41 پاسخ به “در داخل شبکه عصبی – Computerphile”

1. Love the visualization!

2. Another TURING test of comments.
   Prove you are not a.

3. The title must be "inside a cnn and not neural network"😇
   Bye the great explaination of ann!!!

4. Very enjoyable, thank you!

5. An Intellimouse? c 0 0 l

6. Dr Mike Pound, please make a tutorial series on q learning! In depth <3

7. @ 5:58 I got the point i am searching for. Thank you very much..

8. Very cool!
   @5:24 Grayscale is quite a few bits deep, 1-bit depth would be Black & White ( which is not the case in your images, looks like you have at least 16-bit images – if not 256-bit standard grayscale – )

9. This is what Bender's brain was going through when he "thought he saw a two".

10. Let's do 'cause I love CNN

11. This is the best explaination of what is going on inside a neural net! Now I can imagine it more clearly
    Thanks alot!

12. how do you know how many kernels, layers, etc. are best suited for your needs?

13. Thank you very much! Very helpful video!

14. Mike and Rob, the stars of computerphile.
    Great content and nice puns.
    Keep it up guys

15. very helpful, thanks

16. Is captcha a method to filter out bots, or is it a way to coerce humans into training and AI?

17. This is very dangerous for security things like CAPTCHA

18. Thank you Mike, and thank you Shaun, this video is really helping me in my quest! I'm making a small game in which I'm trying to make an AI using the tensorflow library.

19. Computerphile, you single handedly helped me regain my interest with computer science.
    Thank you very much for all your videos (:

20. How comes 50fps? Anyways great vid!

21. I realize this isn't likely to get a reply this late, but I'm trying to replicate the configuration of this network. What activation function are you using for the first fully connected layer? Is it dotplus with a renormalization? I'm assuming FC2 is a softmax layer, so maybe they are both softmax.

22. Please do a video on the maths of forward and back propagation and how they are implemented

23. 3:43 but wouldn't it mean that the digit's 2? because we're starting at index 0, and index 0 is 0, so index 2 is 2.

24. sexy lecturer.

25. I still wan't to see google capcha being beat by tensorflow

26. 13:41 "he"

27. Would love to have someone like him as my professor in my life!

28. HOw can i get these algos if i want to do it on my machine?

29. How to you replicate the learned connections to other systems? How is the "knowledge" abstracted for transport, backup, and further improvements?

    With discrete programming, the instructions are compact and finite and are easily copied.

30. could you make a neural network of neural networks?

31. i am so fascinated by artificial neural networks .

32. Nick Batt, is that you?

33. at one point binary flashed on the screen as a background, here's a part of the translation: E¤ªÉü

34. It's really distracting that the camera looking over the guy's shoulder was out of focus.

35. +1 for running GNU/Linux 🙂

36. Vicarious beat CAPTCHAs in 2013.

37. May be I didn't get the idea, but why there is 10, and not 11 classes for numbers?
    Because if I will give an image of "A" to this network, it will probably say to me "this is 1" or "this is 4" instead of giving the negative answer like "its neither of 10 numbers".

38. Can someone explain how the final convolutional layer is 4x4x50? My understanding based on the previous Neural Network video is that the first convolution will produce an output of 24x24x20, but then wouldn't the next convolution, which has 20 kernels, produce 20 images of the first image layer of the 20 produced from the first convolution, and then another 20 on the second image layer of the 20 produced from the first convolution, such that at the end of the second layer you'd have a 20x20x400 output, and so forth until at the end you'd have 4x4x(some large number) not 4x4x50?

39. What did you say you used to build the model?

40. excellent..

41. Why are we shrinking the images by ignoring edges? Can't we just deal with the edges without centering into the image? It just seems like an arbitrary limitation, maybe what's most significant about a "2" is around the edges!

نظرات بسته شده اند.