On the capacity of ternary Hebbian networks

  • Authors:

  • Y. Baram

  • Affiliations:

  • Dept. of Comput. Sci., Technion-Israel Inst. of Technol., Haifa, Israel

  • Venue:
  • IEEE Transactions on Information Theory
  • Year:
  • 1991

Quantified Score

Hi-index 754.84

Visualization

Abstract

Networks of ternary neurons storing random vectors over the set (-1,0,1) by the so-called Hebbian rule are considered. It is shown that the maximal number of stored patterns that are equilibrium states of the network with probability tending to one as N tends to infinity is at least on the order of N2-1/ alpha /K, where N is the number of neurons, K is the number of nonzero elements in a pattern. and t= alpha K, 1/2