机构地区: 中国传媒大学南广学院信息技术系
出 处: 《电子技术应用》 2009年第7期91-94,共4页
摘 要: 采用遗传学习算法和误差反向传播(BP)算法相结合的混合算法来训练前馈人工神经网络,从而提高神经网络的收敛质量和收敛速度,并将此算法运用到电子舌对黄酒的检测上。与经典BP网络及附加动量项BP网络的训练与预测进行了比较。结果显示:遗传优化BP算法具有预测精度高、收敛速度快及运行时间短的优点,是一种快速、可靠的方法。 The combination of genetic algorithm and back propagation algorithm for training the neural network is described. It can improve the search efficiency and realize global optimization, and this GA-BP algorithm is employed to detect the rice wine by electronic tongue. Compared with the standard back propagation algorithm and its improved method, the result shows the GA-BP algorithm has better prediction precision, higher convergent speed and less running time, and it is a fast and credible method.
领 域: [自动化与计算机技术] [自动化与计算机技术]