Description: 由于BP网络的权值优化是一个无约束优化问题，而且权值要采用实数编码，所以直接利用Matlab遗传算法工具箱。以下贴出的代码是为一个19输入变量，1个输出变量情况下的非线性回归而设计的，如果要应用于其它情况，只需改动编解码函数即可。
-As a result of BP network weights optimization is a constrained optimization problems, and weights to be used real-coded, so the direct use of Matlab genetic algorithm toolbox. Posted the following code is for a 19 input variables, an output variable in case of non-linear regression designed, if applied to other situations, simply change your codec function. Platform: |
Size: 2048 |
Author:王刚 |
Hits:
Description: 本源码是一个用Matlab7.1实现的BP网络的源代码
，他实现了基本的BP网络算法。-The source is a Matlab7.1 achieved using BP network s source code, he realized the basic BP network algorithm. Platform: |
Size: 1024 |
Author:耿世 |
Hits:
Description: 用BP神经网络实现模糊控制规则为T=int[(e
+ec)/2]的模糊神经网络控制器。可以改变隐层节点数和学习速率。网络训练算法是变学习速率法。-BP neural network with fuzzy control rules for the T = int [(e+ Ec)/2] of the fuzzy neural network controller. Can change the hidden layer nodes and learning rate. Network training algorithm is a variable learning rate method. Platform: |
Size: 4096 |
Author:韩梅 |
Hits:
Description: 几个BP神经网络程序，运用不同的算法训练网络-Several BP neural network procedure, using a different algorithm training network Platform: |
Size: 5120 |
Author:许翔 |
Hits:
Description: 基于随机梯度下降法的两层sigmoid神经元的BP算法-Stochastic gradient descent method based on two layers of sigmoid neurons in the BP algorithm Platform: |
Size: 1024 |
Author:songmin |
Hits:
Description: MATLAB neural network backprop code
This code implements the basic backpropagation of
error learning algorithm. The network has tanh hidden
neurons and a linear output neuron.
adjust the learning rate with the slider
-MATLAB neural network backprop code
This code implements the basic backpropagation of
error learning algorithm. The network has tanh hidden
neurons and a linear output neuron.
adjust the learning rate with the slider
Platform: |
Size: 2048 |
Author:azoma |
Hits:
Description: For those who spend most of their time working indoors, the indoor air quality (IAQ) could affect their working efficiency and health. This paper presents an intelligent proportional-integral-derivative (PID) controller for IAQ control. Different the traditional PID controller, this novel controller combined with Back-Propagation Neural Networks (BPNN) technology will regulate the PID parameters kp, ki, kd automatically. In the present study, the algorithm of the BPNN-based PID controller is first discussed in details, and the control performance is then tested by simulation using MATLAB. The difficulty in IAQ control is the existence of control disturbance, time delay and measurement errors. The results show that the combined control algorithm has better performance on the systemic stability, disturbance resistance, fast response rate and small overshoot compared with traditional PID controller.-For those who spend most of their time working indoors, the indoor air quality (IAQ) could affect their working efficiency and health. This paper presents an intelligent proportional-integral-derivative (PID) controller for IAQ control. Different the traditional PID controller, this novel controller combined with Back-Propagation Neural Networks (BPNN) technology will regulate the PID parameters kp, ki, kd automatically. In the present study, the algorithm of the BPNN-based PID controller is first discussed in details, and the control performance is then tested by simulation using MATLAB. The difficulty in IAQ control is the existence of control disturbance, time delay and measurement errors. The results show that the combined control algorithm has better performance on the systemic stability, disturbance resistance, fast response rate and small overshoot compared with traditional PID controller. Platform: |
Size: 4096 |
Author:payam/baban |
Hits:
Search - BPNN algorithm matlab