How can I obtain the "correct" weight matrices of neural networks ?

7 views (last 30 days)
I am using the Neural Network Toolbox of MATLAB. I am trying to train a network for the purpose of image classification and pattern recognition. The input layer has 784 neurons, hidden layer has 100 neurons and the output layer has 10. So accordingly, I expect the inner layer of weight matrix (first layer) to be of size 100 X 784. However, after the network is trained, when I obtain the weights and biases using net.IW or separatewb() function, it shows the inner weight matrix to be of dimension 100 X 663. Why is this so ? Is MATLAB doing some kind of simplification ? Thanks !!

Accepted Answer

Sebastian Kammer
Sebastian Kammer on 23 Nov 2016
Looks like other people have asked the same question before:
It seems that redundant/constant rows in the input data might cause this behavior.
  1 Comment
Ankit Mondal
Ankit Mondal on 30 Nov 2016
Thanks a lot Sebastian. That indeed seems to be the case with my code.

Sign in to comment.

More Answers (0)

Community Treasure Hunt

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

Start Hunting!