Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!

Grab it

Dive into a comprehensive 10-hour video tutorial on TensorFlow and deep learning fundamentals using Python. Master the essentials of regression and classification in machine learning through hands-on coding exercises. Begin with an introduction to deep learning concepts, neural networks, and TensorFlow basics. Progress through creating and manipulating tensors, building neural network regression models, and exploring classification techniques. Learn to prepare datasets, construct models, evaluate performance, and conduct experiments to improve results. Gain practical experience with Google Colab, visualize model predictions, and understand key evaluation metrics. By the end, acquire the skills to build, train, and optimize both regression and classification models using TensorFlow.

Syllabus

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