A neural network for Euclidean distance minimization

Abstract

An electronic neural network, implemented in VLSI-based hardware, for the Euclidean distance minimization problem is described. The convergence properties of the neural network hardware are investigated and compared with computer simulation results.The neural network's ability to quickly find the ltbestll or a agoodtv solution is demonstrated.The effect of noise on the circuit dynamics and the convergence behavior of the neural network hardware is also examined.