Neural Networking for Dummies

So I want to write neural network that would process N-symbol words.

Should I provide 26 symbol neurons for each letter position, so that they give 1.0 for their matching letter? Should I duplicate position for each recognized words? I.e. vocabulary of 1000 N-sized words would require 1000*N*26.

how is it relevant to 'their only stimuli being letters'
blind people learn their first language just like you learned it - aurally from their parents when they cannot yet read and don't know what letter it. deafblind from birth.. afaik they are taught with special gestures (tactile) instead of sound. anyway the concept of letter is a quite abstract concept and i seriously doubt it could be understood without knowing a language beforehand (you may not realize it but our language it's our means to think abstractly and letter is an abstraction, those who don't learn a human language to age of ~6y.o. or so will be half-sapient forever, see feral children)