How Convolutional Neural Networks work

47 thoughts on “How Convolutional Neural Networks work”

1. i've watched a good dozen of videos about convolutional neural networks but you've nailed it!!!
   thx for the insights

2. awesome .

3. clear as crystal!!!

4. Yes, anything that can find cats on the internet are indeed a huge asset.

5. good but sound problem, fix it for next time, do not mind but it will improve your videos quality.

6. You should also add the information about padding when doing the convolutions with the filters as we lose pixel information if we do not do any padding when we get to the edge pixels.

7. Not all heroes wear capes some explain CNN

8. Which CNN architecture uses Tensorflow? GoogleNet?
   Please help me 😀

9. Why can't you train hyperparameters?

10. Hi , this video helped me.

11. Is there us any written blog post or notes of this video lectures you have ?

12. at 16:00 why fully connected layers are stacked .one fully connected layer successfully decided that its a X by high average value .92. I m confuse about why we need again and again fully connected layers.

13. I do not understand the voting part, how does it work and how backpropagation is used for getting votes values. I am pretty confused in it.
    Also, how the values of X or O is changing in the end-> for votes, when testing it??

14. i don't know why there r lots of lots of knowledge about how to implement a cnn with lots of boring parameters we dont understand, no body tell us the reason behind it except this one .

15. A true master are good at simplifying complex things . i have a question . how the computer choose the 2 diagonal line filters and middle little X filter since it have no eyes.

16. your audio sucks!

17. Hi Brandon, may I ask whether we can train CNN for regression, and how effective it is?

18. Awesome video man. I needed something like this.

19. Live long!

20. Amazing!
    I just did not understand how backpropogation helps make the convolutional filters.

21. Hi. I wonder at 17:59, why the error at 'O' line is not 0.51?

22. Thank you so much!
    I have one question btw.
    So if the first conv layer had 5 features to check for and the second layer had 3 features, you would expect 15 outputs matrices right?

    Just wanted to make sure since with large numbers of features you can probably expect potentially several thousand matrices and that sounds insane, especially with multiple color channels.

23. Concise and understandable explanation, with great rule of thumb at the back. Awesome video!

24. Wonderful video, really helped with the concepts. Thank you so much!

25. Flawless!

26. Incredibly interesting and well-made video. What I can't currently understand is how do multiple images(the training data) help with the back-propagation? Are the images looked at separately, with different weights adjusted for each image and then an average calculated, or another method? I'm thinking of making my own CNN, but I'm not exactly sure where the training data fits in. I would certainly appreciate any advice and/or explanations.

27. The rule of thumb is worth gold!

28. A+

29. Jeez, this vid is the most legit tutorial of CNN that I've ever watched. Thanks for the hard work. Appreciate.

30. As clear as anyone can possibly explain the CNNs. One of the best introduction to CNNs hands down!!

31. Awesome video on convolution neural networks. Thanks so much Brandon, I was having difficulty to understand the layers but you made it crystal clear.

32. I was fine up until 14:26 when you didn't explain how the voting for and X or an O works. Now I'm lost. Lines magically appear to the X and O without any reason as to why they're there.

33. louder

34. Berkat video ini, saya jadi paham CNN. Makasih makasih banyak banget luar biasa parah.

35. Ohmygoodgod, this video just saved a presentation of mine and made me feel like I can understand everything 😀 Thank you so much for this!!! Eternaly greatful!

36. Great video. I feel like this is one of the most comprehensive especially on how it explains the process step by step (for instance i noticed other explanations don't bother with how stacking layers works)

37. Very well explained, thank you very much

38. Super video! Absolutely super.

39. Thank you for the great lecture. At the end, you emphasized that CNN works for image (or data that can be expressed in image formats). For data that arrangement doesn't matter what methods do you suggest?

40. This man truly is a god.

41. is it my earphone or this video has a really low audio?

42. Amazing! Thank you!

43. There are many videos on YouTube taking this video as base knowledge & images.

44. Very interesting and thorough. Thank you boss. However, the sound was a little low

45. Best intuitive video on CNN !!

46. Thank you so much! It's really useful!

47. Great video, but the sound is very low. But great job.

Comments are closed.