Logo image
Design of the fully connected binary neural network via linear programming
Conference proceeding

Design of the fully connected binary neural network via linear programming

M Kam, J.-C Chow and R Fischl
1990 IEEE International Symposium on Circuits and Systems (ISCAS), pp 1094-1097 vol.2
1990

Abstract

Algorithm design and analysis Associative memory Convergence Linear programming Neural networks Pattern recognition Robustness Stability Stochastic processes Symmetric matrices
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.< >

Metrics

9 Record Views

Details

Logo image