Long-term attraction in higher order neural networks

  • Authors:
  • D. Burshtein

  • Affiliations:
  • Dept. of Electr. Eng., Tel Aviv Univ.

  • Venue:
  • IEEE Transactions on Neural Networks
  • Year:
  • 1998

Quantified Score

Hi-index 0.00

Visualization

Abstract

Recent results on the memory storage capacity of higher order neural networks indicate a significant improvement compared to the limited capacity of the Hopfield model. However, such results have so far been obtained under the restriction that only a single iteration is allowed to converge. This paper presents a indirect convergence (long-term attraction) analysis of higher order neural networks. Our main result is that for any κd