There are 1,000+ ways to start with deep learning.
That's great, but most people are overwhelmed by so many choices.
This book will take you 90% of the way. Ignore (almost) everything else and focus here:
packt.link
@Kapoor_Amita @antoniogulli @palsujit
1 of 8
That's great, but most people are overwhelmed by so many choices.
This book will take you 90% of the way. Ignore (almost) everything else and focus here:
packt.link
@Kapoor_Amita @antoniogulli @palsujit
1 of 8
This book is an excellent introduction to machine learning for software developers.
The book starts at the very beginning, so you'll be able to follow regardless of your level of familiarity with machine learning.
I love @fchollet's foreword! Straight to the point!
2 of 8
The book starts at the very beginning, so you'll be able to follow regardless of your level of familiarity with machine learning.
I love @fchollet's foreword! Straight to the point!
2 of 8
The book starts from the very beginning with the first two chapters:
1. Neural Network Foundations with TF
2. Regression and Classification
This is the springboard before starting with deep learning.
3 of 8
1. Neural Network Foundations with TF
2. Regression and Classification
This is the springboard before starting with deep learning.
3 of 8
It then goes into the main deep-learning techniques we currently use:
3. Convolutional Neural Networks
4. Word Embeddings
5. Recurrent Neural Networks
6. Transformers
That will give you what you need to work on vision, audio, and text problems.
4 of 8
3. Convolutional Neural Networks
4. Word Embeddings
5. Recurrent Neural Networks
6. Transformers
That will give you what you need to work on vision, audio, and text problems.
4 of 8
From that point, the book will dive into more advanced techniques, starting with an introduction to Unsupervised Learning:
7. Unsupervised Learning
8. Autoencoders
9. Generative Models
10. Self-Supervised Learning
11. Reinforcement Learning
5 of 8
7. Unsupervised Learning
8. Autoencoders
9. Generative Models
10. Self-Supervised Learning
11. Reinforcement Learning
5 of 8
Here is where things get serious, with more advanced and deep topics:
12. Probabilistic TensorFlow
13. An introduction to AutoML
14. The Math Behind Deep Learning
15. Tensor Processing Unit
16. Other Useful Deep Learning Libraries
17. Graph Neural Networks
6 of 8
12. Probabilistic TensorFlow
13. An introduction to AutoML
14. The Math Behind Deep Learning
15. Tensor Processing Unit
16. Other Useful Deep Learning Libraries
17. Graph Neural Networks
6 of 8
18. Machine Learning Best-Practices
19. TensorFlow 2 Ecosystem
20. Advanced Convolutional Neural Networks
Chapter 18 is one of my favorites! That's a must-read for anyone trying to apply machine learning.
7 of 8
19. TensorFlow 2 Ecosystem
20. Advanced Convolutional Neural Networks
Chapter 18 is one of my favorites! That's a must-read for anyone trying to apply machine learning.
7 of 8
A few other highlights:
1. Great source to understand Transformers.
2. Self-Supervised Learning's popularity makes it hard to ignore: This book will help you with that.
3. TensorFlow + Real-world. There's a ton of practical advice in this book!
packt.link
8 of 8
1. Great source to understand Transformers.
2. Self-Supervised Learning's popularity makes it hard to ignore: This book will help you with that.
3. TensorFlow + Real-world. There's a ton of practical advice in this book!
packt.link
8 of 8
Loading suggestions...