Bp和ELM的matlab代码
概览
本文给出了Bp神经网络，ELM-极限学习机的matlab代码（代码来源于前人整理），使用的例程，以及介绍算法原理优秀的链接。
程序包：
链接：https://pan.baidu.com/s/1i_ztrqEmyUDUTQKlAMZGBw
提取码：o5yv
例程
%% 机器学习-例程
%% 简单介绍
%
%
% 功能：基于训练数据，利用学习器，构建预测模型。
%
% 输入：训练数据（特征+标签），测试数据（特征+标签）。
%
% 输出：预测的标签
%
% 学习器的选择：优先ELM。（可以对分类数据做可视化分析，根据分布特点选择对应偏好的分类器）
%
%
% 注意：以下例程中，测试数据是‘特征+标签’，输出是测试精度和预测样本。在实际应用中，可直接将测试样本的标签设置为0，然后进行预测标签。
%% 数据整理
load iris.mat % 加载数据集，特征在前，标签在后，每一行为一个样本，每一列为一个特征
tr=iris(1:100,:); % 取iris数据的前100行作为训练样本
te=iris(101:end,:); % 取后50行作为测试样本
%% 学习器
% 1. Bp神经网络
hiddenSizes = 5; % 隐层单元
[A_Bp,bplabel] = f_Bp(tr,te,hiddenSizes);
% 原理：https://blog.csdn.net/u014303046/article/details/78200010
% 2. ELM
NumberofHiddenNeurons = 10;
[A_ELM, Label_ELM, TrainingAccuracy, TrainingTime, TestingTime] = f_ELM(tr,te,NumberofHiddenNeurons);
% 原理：https://blog.csdn.net/qq_32892383/article/details/90760481
子程序
function [A,bplabel]=f_Bp(tr,te,hiddenSizes)
%Input: tr: Training set
% te: testing set
% Note that: each row represents a instance, last column is label, begins from 1
% hiddenSizes：the size of hidden layer(default = 10)隐层神经元个数；
%Output: A: Testing Accuracy
% bplabel: predict label by svm for testingdata
if ~exist('hiddenSizes', 'var')
hiddenSizes = 10;
end
input_train=tr(:,1:end-1)';
output_train=tr(:,end);
input_test=te(:,1:end-1)';
output_test=te(:,end);
label=[output_train;output_test];
L=unique(label); % 合并A中相同数据
ls=length(L(:)); %统计类别总数
ns=length(output_train);
output=zeros(ns,ls);
for j=1:ns
output(j,output_train(j))=1;
end
%% BP网络训练
% %初始化网络结构
net=newff(input_train,output',[hiddenSizes]);
%newff函数的格式为：
%net=newff(PR,[S1 S2 ...SN],{TF1 TF2...TFN},BTF,BLF,PF），函数newff建立一个可训练的前馈网络。输入参数说明：
%PR：Rx2的矩阵以定义R个输入向量的最小值和最大值；
%Si：第i层神经元个数；
%TFi：第i层的传递函数，默认函数为tansig函数；
%BTF：训练函数，默认函数为trainlm函数；
%BLF：权值/阈值学习函数，默认函数为learngdm函数；
%PF：性能函数，默认函数为mse函数。
%% 指定训练参数
net.trainParam.epochs=1000;%%%最大迭代次数
net.trainParam.lr=0.01;%%%学习率
net.trainParam.goal=0.01;%%%最小均方误差
%% 指定隐层函数和训练函数
% hiddenFcn：Hidden Layer function (default = 'tansig')隐层的传递函数，默认函数为tansig函数；
% trainFcn：Training function (default = 'trainlm')训练函数，默认函数为trainlm函数；
net.trainFcn = 'trainlm'; % 梯度下降算法
% net.trainFcn = 'traingd'; % 梯度下降算法
% net.trainFcn = 'traingdm'; % 动量梯度下降算法
% net.trainFcn = 'traingda'; % 变学习率梯度下降算法
% net.trainFcn = 'traingdx'; % 变学习率动量梯度下降算法
% (大型网络的首选算法)
% net.trainFcn = 'trainrp'; % RPROP(弹性BP)算法,内存需求最小
% (共轭梯度算法)
% net.trainFcn = 'traincgf'; % Fletcher-Reeves修正算法
% net.trainFcn = 'traincgp'; % Polak-Ribiere修正算法,内存需求比Fletcher-Reeves修正算法略大
% net.trainFcn = 'traincgb'; % Powell-Beal复位算法,内存需求比Polak-Ribiere修正算法略大
% (大型网络的首选算法)
% net.trainFcn = 'trainscg'; % Scaled ConjugateGradient算法,内存需求与Fletcher-Reeves修正算法相同,计算量比上面三种算法都小很多
% net.trainFcn = 'trainbfg'; % Quasi-NewtonAlgorithms - BFGS Algorithm,计算量和内存需求均比共轭梯度算法大,但收敛比较快
% net.trainFcn = 'trainoss'; % One Step SecantAlgorithm,计算量和内存需求均比BFGS算法小,比共轭梯度算法略大
% (中型网络的首选算法)
% net.trainFcn = 'trainlm'; % Levenberg-Marquardt算法,内存需求最大,收敛速度最快
% net.trainFcn = 'trainbr'; % 贝叶斯正则化算法
% 有代表性的五种算法为:'traingdx','trainrp','trainscg','trainoss','trainlm'
%% 网络训练
net=train(net,input_train,output');
%% BP网络预测
%网络预测输出
Y=sim(net,input_test);
%% 结果分析
%根据网络输出找出数据属于哪类
s=size(Y,2);
for i=1:s
[m,I]=max(Y(:,i));
bplabel(i,1)=I;
end
net.iw{1,1};%隐层权值
net.b{1};%隐层阈值
net.lw{2,1};%输出层权值
net.b{2};%输出层阈值
%预测正确率
rightnumber=0;
for i=1:length(output_test)
if bplabel(i)==output_test(i)
rightnumber=rightnumber+1;
end
end
A=rightnumber/length(output_test);
end
