Helpful Links

Python modules & tools

Python 2.7

The SciPy module for science & math computing in python

The MatPlotLib module for making plots in python

scikit-learn for python data mining and machine learning

The Jupyter notebook for scientific computing

Theano is a Python library that integrates with NumPy to let you optimize multi-dimensional array math efficiently.

Python tutorials

Google's Python Class is a great tutorial on Python.

The Beginner's Guide to Python

The Beginner's Guide to MatPlotLib

Machine Learning Toolkits

The Deep Learning list of software links

Weka data mining toolkit

The libsvm support vector machine tool kit

HTK hidden Markov model toolkit

Java NNS neural net toolkit

Matlab NNSYSID neural net toolkit

NNinExcel neural nettoolkit

Torch is a scientific computing framework with wide support for machine learning algorithms.

TensorFlow is Google's open source software library (intended for DNNs) for numerical computation using data flow graphs.


University of California Irvine Machine Learning Dataset Repository has many classic datasets.

The Movielens collaborative filtering dataset

The Jester collaborative filtering joke dataset

Datasets for the book The Elements of Statistical Learning

The Yale Face dataset - The database contains 5760 single light source images of 10 subjects each seen under 576 viewing conditions (9 poses x 64 illumination conditions).

The University of Iowa Instrument Recording repository - If you want to learn the difference between different musical instrument sounds, this is a useful set.

The Statlab collection of datasets - Has things like a pre-classified dataset containing 11,000 web pages from 11 different categories and data on salaries of Major League Baseball players.

Datasets used in the book Pattern Recognition and Machine Learning by Chris Bishop


The Elements of Statistical Learning

Reinforcement Learning: An Introduction by Richard S. Sutton (Author), Andrew G. Barto (Author)

Pattern Recognition and Machine Learning by Christopher Bishop

Adaptation in Natural and Artificial Systems by John Holland 

Data Mining: Practical Machine Learning Tools and Techniques (Second Edition) - Ian H. Witten, Eibe Frank

Neural Networks for Pattern Recognition by Christopher M. Bishop

Neural Networks: A Comprehensive Foundation (2nd Edition) by Simon Haykin

Support Vector Machines and other kernel-based learning methods by John Shawe-Taylor Nello Cristianin

Causality, by Judea Pearl


American Association of Artificial Intelligence (AAAI)  page on Machine Learning


The Deep Learning website

Machine Learning Journal

Journal of Machine Learning Research

AI Magazine


Association of Artificial Intelligence Confrence (AAAI)

Neural Information Processing Systems (NIPS)

Machine Learning for Signal Processing (MLSP)

International Conference on Machine Learning and its Applications (ICMLA)

Research Groups & Researchers

UC Irvine's Center for Machine Learning

Carnegie Mellon University's Machine Learning Department

Northwestern University's Qualitative Reasoning Group

The Reinforcement Learning Repository

Christopher Bishop (heads machine learning at Microsoft Research Cambridge)

Michal Jordan (he is a big guy in graphical models for learning)

Judea Pearl (known for his work on Bayesian reasoning)

Lawrence Rabiner (speech recognition and Markov models)

Robert Schapire (known for his work on Boosting)

Richard Sutton (he is a big guy in Reinforcement Learning)

Vladimir Vapnik (known for his work on Support Vector Machines)