Source: Deep Learning on Medium
Deep Learning Books you should read in 2020
What are the best books on deep learning right now?
With the rise of machine learning and data science, applied everywhere and changing every industry, it’s no wonder that experts in machine learning are handsomely paid and much looked after. If you’ve already read a couple of data science and machine learning books, it’s time to focus on deep learning: Neural Networks, Keras, Tensorflow, Scikit-learn, etc.
If you’re just getting into Machine Learning there’s the one book I can’t stop recommending. It’s simply great!
Introduction to Machine Learning with Python is a smooth introduction into machine learning and deep learning. It doesn’t assume any knowledge about coding and Python in particular and it introduces fundamental concepts and applications of machine learning, discussing various methods through examples. That’s the best book I’ve ever seen for an entry level Deep Learning Engineer.
If you’ve already completed a couple of machine learning projects, you know something about Keras or Tensorflow, you’ve used scikit-learn then I have two recommendations for you.
Hands-On Machine Learning with Scikit-Learn and TensorFlow covers all the fundamentals in deep learning, with working code and amazing visualizations full of colours. It’s really fun to read, it is a complete 400+ pages guide through classification, clustering, neural networks and other methods with many examples to try for yourself.
Deep Learning with Python is all about using Keras as your primary framework for Deep Learning. Francois Chollet, the creator of Keras, gives a great overview of this easy-to-use and efficient frameworks. From MNIST to CNNs, through computer vision to NLP. All in one place, given in a concise form.
Deep Learning and the Game of Go has as a goal teaching you neural networks and reinforcement learning using Go as a guiding example. During the course of the book, you’ll learn how to create your own bot/agent able to play the game, which is pretty awesome.
Deep Learning is a must-read if you’re serious about deep learning. It doesn’t give you code, assuming you’re able to code everything yourself at this stage, but it gives you explanations of why certain layers work better, how to optimize hyperparameters, what network architectures to use, etc. It gives an up-to-date account of deep learning.
Machine Learning: a Probabilistic Perspective is about mathematical perspective on machine learning. Hard to read, but a great reference for any mathematical issues you might have, when you build deep learning models. It’s very useful as an encyclopedic reference. For experts only.