Programming Machine Learning (PragProg)

Machine learning can be intimidating, with its reliance on math and algorithms that most programmers don't encounter in their regular work. The good news is that it doesn't have to be that hard. Take a hands-on approach, writing the Python code yourself, without any libraries to obscure what's really going on. Iterate on your design, and add layers of complexity as you go.

Paolo Perrotta @nusco

edited by Katharine Dvorak @katied

Machine learning can be intimidating, with its reliance on math and algorithms that most programmers don’t encounter in their regular work. The good news is that it doesn’t have to be that hard. Take a hands-on approach, writing the Python code yourself, without any libraries to obscure what’s really going on. Iterate on your design, and add layers of complexity as you go.

Build an image recognition application from scratch with supervised learning. Predict the future with linear regression. Dive into gradient descent, a fundamental algorithm that drives most of machine learning. Create perceptrons to classify data. Build neural networks to tackle more complex and sophisticated data sets. Train and refine those networks with backpropagation and batching. Layer the neural networks, eliminate overfitting, and add convolution to transform your neural network into a true deep learning system.

Start from the beginning and code your way to machine learning mastery.


“Let me say that I think this is a brilliant book. It takes the reader step by step through the thinking behind machine learning. Combine that with Paolo’s fun approach and this is the book I’d suggest every machine learning neophyte start with.”

Russ Olsen, Author, Getting Clojure and Eloquent Ruby


  • Full details: Search
  • View this book’s portal and details on how to post errata and suggestions here.

Don’t forget you can get 35% off with your Devtalk discount! Just use the coupon code “devtalk.com" at checkout :+1:

2 Likes

Dear Paolo Perrotta - I really loved your Programming Machine Learning book.

What would be good follow-up books for your book?

Maybe something that goes deeper into CNN/RNN topics, Or stuff not covered in your book (refining existing models with Keras, …,). Maybe something with re-inforcement learning or other non-supervised forms?

Best regards,
Dominik

1 Like

Thank you, Dominik! (And speaking of compliments, I appreciate the Machinarium avatar!)

Whenever people ask me for a good follow-up, I usually recommend all the courses from Andrew Ng. Some are free, others require a subscription–but the free ones are the best IMHO. He’s a world-class authority on ML, and his style is ideal if you want to take the leap into a more theoretical approach to the topic.

If you want to stay concrete, or maybe get more concrete and learn by doing, then your best bet might be doing Kaggle competitions. They’re a great way to get your hands dirty.

Let me know how it goes!

1 Like

Hehe, yep, I’m a big Machinarium fan :slight_smile:

Thank you for your recommendations! Will look into the courses of Andrew Ng! Today I started my first Kaggle demo competition. So thank you for that pointer as well!

All the best from Austria,
D.R.

2 Likes