiroJ., A. MooreM.
  • J . Phys , A
  • 1986

Networks of formal neurons and memorypalimpses

  • G Parisi
  • 1986

Scaling laws for the attractors of Hop eld model

  • J. AmitD., N. Brunel
  • J . Physique Lett .
  • 1985

Similar Papers

Loading similar papers…