论文部分内容阅读
详细介绍了CMAC神经网络结构、中间层作用函数地址的计算方法、输出层权值的学习算法，并利用CMAC神经网络对水下机器人深度模糊控制器进行了学习。仿真结果表明，训练得到的CMAC神经控制器控制效果良好，中间层作用函数地址的计算方法正确。
The CMAC neural network structure, the calculation method of the middle layer function address and the learning algorithm of the output layer weight are introduced in detail. The CMAC neural network is used to study the underwater robot fuzzy controller. The simulation results show that the trained CMAC neural controller has a good control effect and the calculation of the middle layer function address is correct.