matlab BP神经网络

clear

clc

% 准备数据

inputs = rand(10, 100); % 100组输入，每组10个特征

outputs = rand(1, 100); % 100组输出，每组1个输出值

% 将数据分成训练集和测试集

trainRatio = 0.8;

valRatio = 0.1;

testRatio = 0.1;

trainInd, valInd, testInd = dividerand(100, trainRatio, valRatio, testRatio);

X_train = inputs(:, trainInd);

y_train = outputs(:, trainInd);

X_test = inputs(:, testInd);

y_test = outputs(:, testInd);

% 创建前馈神经网络

hiddenLayerSize = 10;

net = feedforwardnet(hiddenLayerSize);

% 设置训练、验证和测试数据

net.divideParam.trainRatio = 0.8;

net.divideParam.valRatio = 0.1;

net.divideParam.testRatio = 0.1;

% 训练神经网络

net, tr = train(net, X_train, y_train);

% 查看训练结果

plotperform(tr);

% 进行预测

y_pred = net(X_test);

% 计算误差

errors = y_pred - y_test;

% 输出误差

for i = 1:length(y_test)

fprintf('Test sample %d:\n', i);

fprintf('Predicted output: %.4f\n', y_pred(i));

fprintf('Actual output: %.4f\n', y_test(i));

fprintf('Error: %.4f\n\n', errors(i));

end

% 计算均方误差（MSE）

mse = mean(errors.^2);

fprintf('Mean Squared Error: %.4f\n', mse);