MATLAB: HOW TO VIEW NO OF HIDDEN NEURONS IN A SAVED NETWORK

Deep Learning Toolboxneural network

I HAVE MADE A NETWORK AND SAVED IT. BUT KNOW I FORGOT THE NO O HIDDEN NEURONS AND LAYER THAT I USED TO CREATE IT. CAN ANYONE TELL ME HOW TO KNOW THAT

Best Answer

1. The net diagram

 view(net)

2. I = size(input,1), O = size(target,1), Nw = net.numWeightElements

 Assuming no input or feedback delays,
 Invert Nw = (I+1)*H+(H+1)*O to obtain 
 H = (Nw-O)/(I+O+1)

3. Compare methods 1 and 2

Hope this helps.

Thank you for formally accepting my answer

Greg

Related Solutions

MATLAB: The performance of hidden neurons

I do not understand your problem. However if you want to see examples of searching for the optimal (e.g., smallest) value of hidden nodes that will yield a specified performance, see some of my zillion examples.

Search both the NEWSGROUP and ANSWERS using

 greg Hmin dH Hmax

Hope this helps.

THank you for formally accepting my answer

Greg

MATLAB: How many neurons in the hidden layer??

For a given performance on training data, the fewer the number of weights, the better. Then the net will better generalize to validation, test and unseen data with the same statistical properties.

Since universal approximators can be made with a single hidden layer. Most default configurations have an I-H-O node topology for I dimensional inputs, O-dimensional outputs and H hidden nodes. The resulting number of unknown weights is

 Nw = (I+1)*H+(H+1)*O

With Ntrn input/target training pairs, the number of training equations is

 Ntrneq = Ntrn*O.

For the number of unknowns to not exceed the number of equations, Nw <= Ntrneq which yields the following upper bound on the number of hidden nodes

 H <= Hub = (Ntrneq-O)/(I+O+1)

If possible, increase stability, robustness and generalization with Nw << Ntrneq which yields.

   H << Hub

It is very doubtful that you need 77 inputs. Using more than necessary will increase the number of weights and, typically, destabilize your design. Therefore, you should first reduce the number of inputs before trying to reduce the number of hidden nodes.

The choice of variables obtained from the linear STEPWISE and STEPWISEFIT model functions are, typically relevant.

Hope this helps.

Thank you for formally accepting my answer

Greg

PS I should have a number of posts in the NEWSGROUP and ANSWERS which are relevant.

Best Answer

Related Solutions

MATLAB: The performance of hidden neurons

MATLAB: How many neurons in the hidden layer??

Related Question