# How to decide Linear Separability in my Neural Net work?

I am going to design a Neural Net which will be able to break a 5 letter (characters) word into its corresponding syllables (hybrid syllables, I mean it will not strictly adhere to grammatical Syllable rules but will be based on some training sets I provide).

Example : Train -> tra-in

I think of implementing it in terms of some feedforward net as follows :

Input layer ->Hidden layers -> Output layer

There will be 5 input nodes in the form of decimals (1/26 =0.038 for 'A' ; 2/26 = 0.076 for 'B' ......)

The output layer consists of 4 Nodes which corresponds to each gap between two characters in the word.

And fires as follows :

For "TRAIN" (TRA-IN): Input (0.769,0.692,0.038,0.346,0.538) Output(0,0,1,0)

For "BORIC" (BO-RI-C): **Input.... Output (0,1,0,1)

Is it at all possible to implement the Neural Nets in the way I am doing??

And if possible, then how will I decide the number of Hidden layers and Nodes in each layer??

( In the book I am reading, XOR gate problem and its implementation using hidden layer is given . In XOR we could decide the number of Nodes and Hidden Layers required by seeing the Linear Separability of XOR using two lines. But here I think such analysis can't be made.

So how do I proceed?? Or is it a trial and error process?)