I have spent a bunch of time looking at this series of videos (Neural Network Tutorial), by Ryan Harris: https://www.youtube.com/watch?v=Q_5B3GuWPCc&index=41&list=PL29C61214F2146796

I am using his libraries to implement my solution.

My objective is to be able to train a neural network to detect a picture of a Coca-Cola can. I have several 80 x 108 pixel pictures of the cans. So this means I will need a layer of 6480 inputs. My goal is to have it output to a single output, ideally this output would show on a scale of 0 to 1. The values would show how certain the network is that it is a Coca-Cola can. For example 0.30 would be 30 percent sure.

I'm looking for resources or pointers that would show me how this is done.

Thanks for any help you can provide

  • $\begingroup$ Have a look at: stackoverflow.com/questions/10168686/…. Possible answer is there. $\endgroup$ Feb 28 '15 at 11:17
  • $\begingroup$ A modern approach to any image recognition task -- not just Coke cans -- is to use a conv-neural-network. $\endgroup$
    – Sycorax
    Aug 13 '18 at 1:27
  • $\begingroup$ This question is very broad, and I believe you would profit from reading an introductory level textbook. We have a helpful list of textbooks and courses about neural networks. If afterwards you still have more specific questions, then please do ask them here. If you already have read such a textbook, please edit your question to make it more specific. Thank you! $\endgroup$
    – Sycorax
    Aug 13 '18 at 1:27

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.