从命令行使用nntool [MATLAB]

时间:2009-11-04 12:27:42

标签: matlab command-line neural-network nntool

我有这段代码:

in = [5 columns of data-points];
out = [1 column of data-points];
net = newfit(in,out,5);
net = train(net,in,out);

现在我想

  • 访问生成的错误变量(以便我可以计算平均错误等。)
  • 循环运行,所以我想在循环之间重新初始化权重
  • 访问存储时间运行
  • 的变量

如何从命令行完成这三件事?

[我知道如何使用nntool GUI]来完成这些事情

1 个答案:

答案 0 :(得分:3)

示例:

% some random data
in = rand(100,5)';
out = rand(100,1)';

% create a feed-forward back-propagation neural network
% (1 hidden layer with 5 neurons)
net = newfit(in,out,5);
net.trainParam.showWindow = 0;     % dont show GUI

% repeat 10 times
rmse = [];
t = [];
for i=1:10
    net = init(net);               % initialize network weights

    tic
    net = train(net,in,out);       % train
    predicted = sim(net, in);      % test
    t(i) = toc;

    r = (out - predicted);         % residuals
    rmse(i) = sqrt(mean(r.^2));    % root mean square error
end

% plot errors and elapsed times
bar([t; rmse]', 'grouped'), xlabel('Runs')
legend({'Elapsed Time' 'RMSE'}, 'orientation','horizontal')

screenshot


注意:在R2010b中,newfit函数已被弃用,而不是fitnet,请使用以下代码来创建网络:

% old
%net = newfit(in,out,5);

% new
net = fitnet(5);                   % create ANN
net = configure(net, in, out);     % set input/output sizes according to data