- Grokking Deep Learning
This is a fantastic book that assumes no prerequisites other than knowing python, and takes you through the fundamentals of DL. It has very intuitive and easy to follow explanations, and doesn't use any libraries other than NumPy, so you're building the whole thing yourself, from scratch.
- Deep Learning With Python
This is kind of the opposite of the previous one, it doesn't go into math and theory, instead it guides you through building several practical projects with a very simple to use DL library(keras). It's a great way to gain practical experience in addition to theory from the previous book. Also has no prerequisites other than python, and makes it very easy to get started.
- 3blue1brown videos on neural networks:
Extremely brilliant high-level concise overview of how ANNs work. I highly recommend you get started here. You should also check out his videos on calulus and linear algebra, they're fantastic way to learn the math you need.
- Khan Academy videos - one of the easiest ways to learn the math prerequisites.
Probability and Statistics:
- Hands-On Machine Learning with Scikit-Learn and TensorFlow
I haven't read this one yet, but it looks very promising, and a lot of people seem to find it very useful.
- Andrew Ng's Coursera course
Everyone knows about this one, I just think every article on AI resources should mention it, one of the most popular ways to get started with ML.
- New MIT courses on Self-Driving cars and AGI
- The Master Algorithm
Excellent high-level overview of ML field and algorithms.
Other great stuff:
- Artificial Intelligence: A Modern Approach
The leading textbook in Artificial Intelligence. It's not the fastest way to get started, but it's considered one of the best AI textbooks ever written.
- Stanford AI course (CS 188)
Brilliant course based on AIMA. Not DL, but solid fundamentals of AI and ML.
- Couple of great playlists on DL, just to complete the collection:
Machine Learning with Python
Neural Networks Demystified
For reinforcement learning, I hear Barto and Sutton is very readable, but I haven't read it myself. You can just pick the concepts up by reading papers. The introduction in the Deep Q-Learning paper is not great, but it's how I first learned the concept.
When I first started using scikit-learn, I was overwhelmed with the number of classes and options available. I just chose some basic classifiers I was familiar with and stuck with most of the default settings. The book explains many of the other models and when they would be useful, but also spends a lot of time exploring the datasets (using pandas), preprocessing data and building data pipelines, finding the best hyperparameters, best ways to evaluate a models performance, etc. The library feels less like a big bag of algorithms now and more like a cohesive data pipeline.
Fresh book recommendations delivered straight to your inbox every Thursday.