Suggest to network architecture for two class classification problem by using MLP neural network

HI, please guide me for choose these parameters for binary classification by using MLP neural network .

     number of samples : 300 (150 for class 1 and 150 for class 2)
     train set = ?
     validation set = ?
     Test set = ? 
     number of input : 10 or 15 (depend on features)please explain  The impact on the hidden layer for both numbers.
     number of hidden layer : ؟
     number of hidden neuron : ?
     number of output neuron : ?
     value for target matrix : (for example 1 and -1 , or 1 and 0)

Answer 1

[Greg Heath]

Most of your questions can be answered from

 1. The doc and help documentation examples

 help patternnet
 doc patternnet

 2. My NEWSGROUP and ANSWERS posts using search words

 greg patternnet

Hope this helps.

Thank you for formally accepting my answer

Greg