针对传统的ＢＰ或ＧＡ对模糊神经网络的识别应用存在收敛容易陷入局部极小 识别率低下等问题 提出一 种基于ＢＦＧＳ的混合遗传算法 其基本思想为 首先构造一种前馈型模糊神经网络结构 然后用遗传算法进化若干代 后 当目标函数的梯度或者范数小于预先设定值 则改用ＢＦＧＳ算法进行优化识别 仿真实验表明 对比ＧＡ该算法 收敛速度较快 识别精度提高了约７％ 能够较好地应用于一类模糊神经网络的识别-In traditional BP or GA to identify the application

在matlab软件中编程实现基于遗传算法优化BP神经网络非线性系统拟合算法-In the matlab software programming based on genetic algorithm to optimize the BP neural network nonlinear system fitting method

Introducing the rank-weight method into the basic ant colony optimization (ACO), we use the modified ACO to optimize the weights and thresholds value of neural networks (NN). And when the BPNN is being trained, this method can solve the disad

In this paper three different methods such as GDM AGDM and modified PSO are adopted to optimize the neural networks, and simulate the DTC system with MATLAB/SIMULINK. The result shows: modified PSO algorithm can solve the problem of neural n