Custom neural network not training

Question

Jérôme 2013-6-22

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/79916-custom-neural-network-not-training

Hi;

I'm trying to set up a custom neural network, but when I train it, it doesn't train : the training process makes 0 iterations! I don't get any errors though, just 0 iterations, and I have no idea why. (The architecture might seem odd to you, it is supposed to be a custom PNN. But before we can even discuss if it makes sense or not, I would like to be able to train it...)

Here is the code

net = network;
  net.trainFcn = 'trainlm';
  net.performFcn = 'mse';
  net.numInputs = 1;
  net.numLayers = (2*nbclasses)+1; % (one pattern layer + one summation layer per class) + competition layer
  net.inputConnect(1:nbclasses,:) = 1; % connects the input to all pattern layers
    for i = 1:nbclasses % Connect the pattern layers to their corresponding summation layers
        net.layerConnect(i+nbclasses,i) = 1;
        net.layers{i}.size = size(tr_feature,1);
        net.layers{i}.transferFcn = 'radbas';
    end
    for i = (nbclasses+1):(nbclasses*2) % Connect all summation layers to the competition layer
        net.layers{i}.size = 1;
        net.layerConnect(net.numLayers,i) = 1;
    end
    net.layers{net.numLayers}.transferFcn = 'compet';    
    net.outputConnect(1,end) = 1;
    net.view;
    [net, tr] = train(net,tr_feature',tr_true');
    % tr_feature is a 800x2 data matrix, tr_true is the 800x1 corresponding labels

Any idea?

Thanks in advance!

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Greg Heath 2013-6-30

编辑：Greg Heath 2013-6-30

The best way for us to help is to have

1.The name of one of the MATLAB nndata sets (help nndatasets) on which we can test your code. For example, the crab_data set using only the first row of the target matrix.

2. Post code that either runs when cut and pasted or is close to running.Include any error messages.

3. Have you looked at the results of

net = newpnn(tr_feature',ind2vec(tr_true')) % NO SEMICOLON

4. The notation 'tr' should be reserved for the training record output of training, i.e., [ net tr ] = train(net,input,target);

5. nbclasses = 2?

Hope this helps.

Greg

请先登录，再进行评论。

请先登录，再回答此问题。

Custom neural network not training

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

回答（0 个）

另请参阅

类别

标签

Community Treasure Hunt

Custom neural network not training

1 个评论 显示 -1更早的评论隐藏 -1更早的评论

回答（0 个）

另请参阅

类别

标签

Community Treasure Hunt

1 个评论
显示 -1更早的评论隐藏 -1更早的评论