How to divide class in neural network for Biometric authentication?

I just want to know how to decide class for person authentication using any of the parameter like fingerprint iris whatever. I am just eager to how to perform person authentication by Neural network as i have 5 sample for each subject i just want to train NN by 4 out of each 6 samples..

Please put you kind suggestion

Answer 1

[Greg Heath]

You are going to have to design many candidate nets to decide the number of hidden nodes and which random weight initialization will yields the best net. If you have a lot of data, you can just use the default dividerand with the default train/val/test ratio = 0.7/0.15/0.15 . However, if this isn't satisfactory, you could change it to 0.666/0.167/0.167/. However, it really isn't worth the trouble.

If you don't have much data you might want to use divideind to specify which inputs belong to each trn/val/test subset.

How many people are there? If there are Np people you could use one input from each person in every group of Np.

Hope this helps.

Greg