Comparison Between Kanerva's SDM and Hopfield-Type Neural Networks

@article{Keeler1988ComparisonBK,
  title={Comparison Between Kanerva's SDM and Hopfield-Type Neural Networks},
  author={James D. Keeler},
  journal={Cognitive Science},
  year={1988},
  volume={12},
  pages={299-329}
}
The Sparse, Distributed Memory (SDM) model (Kanerva. 1984) is compared to Hopfield-type, neural-network models. A mathematical framework for cornporing the two models is developed, and the capacity of each model is investigated. The capacity of the SDM can be increased independent of the dimension of the stored vectors, whereas the Hopfield capacity is limited to a fraction of this dimension. The stored information is proportional to the number of connections, and it is shown that this… CONTINUE READING

From This Paper

Topics from this paper.
28 Citations
29 References
Similar Papers

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 29 references

Basins of Attraction of Neural Network Models

  • J. D. Keeler
  • 1986
Highly Influential
2 Excerpts

Infinite range models of spin - glasses

  • S. Kirkpatrick, D. Sherrington
  • Physicul Review B
  • 1988

The capacity of the Kanerva Associative Memory

  • P. A. Chou
  • 1988
1 Excerpt

Collective phenomena of coupled lattice maps : Reaction diffusion systems and neural networks

  • J. S. Denker, J. D. Keeler
  • 1987

Similar Papers

Loading similar papers…