Intro to ConvNets: The backbone of modern computer vision

Transcript

1. 1.

   The backbone of modern computer vision Intro to ConvNets

2. 2.

   2

3. 3.

   3 =

4. 4.

   4

5. 5.

   Convolutional Network

6. 6.

   6 ⊙ = Σ input output kernel

7. 7.

   7 input output ⊙ = kernel Σ

8. 8.

   8 input output = kernel Σ ⊙

9. 9.

   9 input output ⊙ = kernel Σ

10. 10.

    10 kernel input output

11. 11.

    11

12. 12.

    12 Optimization Label: Bird ConvNet Loss Function Prediction: Cat

13. 13.

    13 Optimization ConvNet Prediction: Bird Loss Function Label: Bird

14. 14.

    14 Non-linear function from: wikipedia.org Sigmoid Function

15. 15.

    15 Pooling operation from: computersciencewiki.org

16. 16.

    16

17. 17.

    17 Conv layer Non-linear function Convolution & Non-linear function &

    Pooling Pooling Conv layer Non-linear function Pooling Conv layer Non-linear function
18. 18.

    18 AlexNet (2012)

19. 19.

    Thanks!