Convolutional Neural Networks

Back to Home

01. Introducing Alexis
02. Applications of CNNs
03. Lesson Outline
04. MNIST Dataset
05. How Computers Interpret Images
06. MLP Structure & Class Scores
07. Do Your Research
08. Loss & Optimization
09. Defining a Network in PyTorch
10. Training the Network
11. Pre-Notebook: MLP Classification, Exercise
12. Notebook: MLP Classification, MNIST
13. One Solution
14. Model Validation
15. Validation Loss
16. Image Classification Steps
17. MLPs vs CNNs
18. Local Connectivity
19. Filters and the Convolutional Layer
20. Filters & Edges
21. Frequency in Images
22. High-pass Filters
23. Quiz: Kernels
24. OpenCV & Creating Custom Filters
25. Notebook: Finding Edges
26. Convolutional Layer
27. Convolutional Layers (Part 2)
28. Stride and Padding
29. Pooling Layers
30. Notebook: Layer Visualization
31. Capsule Networks
32. Increasing Depth
33. CNNs for Image Classification
34. Convolutional Layers in PyTorch
35. Feature Vector
36. Pre-Notebook: CNN Classification
37. Notebook: CNNs for CIFAR Image Classification
38. CIFAR Classification Example
39. CNNs in PyTorch
40. Image Augmentation
41. Augmentation Using Transformations
42. Groundbreaking CNN Architectures
43. Visualizing CNNs (Part 1)
44. Visualizing CNNs (Part 2)
45. Summary of CNNs
46. Introduction to GPU Workspaces
47. Workspace Playground
48. GPU Workspace Playground

Back to Home

23. Quiz: Kernels

Kernel convolution

Now that you know the basics of high-pass filters, let's see if you can choose the best one for a given task.

Four different kernels

Kernel convolution

Of the four kernels pictured above, which would be best for finding and enhancing horizontal edges and lines in an image?

a

b

c

d

SOLUTION:

d

udacity2.0 If you need the newest courses Plase add me wechat: udacity6