/ML-material

Useful machine learning materials

ML-material

Useful machine learning materials

Textbooks:

Machine learning in general:

  1. Machine Learning, T. Mitchell.
  2. Pattern Recognition and Machine Learning, C. Bishop.
  3. Machine Learning: a Probabilistic Perspective, K. Murphy.

Linear Algebra:

  1. Linear Algebra, D. Cherney, et al.

Statistics:

  1. All of Statistics: A Concise Course in Statistical Inference, L. Wasserman.
  2. High-Dimensional Probability: An Introduction with Applications in Data Science, R. Vershynin.

Statistical Machine Learning:

  1. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, T. Hastie, et al.

Learning Theory:

  1. Understanding Machine Learning: From Theory to Algorithms Shalev-Shwartz, Ben-David.

Optimization:

  1. Convex Optimization, S. Boyd and L. Vandenberghe.
  2. Convex Optimization: Algorithms and Complexity, S. Bubeck.
  3. Optimization Methods for Large-Scale Machine Learning, L, Bottou, et al.

Deep Learning:

  1. Deep Learning, I. Goodfellow and Y. Bengio and A. Courville

Information Theory:

  1. Elements of Information Theory, T. M. Cover, J. A. Thomas

Online Courses:

  1. CS229 - Machine Learning at Stanford, Andrew Ng.
  2. CNN Tutorial from CS231n at Stanford.

Tutorials of Deep Learning Frameworks:

  1. TensorFlow, Keras.
  2. PyTorch.
  3. MXNet.

Distributed Machine Learning:

Tutorials:

  1. Distributed training with TensorFlow.
  2. Distributed training with PyTorch.
  3. OpenMPI.

Sample Projects:

  1. A simple Parameter Server prototype in PyTorch.
  2. Horovod. A distributed training framework developed by Uber.

Cloud Computing Resources:

  1. AWS.
  2. GoogleCloud.
  3. Azure.
  4. CloudLab, for researchers in academia, totally free.