Thread by @svpino

"Hands-On Machine Learning..." is —without a doubt— my favorite machine learning book.

It's not only a great reference, but it's the type of book that you can easily read cover to cover!

If you want to start from a solid foundation, look no further.

💰 amzn.to/2KPuRAo

The book assumes that you have some experience with:

▫️ Python programming
▫️ NumPy
▫️ Pandas
▫️ Matplotlib

For a deeper dive, it expects you to have a reasonable understanding of calculus, linear algebra, probabilities, and statistics.

The book is organized into two parts:

▫️ The Fundamentals of Machine Learning
▫️ Neural Networks and Deep Learning

Here is the outline of what's covered: 👇

Part I - The Fundamentals of Machine Learning

▫️ What is machine learning?
▫️ Steps in a machine learning project
▫️ Learning by fitting a model to data
▫️ Optimizing a cost function
▫️ Handling, cleaning and preparing data
▫️ Selecting and engineering features
(...)

(...)
▫️ Selecting a model
▫️ Tuning hyperparameters
▫️ Cross-validation
▫️ Challenges with machine learning
▫️ Common learning algorithms
▫️ Curse of dimensionality
▫️ Unsupervised learning techniques

Part II - Neural Networks and Deep Learning

▫️ What is a neural net?
▫️ Building and training neural nets
▫️ TensorFlow and Keras
▫️ Feedforward neural nets
▫️ Convolutional networks
▫️ Recurrent networks
▫️ LSTM
▫️ Encoder / Decoders
▫️ Transformers
(...)

(...)
▫️ Autoencoders
▫️ Generative adversarial networks
▫️ Training techniques
▫️ Reinforcement learning
▫️ Loading and preprocessing a large amount of data
▫️ Training and deploying models at scale

When I bought the book, I felt intimidated by it: it's thick and heavy!

At the time, almost every machine learning book I had was hard to read —full of formulas and lingo.

This book is different.

This book is for you and me.

Now, I open it every week.

I'm either looking for something specific, or I simply read a couple of pages.

It never ceases to amaze me how much knowledge it packs!

Thanks, @aureliengeron! I really love what you did here!