0

How are the weights given between the input-neurons and the hidden-neurons and as well between the hidden-neurons and the output-neurons? I am aware that the weights are given randomly at the beginning.

Secondly, I'm doing character recognition and lets say that I have a character of size 8x8 pixels meaning 64 input neurons, that should mean that I need to have 64 output-neurons as well right?

TheCodeArtist
  • 21,479
  • 4
  • 69
  • 130
David Farrugia Id-Diesel
  • 1
  • 1
  • 1
  • 1
    The answer to your first question is "backpropagation". The answer to your second question is "no, you'll have as many output neurons as characters you wish to recognize". – Sneftel Feb 17 '14 at 21:10
  • Incidentally, processing a grid of raw pixel values with an ANN is a *terrible* way to do OCR. I'm guessing that this is for a school assignment, though. – Sneftel Feb 17 '14 at 21:10

1 Answers1

0

For the output layer size see my answer to the same question here.

I'm unsure what you mean by "how weights are given". Do you mean "trained"? If yes, usually by Backpropagation. If you mean "how it is represented": usually as an array or a matrix.

If you want to read more about fine-tuning for backpropagation, read this paper by LeCun.

On another note: 1 pixel per node as input is something you would never do. You never feed raw data into the network because it contains noise and unneeded information. Find a representation, a model, an encoding or something similar before you feed it into the network. To understand how this is done, you have no other choice than to do some research. There are too many possibilities to give a clear answer.

Community
  • 1
  • 1
runDOSrun
  • 10,359
  • 7
  • 47
  • 57