# Resources for learning data science and machine learning

Recently a few people have asked me for the best courseware for learning machine learning. The truth is there is no simple answer. Certainly the machine learning course by Andrew Ng is a good place to start, but most people I know are looking for more depth. Here are some resources I’ve collected. This list will be expanded and refined over time:

## Select online courses for machine learning

Coursera: “Machine Learning” - Andrew Ng (the most popular)

Coursera: “Neural Networks for Machine Learning” - Geoffrey Hinton (for a deep dive)

Lectures for course on reinforcement learning.

The are a gazillion other data science / machine learning online courses. Many of them are very short there or only superficially introduce topics and show you barebones implementations. Someone reviewed a large number of them here

## Learning Python

Think Python: How to Think Like a Computer Scientist

PHY 546: Python for Scientific Computing - Course taught by Michael Zingale at Stony Brook University, contains many interactive Jupyter notebooks.

Code Like a Pythonista: Idiomatic Python

Learn Python the Hard Way - I used this book somewhat and like how it was faster pace than other books

Introduction to machine learning in Python with scikit-learn (video series)

## Pandas

Pandas tutorials from Wes McKinney, lead Pandas developer

## General programming / algorithms

*Problem Solving with Algorithms and Data Structures in Python* from Interactive Programming

MIT Introduction to Algorithms online course

## Accessible and information dense research papers

Check out the awesome graphical papers at *Distill*, such as:

## Cool blog posts

*Conv-nets : a Modular Perspective* - Christopher Olah

*Understanding Convolutions * - Christopher Olah

*The Unreasonable Effectiveness of Recursive Neural Networks* - Andre Karpathy

*Practical seq2seq* - Suriyadeepan Ram

Tensorflow Neural Network playground

## Important papers for deep learning

*Attention and Augmented Recurrent Neural Networks*

*Inceptionism: running “Deep Dream” at Google Research *

## YouTube channels

Some people love em, some people hate em.

Two minute papers (100,000+ subscribers!)

Siraj Rival - (225,000+ subscribers)

## Textbooks

Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems by Aurélien Géron - One of my personal favorite books - if you already know Python well and want to get hands on with machine learning quickly and up to speed on the latest methods & techniques, this is an excellent book.

http://www.deeplearningbook.org/ Free draft online, by Ian Goodfellow and Yoshua Bengio and Aaron Courville

“Information Theory, Inference, and Learning Algorithms” by David J.C. MacKay

Kevin Murphy’s *Machine learning: a Probabilistic Perspective*

Bishop’s *Pattern Recognition and Machine Learning*

Hastie, Tibshirani, and Friedman’s *The Elements of Statistical Learning*

Kuhn and Johnson, *Applied Predictive Modeling*

Sebastian Raschka, *Python Machine Learning *(free, online)
Pattern Classification 3rd Edition by R. Duda, P.E. Hart and D.G Stork

Machine Learning: A Bayesian and Optimization Perspective (Net Developers) - by Sergios Theodoridis

David Barber’s *Bayesian Reasoning and Machine Learning*

Foundations of Machine Learning, Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar

Learning From Data, Yaser S. Abu-Mostafa, Malik Magdon-Ismail, Hsuan-Tien Lin - one of the most popular texts, presents a more rigorous statistical learning perspective.

All of Statistics, Larry Wasserman

Probabilistic Graphical Models: Principles and Techniques, Daphne Koller, Nir Friedman

Gaussian Processes For Machine Learning, Carl Edward Rasmussen, Christopher K. I. Williams [free pdf]

Building Machine Learning Systems with Python

Amazon.com: Convex Optimization (9780521833783): Stephen Boyd, Lieven Vandenberghe: Books<

## Cool articles for lay audiences

The Extraordinary Link Between Deep Neural Networks and the Nature of the Universe

## Books for lay audiences

The Master Algorithm : How the Quest for the Ultimate Learning Machine Will Remake Our World by Pedro Domingos

The Signal and the Noise: Why So Many Predictions Fail–but Some Don’t by Nate Silver

Superintelligence: Paths, Dangers, Strategies by Nick Bostrom (a must read!)

Life 3.0: Being Human in the Age of Artificial Intelligence by Max Tegmark

On Intelligence by Jeff Hawkins – highly recommended!!

## Select bootcamps:

Insight Data Science Foundation’s Program - 8 weeks, online, paid

Ivy Data Science - variable timeframes, paid, online, onsite

Signal Data Science - Berkeley, pay 20% of salary for one year after you get a job.

The Data Incubator (NYC, DC, SF) for recent Ph.D.s