论文信息 - Design of parallel distributed Cauchy machines

Design of parallel distributed Cauchy machines

A parallel and stochastic version of Hopfield-like neural networks is presented. Cauchy color noise is assumed. The specific noise is desirable for fast convergence to a fixed point representing a neighborhood minimum. It can be quickly quenched at each iteration according to a proven cooling schedule in generating random states on the energy landscape. An exact Cauchy acceptance criterion is analytically derived for hill-climbing capability. The improvement is twofold: a faster cooling schedule (the inversely linear cooling schedule characterized by the Cauchy simulated annealing) and parallel executions of all neurons. Such a Cauchy machine can be electronically implemented, and the design is given.<<ETX>>

Y. Takefuji | H. Szu | H. Szu | Yoshiyasu Takefuji

[1] C. D. Gelatt,et al. Optimization by Simulated Annealing , 1983, Science.

[2] Yutaka Akiyama,et al. Conductance Programmable Neural Chips Employing Switched Resistors , 1988 .

[3] H. Szu,et al. Fast TSP algorithm based on binary neuron output and analog neuron input using the zero-diagonal interconnect matrix and necessary and sufficient constraints of the permutation matrix , 1988, IEEE 1988 International Conference on Neural Networks.

[4] H. Szu,et al. Nonconvex optimization by fast simulated annealing , 1987, Proceedings of the IEEE.

[5] John J. Hopfield,et al. Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[6] Donald Geman,et al. Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.