Capacity of neural networks with discrete synaptic couplings

@inproceedings{Gutfreund2001CapacityON,
  title={Capacity of neural networks with discrete synaptic couplings},
  author={Hanoch Gutfreund},
  year={2001}
}
We study the optimal storage capacity of neural networks with discrete local constraints on the synaptic couplings J,,. Models with such constraints inlcude those with binary couplings J,, = i l or J,, = 0, 1, quantised couplings with larger synaptic range, e.g. J,, = *l/L, *2/ L, . . . , *1 and, in the limit, continuous couplings confined to the hypercube l J 8 , 1 s 1 (‘box confinement’). We find that the optimal storage capacity ( Y ( K ) is best determined by the vanishing of a suitably… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-10 of 18 extracted citations

References

Publications referenced by this paper.

Principles o j Neurodynamics (New York: Spartan Books

  • F Rosenblatt
  • 1962
2 Excerpts

Similar Papers

Loading similar papers…