Paralleled hardware annealing for optimal solutions on electronic neural networks
- 1 July 1993
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 4 (4) , 588-599
- https://doi.org/10.1109/72.238314
Abstract
Three basic neural network schemes have been extensively studied by researchers: the iterative networks, the backpropagation networks, and the self-organizing networks. Simulated annealing is a probabilistic hill-climbing technique that accepts, with a nonzero but gradually decreasing probability, deterioration in the cost function of the optimization problems. Hardware annealing, which combines the simulated annealing technique with continuous-time electronic neural networks by changing the voltage gain of neurons, is discussed. The initial and final voltage gains for applying hardware annealing to Hopfield data-conversion networks are presented. In hardware annealing, the voltage gain of output neurons is increased from an initial low value to a final high value in a continuous fashion which helps to achieve the optimal solution for an optimization problem in one annealing cycle. Experimental results on the transfer function and transient response of electronic neural networks achieving the global minimum are also presented.Keywords
This publication has 29 references indexed in Scilit:
- A Cascadable Neural Network Chip Set With On-chip Learning Using Noise And Gain AnnealingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- An analog neural network processor for self-organizing mappingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A neural architecture for the assignment problem: simulation and VLSI implementationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Mean field annealing: a formalism for constructing GNC-like algorithmsIEEE Transactions on Neural Networks, 1992
- A reconfigurable VLSI neural networkIEEE Journal of Solid-State Circuits, 1992
- An Analog Neural Network Processor With Programmable Network TopologyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- An MOS transistor charge model for VLSI designIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 1988
- BSIM: Berkeley short-channel IGFET model for MOS transistorsIEEE Journal of Solid-State Circuits, 1987
- Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuitIEEE Transactions on Circuits and Systems, 1986
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984