function [TestingAccuracy, elmlabel, TrainingAccuracy, TrainingTime, TestingTime] = f_ELM(tr,te,NumberofHiddenNeurons)
% Input:
% Tr - Filename of training data set
% Te - Filename of testing data set
% Note that: each row represents a instance, last column is label, begins from 1
% Elm_Type - 0 for regression; 1 for (both binary and multi-classes) classification
% NumberofHiddenNeurons - Number of hidden neurons assigned to the ELM
% ActivationFunction - Type of activation function:
% 'sig' for Sigmoidal function
% 'sin' for Sine function
% 'hardlim' for Hardlim function
% 'tribas' for Triangular basis function
% 'radbas' for Radial basis function (for additive type of SLFNs instead of RBF type of SLFNs)
%
% Output:
% TrainingTime - Time (seconds) spent on training ELM
% TestingTime - Time (seconds) spent on predicting ALL testing data
% TrainingAccuracy - Training accuracy:
% RMSE for regression or correct classification rate for classification
% TestingAccuracy - Testing accuracy:
% RMSE for regression or correct classification rate for classification
%elmlabel - predict label by elm for testingdata
Elm_Type=1;
ActivationFunction='sig';
Tr=tr;
Te=te;
if ~exist('Elm_Type', 'var')
Elm_Type = 1;
end
if ~exist('NumberofHiddenNeurons', 'var')
NumberofHiddenNeurons = 10;
end
if ~exist('ActivationFunction', 'var')
ActivationFunction = 'sig';
end
%%%%%%%%%%% Macro definition
REGRESSION=0;
CLASSIFIER=1;
%%%%%%%%%%% Load training dataset
T=Tr(:,end)';
P=Tr(:,1:end-1)';
clear Tr; % Release raw training data array
%%%%%%%%%%% Load testing dataset
TV.T=Te(:,end)';
TV.P=Te(:,1:end-1)';
clear Te; % Release raw testing data array
NumberofTrainingData=size(P,2);
NumberofTestingData=size(TV.P,2);
NumberofInputNeurons=size(P,1);
if Elm_Type~=REGRESSION
%%%%%%%%%%%% Preprocessing the data of classification
sorted_target=sort(cat(2,T,TV.T),2);
label=zeros(1,1); % Find and save in 'label' class label from training and testing data sets
label(1,1)=sorted_target(1,1);
j=1;
for i = 2:(NumberofTrainingData+NumberofTestingData)
if sorted_target(1,i) ~= label(1,j)
j=j+1;
label(1,j) = sorted_target(1,i);
end
end
number_class=j;
NumberofOutputNeurons=number_class;
%%%%%%%%%% Processing the targets of training
temp_T=zeros(NumberofOutputNeurons, NumberofTrainingData);
for i = 1:NumberofTrainingData
for j = 1:number_class
if label(1,j) == T(1,i)
break;
end
end
temp_T(j,i)=1;
end
T=temp_T*2-1;
%%%%%%%%%% Processing the targets of testing
temp_TV_T=zeros(NumberofOutputNeurons, NumberofTestingData);
for i = 1:NumberofTestingData
for j = 1:number_class
if label(1,j) == TV.T(1,i)
break;
end
end
temp_TV_T(j,i)=1;
end
TV.T=temp_TV_T*2-1;
end % end if of Elm_Type
%%%%%%%%%%% Calculate weights & biases
start_time_train=cputime;
%%%%%%%%%%% Random generate input weights InputWeight (w_i) and biases BiasofHiddenNeurons (b_i) of hidden neurons
InputWeight=rand(NumberofHiddenNeurons,NumberofInputNeurons)*2-1;
BiasofHiddenNeurons=rand(NumberofHiddenNeurons,1);
tempH=InputWeight*P;
clear P; % Release input of training data
ind=ones(1,NumberofTrainingData);
BiasMatrix=BiasofHiddenNeurons(:,ind); % Extend the bias matrix BiasofHiddenNeurons to match the demention of H
tempH=tempH+BiasMatrix;
%%%%%%%%%%% Calculate hidden neuron output matrix H
switch lower(ActivationFunction)
case {'sig','sigmoid'}
%%%%%%%% Sigmoid
H = 1 ./ (1 + exp(-tempH));
case {'sin','sine'}
%%%%%%%% Sine
H = sin(tempH);
case {'hardlim'}
%%%%%%%% Hard Limit
