2

I have been studying neural networks and I recently found out about deep learning and convolutional neural networks. Can someone give me a newbie introduction to convolutional neural networks, what is the intuition behind them, little bit about the theory (+ possible good references for details and pseudo-code). I do understand how convolution-operation is defined, but can't connect it into neural networks. I'm also just beginning with deep learning methods, so I don't have any experience with that.

Question shortly put: Could someone give an introduction to convolutional neural networks? I would appreciate to have answers to questions:

  1. What?

  2. Why?

  3. How?

Ferdi
  • 4,882
  • 7
  • 42
  • 62
jjepsuomi
  • 5,207
  • 11
  • 34
  • 47
  • 3
    I think the question is too broad. Also, Murphy's and Bishop's book have good and gentle introductions. – bayerj Sep 25 '14 at 12:43
  • Hi @bayerj could you give the name of the books? =) thank you for your help, okay, even a small introduction is enough :) – jjepsuomi Sep 25 '14 at 12:48
  • 1
    Chris Bishop "Pattern recognition and machine learning". Kevin Murphy "Machine learning: a probabilistic perspective". – bayerj Sep 26 '14 at 10:43
  • If you understand how a fully-connected layer works, you might find [my drawings](https://stats.stackexchange.com/a/409172) to be useful. – Dave Jan 03 '22 at 21:45

1 Answers1

1

Here is an oft-cited course on Computer Vision (CV) to get you started. There are a few more for when you get more advanced (also includes general ML courses).

I find video can be much more engaging, but of course the tradeoff is that if you're on the internet it's easier to get distracted.

Nathan
  • 227
  • 2
  • 9