text prediction

Hi Karparthy

I have trouble understanding a few points in the character prediction demo:

1) What is the meaning of letter_size?
letter_size = 5; // size of letter embeddings

My understanding is that the inputs to the network are just vectors of length 50 (or however many unique characters in our dataset) that look like [0, 0, 0, 0, 1, 0, 0, 0 ... ], and the output is similar

2) to tick the model forward, you used 'rowPluck'
x = G.rowPluck(model['Wil'], ix);

and I think ix is the integer index that represents the character. I exampled x in inspector and is a value of floats of length letter_size, rather than a large binary vector of length 50

So I have a little bit of a hard time what is going on and currently quite puzzled. Any advice or guidance appreciated!

Thanks

David

The issue names the character prediction demo, `letter_size`, and `G.rowPluck(model['Wil'], ix)`; start there and trace how the index and embedding dimensions are used. Done means adding clear documentation that resolves the questions about character inputs, embeddings, and `rowPluck`.

Written by the indexing model from the issue text.