H = double(hardlim(tempH));
case {'tribas'}
%%%%%%%% Triangular basis function
H = tribas(tempH);
case {'radbas'}
%%%%%%%% Radial basis function
H = radbas(tempH);
%%%%%%%% More activation functions can be added here
end
clear tempH; % Release the temparary array for calculation of hidden neuron output matrix H
%%%%%%%%%%% Calculate output weights OutputWeight (beta_i)
OutputWeight=pinv(H') * T'; % implementation without regularization factor //refer to 2006 Neurocomputing paper
%OutputWeight=inv(eye(size(H,1))/C+H * H') * H * T'; % faster method 1 //refer to 2012 IEEE TSMC-B paper
%implementation; one can set regularizaiton factor C properly in classification applications
%OutputWeight=(eye(size(H,1))/C+H * H') \ H * T'; % faster method 2 //refer to 2012 IEEE TSMC-B paper
%implementation; one can set regularizaiton factor C properly in classification applications
%If you use faster methods or kernel method, PLEASE CITE in your paper properly:
%Guang-Bin Huang, Hongming Zhou, Xiaojian Ding, and Rui Zhang,
%"Extreme Learning Machine for Regression and Multi-Class Classification,"
%submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence, October 2010.
end_time_train=cputime;
TrainingTime=end_time_train-start_time_train; % Calculate CPU time (seconds) spent for training ELM
%%%%%%%%%%% Calculate the training accuracy
Y=(H' * OutputWeight)'; % Y: the actual output of the training data
if Elm_Type == REGRESSION
TrainingAccuracy=sqrt(mse(T - Y)); % Calculate training accuracy (RMSE) for regression case
end
clear H;
%%%%%%%%%%% Calculate the output of testing input
start_time_test=cputime;
tempH_test=InputWeight*TV.P;
clear TV.P; % Release input of testing data
ind=ones(1,NumberofTestingData);
BiasMatrix=BiasofHiddenNeurons(:,ind); % Extend the bias matrix BiasofHiddenNeurons to match the demention of H
tempH_test=tempH_test + BiasMatrix;
switch lower(ActivationFunction)
case {'sig','sigmoid'}
%%%%%%%% Sigmoid
H_test = 1 ./ (1 + exp(-tempH_test));
case {'sin','sine'}
%%%%%%%% Sine
H_test = sin(tempH_test);
case {'hardlim'}
%%%%%%%% Hard Limit
H_test = hardlim(tempH_test);
case {'tribas'}
%%%%%%%% Triangular basis function
H_test = tribas(tempH_test);
case {'radbas'}
%%%%%%%% Radial basis function
H_test = radbas(tempH_test);
%%%%%%%% More activation functions can be added here
end
TY=(H_test' * OutputWeight)'; % TY: the actual output of the testing data
[TYmax,elmlabel]=max(TY);
elmlabel=elmlabel';
end_time_test=cputime;
TestingTime=end_time_test-start_time_test; % Calculate CPU time (seconds) spent by ELM predicting the whole testing data
if Elm_Type == REGRESSION
TestingAccuracy=sqrt(mse(TV.T - TY)); % Calculate testing accuracy (RMSE) for regression case
end
if Elm_Type == CLASSIFIER
%%%%%%%%%% Calculate training & testing classification accuracy
MissClassificationRate_Training=0;
MissClassificationRate_Testing=0;
for i = 1 : size(T, 2)
[x, label_index_expected]=max(T(:,i));
[x, label_index_actual]=max(Y(:,i));
if label_index_actual~=label_index_expected
MissClassificationRate_Training=MissClassificationRate_Training+1;
end
end
TrainingAccuracy=1-MissClassificationRate_Training/size(T,2);
for i = 1 : size(TV.T, 2)
[x, label_index_expected]=max(TV.T(:,i));
[x, label_index_actual]=max(TY(:,i));
if label_index_actual~=label_index_expected
MissClassificationRate_Testing=MissClassificationRate_Testing+1;
end
end
TestingAccuracy=1-MissClassificationRate_Testing/size(TV.T,2);
end