Boltzmann machine optimization based on genetic algorithm
Yao Shu-kui · Computer Engineering and Applications Journal · 2011
Boltzmann machine is widely used in stochastic neural networks.It can obtain the global optimum or a near-optimal solution by network learning based on simulated annealing.Compared the expectations of the network model with the actual learning of the network model to adjust the weights of the network,so that the network can be as much as possible to meet or close to the desired network model.This genetic algorithm is applied to the learning of the Boltzmann machine,which can change the network weights through the competitive selection genetic algorithm optimizing operation,so that the network can achieve the desired pattern.An example proves that this is a simple and practical way to adjust the network weights.