Design of the fully connected binary neural network via linear programming

Moshe Kam, Jeng Chieh Chow, Robert Fischl

Research output: Contribution to journalConference articlepeer-review

8 Scopus citations

Abstract

An attempt is made to develop an alternative to the Hebbian-hypothesis-based design, using a powerful linear-programming (LP)-based algorithm. The LP-based algorithm attempts to build around each pattern to be stored a ball with a prespecified radius (in the Hamming distance sense) which is the ball of convergence for the pattern: when the network starts as one of the states in the ball, it will eventually converge to the central pattern. The Hopfield model and the sum-of-outer-products (SOOP) design are presented. Calculations are made of the radius of the balls of convergence for any given design. The LP-based algorithm is developed, and examples are presented demonstrating the advantages accrued for the network's retrieval capability through the LP algorithm.

Original languageEnglish (US)
Pages (from-to)1094-1097
Number of pages4
JournalProceedings - IEEE International Symposium on Circuits and Systems
Volume2
StatePublished - Dec 1 1990
Externally publishedYes
Event1990 IEEE International Symposium on Circuits and Systems Part 3 (of 4) - New Orleans, LA, USA
Duration: May 1 1990May 3 1990

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Design of the fully connected binary neural network via linear programming'. Together they form a unique fingerprint.

Cite this