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