Simulated Annealing and Boltzmann Machines: A Stochastic Approach to Combinatorial Optimization and
Annealing is the physical process of heating up a solid until it melts, followed by careful cooling until it cristalyzes in a state corresponding to a perfect lattice. In combinatorial optimization a similar process can be defined and the resulting method is called simulated annealing. A substantial reduction of the computational effort required by the simulated annealing algorithm may be achieved by using computational models that are based on massively parallel execution. An example of such a model is the Boltzmann machine. A Boltzmann machine is thought to consist of a large network of simple computing elements, called units, that are connected in some way.
0コメント