Inhomogeneities in Heteroassociative Memories with Linear Learning Rules

@article{Sterratt2008InhomogeneitiesIH,
  title={Inhomogeneities in Heteroassociative Memories with Linear Learning Rules},
  author={David C. Sterratt and David J. Willshaw},
  journal={Neural Computation},
  year={2008},
  volume={20},
  pages={311-344}
}
We investigate how various inhomogeneities present in synapses and neurons affect the performance of feedforward associative memories with linear learning, a high-level network model of hippocampal circuitry and plasticity. The inhomogeneities incorporated into the model are differential input attenuation, stochastic synaptic transmission, and memories learned with varying intensity. For a class of local learning rules, we determine the memory capacity of the model by extending previous… CONTINUE READING
BETA

Citations

Publications citing this paper.
SHOWING 1-10 OF 10 CITATIONS

Efficient Associative Computation with Discrete Synapses

  • Neural Computation
  • 2016
VIEW 3 EXCERPTS
CITES RESULTS & BACKGROUND
HIGHLY INFLUENCED

Optimal synaptic learning in non-linear associative memory

  • The 2010 International Joint Conference on Neural Networks (IJCNN)
  • 2010
VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND

Zip nets: Efficient associative computation with binary synapses

  • The 2010 International Joint Conference on Neural Networks (IJCNN)
  • 2010
VIEW 2 EXCERPTS
CITES METHODS & BACKGROUND

Memory stability and synaptic plasticity

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS

Optimal Learning Rules for Discrete Synapses

  • PLoS Computational Biology
  • 2008
VIEW 2 EXCERPTS
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 62 REFERENCES

Optimising synaptic learning rules in linear associative memories

  • Biological Cybernetics
  • 1991
VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

On the asymptotic information storage capacity of neural networks

G. Palm
  • Neural computers (pp. 271–280)
  • 1988
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…