How can I obtain the "correct" weight matrices of neural networks ?
7 views (last 30 days)
Show older comments
Ankit Mondal on 20 Nov 2016
Commented: Ankit Mondal on 30 Nov 2016
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 !!
Sebastian Kammer on 23 Nov 2016
Looks like other people have asked the same question before:
Take a look at this MATLAB Answers thread.
It seems that redundant/constant rows in the input data might cause this behavior.
More Answers (0)
Find more on Define Shallow Neural Network Architectures in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!