搜索资源列表
matlab
- 神经网络的程序说明,以及代码 神经网络工具箱应用-Neural network descr iption of the procedures, as well as application code neural network toolbox
invertedpendulum
- 倒立摆是一种复杂、时变、非线性、强耦合、自然不稳定的高阶系统，许多抽象的控制理论概念都可以通过倒立摆实验直观的表现出来。基于人工神经网络BP算法的倒立摆小车实验仿真训练模型，其倒立摆BP网络为4输入3层结构。输入层分别为小车的位移和速度、摆杆偏离铅垂线的角度和角速度。隐含层单元数16个。输出层设置为1个输出单元。输入层采用Tansig函数，隐含层采用Logsig函数，输出层采用Purelin函数。用Matlab 6.5数值计算软件对模型
BPNN4_2
- load training.txt load TrainOut.txt load validation.txt load ValOut.txt load testing.txt load TestOut.txt INPUT=[training validation testing] OUTPUT=[TrainOut ValOut TestOut] net=newff(INPUT,OUTPUT,200,{ t
Function-approximation
- 函数逼近的MATLAB程序，本程序设计一个两层的bp网络用于函数逼近，隐层的激活函数为 tansig,输出层激活函数为purelin线性函数 -Function approximation of the MATLAB program, the program design of a two-tier network for function approximation bp, hidden layer activation fun
ijrte0206121124
- Abstract-This paper introduces the new concept of Artificial Neural Networks (ANNs) in estimating speed and controlling the separately excited DC motor. The neural control scheme consists of two parts. One is the n
gm11
- function exp85 clear all p=[0:0.1:1.1] t=[22.4570 26.6012 12.6416 5.9367 6.9265 28.2432 31.5068 37.0166 7.8947 1.0398 12.7095] net=newff([0 1],[5 1],{ tansig purelin }, traingdx , learngdm ) net.trai
twodimapproximationbp
- 单输出函数Y=SIN(X)逼近问题的bp程序:假设网络结构为3--2--1，输入维数M,共N个样本,一般输入不算层，输出算层- 激活函数: hardlim---(0,1),hardlims---（-1,1),purelin,logsig---(0,1),tansig----(-1,1) softmax,poslin,radbas,satlin,satlins,tribas 训练算法: 1.traing
SingularValueDecomposition
- 人脸识别过程中的奇异值分解算法代码，亲测可用，实现步骤为： feature = allFeature(1) //featurenumber=8,16,24,32,48,64,80 [pn,pnewn,t,num_train,num_test] = train_test(feature,num_train) //num_train=1~10 [net] = createBP(pn) //110,tansig,pur