基于动态距离寻优的遗传神经网络优化算法

Genetic Neural Network Optimization Algorithm Based on Dynamic Distance Optimization

针对BP神经网络算法存在收敛速度慢,易陷入局部极小值的缺陷,导致应用效果差,错误率高的问题,利用遗传算法全局搜索能力强的优点对BP神经网络的缺陷进行改进,提出一种基于动态距离寻优的遗传神经网络优化算法。采用BP神经网络构建信道分类器,通过动态距离的观点对遗传算法优化,增强寻优能力,消除计算中的模糊性和不确定性,对神经网络权值实现优化,最终完成算法优化平衡。仿真结果表明,相对于传统遗传优化BP神经网络算法,改进算法收敛速度快,应用的误码率降低,获得更好的收敛特性和均衡效果。

According to the BP neural network algorithm slow convergence speed, easy to fall into local minimum value, lead to poor application effect, the error rate is high. In order to overcome the defects of BP neural network, the use of the advantages of strong global search ability of genetic algorithm to improve the defects of BP neural network, this paper puts forward a distance based on dynamic optimization genetic neural network optimization algorithm. By using BP neural network classifier constructed channel, through the dynamic of the distance from the point of view of genetic algorithm （ga） optimization, enhance optimization ability, eliminate, fuzziness and uncertainty in the calculation of the weights of neural network to realize the optimization, the final algorithm. Simulation results show that compared with the traditional genetic algorithm to optimize the BP neural network, change the algnrithm convergence speed, the application of the lower ber, get better convergence properties and balanced.