Annealing by Perturbing Synapses

Shiao-Lin LIN  Jiann-Ming WU  Cheng-Yuan LIOU  

IEICE TRANSACTIONS on Information and Systems   Vol.E75-D   No.2   pp.210-218
Publication Date: 1992/03/25
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Bio-Cybernetics
bio-cybernetics,  artificial intelligence and cognitive science,  neural network,  Hopfield model,  simulated annealing,  optimization,  

Full Text: PDF>>
Buy this Article

By close analogy of annealing for solids, we devise a new algorithm, called APS, for the time evolution of both the state and the synapses of the Hopfield's neural network. Through constrainedly random perturbation of the synapses of the network, the evolution of the state will ignore the tremendous number of small minima and reach a good minimum. The synapses resemble the microstructure of a network. This new algorithm anneals the microstructure of the network through a thermal controlled process. And the algorithm allows us to obtain a good minimum of the Hopfield's model efficiently. We show the potential of this approach for optimization problems by applying it to the will-known traveling salesman problem. The performance of this new algorithm has been supported by many computer simulations.