MATLAB: Is the neural network properly trained

Deep Learning Toolboxneural networkneural networks

Hello i have a feature vector of 12455×400 matrix and out put target of 40×400 matrix .I am training using patternent and fucntion is trainscg for face recognition using local binary pattern. I hve 400 images which have 40 individuals in them. This is my neural network output .

8.333 mis classifications means it had identified almost all other ~92% of images in the test set of 60 images?

Best Answer

Yes.

However, isn't there any way to use feature extraction to reduce your input dimension below 12455 ???

Can patternnet really handle vectors that long?

Thank you for formally accepting my answer

Greg

Related Solutions

MATLAB: How to train a feedfordward neural network with error weights

 Use the command window
 help mse
 doc mse

Hope this helps.

Thank you for formally accepting my answer

Greg

MATLAB: How to avoid training stops at less no of iterations in neural network training

Validation stopping prevents poor performance on nontraining data. Since weight initialization and trn/val/tst datadivision are random, my approach is too design many (~100) nets with different initial random number states and choose the net with the smallest number of hidden nodes that yields a Rsq >= 0.99.

I have posted zillions of examples in both NEWSGROUP and ANSWERS Search words

 Hmin dH Hmax Ntrials

Hope this helps.

Thank you for formally accepting my answer

Greg

Best Answer

Related Solutions

MATLAB: How to train a feedfordward neural network with error weights

MATLAB: How to avoid training stops at less no of iterations in neural network training

Related Question