1 - Intro/hello/how to approach this video 1:49
2 - MODULE 0 START (TensorFlow/deep learning fundamentals) 0:02
3 - [Keynote] 1. What is deep learning? 4:37
4 - [Keynote] 2. Why use deep learning? 9:38
5 - [Keynote] 3. What are neural networks? 10:22
6 - [Keynote] 4. What is deep learning actually used for? 8:36
7 - [Keynote] 5. What is and why use TensorFlow? 7:54
8 - [Keynote] 6. What is a tensor? 3:34
9 - [Keynote] 7. What we're going to cover 4:31
10 - [Keynote] 8. How to approach this course 5:32
11 - 9. Creating our first tensors with TensorFlow 18:46
12 - 10. Creating tensors with tf Variable 7:07
13 - 11. Creating random tensors 9:39
14 - 12. Shuffling the order of tensors 9:39
15 - 13. Creating tensors from NumPy arrays 11:56
16 - 14. Getting information from our tensors 11:54
17 - 15. Indexing and expanding tensors 12:34
18 - 16. Manipulating tensors with basic operations 5:32
19 - 17. Matrix multiplication part 1 11:54
20 - 18. Matrix multiplication part 2 13:29
21 - 19. Matrix multiplication part 3 10:01
22 - 20. Changing the datatype of tensors 6:56
23 - 21. Aggregating tensors 9:49
24 - 22. Tensor troubleshooting 6:12
25 - 23. Find the positional min and max of a tensor 9:28
26 - 24. Squeezing a tensor 3:00
27 - 25. One-hot encoding tensors 5:46
28 - 26. Trying out more tensor math operations 4:46
29 - 27. Using TensorFlow with NumPy 5:42
30 - MODULE 1 START (neural network regression) 0:10
31 - [Keynote] 28. Intro to neural network regression with TensorFlow 7:31
32 - [Keynote] 29. Inputs and outputs of a regression model 8:57
33 - [Keynote] 30. Architecture of a neural network regression model 7:55
34 - 31. Creating sample regression data 12:47
35 - 32. Steps in modelling with TensorFlow 20:13
36 - 33. Steps in improving a model part 1 6:02
37 - 34. Steps in improving a model part 2 9:25
38 - 35. Steps in improving a model part 3 12:32
39 - 36. Evaluating a model part 1 ("visualize, visualize, visualize") 7:24
40 - 37. Evaluating a model part 2 (the 3 datasets) 11:01
41 - 38. Evaluating a model part 3 (model summary) 17:16
42 - 39. Evaluating a model part 4 (visualizing layers) 7:16
43 - 40. Evaluating a model part 5 (visualizing predictions) 9:14
44 - 41. Evaluating a model part 6 (regression evaluation metrics) 8:07
45 - 42. Evaluating a regression model part 7 (MAE) 5:50
46 - 43. Evaluating a regression model part 8 (MSE) 3:18
47 - 44. Modelling experiments part 1 (start with a simple model) 13:49
48 - 45. Modelling experiments part 2 (increasing complexity) 11:29
49 - 46. Comparing and tracking experiments 10:18
50 - 47. Saving a model 9:23
51 - 48. Loading a saved model 10:16
52 - 49. Saving and downloading files from Google Colab 6:17
53 - 50. Putting together what we've learned 1 (preparing a dataset) 13:30
54 - 51. Putting together what we've learned 2 (building a regression model) 13:22
55 - 52. Putting together what we've learned 3 (improving our regression model) 15:43
56 - [Code] 53. Preprocessing data 1 (concepts) 9:35
57 - [Code] 54. Preprocessing data 2 (normalizing data) 10:55
58 - [Code] 55. Preprocessing data 3 (fitting a model on normalized data) 7:39
59 - MODULE 2 START (neural network classification) 0:09
60 - [Keynote] 56. Introduction to neural network classification with TensorFlow 8:23
61 - [Keynote] 57. Classification inputs and outputs 6:36
62 - [Keynote] 58. Classification input and output tensor shapes 6:22
63 - [Keynote] 59. Typical architecture of a classification model 9:36
64 - 60. Creating and viewing classification data to model 11:30
65 - 61. Checking the input and output shapes of our classification data 4:37
66 - 62. Building a not very good classification model 12:10
67 - 63. Trying to improve our not very good classification model 9:13
68 - 64. Creating a function to visualize our model's not so good predictions 15:07
69 - 65. Making our poor classification model work for a regression dataset