Why is the size of the input weight matrix sometimes smaller than the input length when training a neural network?

4 次查看（过去 30 天）

显示更早的评论

Antje 2012-9-6

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/47514-why-is-the-size-of-the-input-weight-matrix-sometimes-smaller-than-the-input-length-when-training-a-n

评论： Greg Heath 2017-5-5

采纳的回答： Antje

在 MATLAB Online 中打开

I have a question regarding the size of the inut weight matrix for a neural network. My IW Matrix is smaller than expected and I don't know why. What I do:

net=patternnet(1);
[net,tr]=train(net,inputs,targets);
net.IW              %size of the input weight matrices
ans = 
    [1x14 double]
    []
net.inputs.size     %size of my inputs
ans = 
    [15]
net.layers.size     %size of my hidden and output layer
ans = 
    [1]
    [2]

As far as I understood, the size of my input weight matrix should be 1 (size of hidden layer) by 15 (length of input vectors). I tried it several times with different input sizes, but the size of IW sometimes is equal or 1-2 smaller than my input size.

I want to know why this happens and how I can match the weights to the input variables. Thanks in advance, Antje

2 个评论
显示无隐藏无

Sean de Wolski 2012-9-6

Are the inputs unique?

Greg Heath 2012-9-6

What are

size(inputs)

size(targets)

Greg

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Antje 2012-9-6

3
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/47514-why-is-the-size-of-the-input-weight-matrix-sometimes-smaller-than-the-input-length-when-training-a-n#answer_58076

Oh, finally I got it!

The problem was, that there were some redundant columns in the inputs. I have not seen them, because I have a huge amount of data.

It seems that the training process ignores these columns, but I could not see which of them.

If I get rid of them before the training, than there are no deviations in size of the input and size of the weight matrix.

5 个评论
显示 3更早的评论隐藏 3更早的评论

enjy fikry 2017-5-5

how can i stop that from happening ? i don't want the training process to ignore these constant columns

Greg Heath 2017-5-5

You should.

They have zero variance.

Therefore they cannot contribute to learning.

However, they can confuse those who do not understand this.

Hope this helps.

Greg

请先登录，再进行评论。

更多回答（0 个）

请先登录，再回答此问题。

类别

AI and Statistics Deep Learning Toolbox Sequence and Numeric Feature Data Workflows

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

产品

Deep Learning Toolbox

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Translated by