Roadmap to ML

This is my roadmap to go from an undergraduate CS and math background to a very good understanding of Machine Learning and Deep Learning concepts, and more importantly to successfully apply ML and DL. I will put here everything I’ve done (in italic), I’m doing (in bold), and I’m planning on doing (normal text) in order to reach that goal.

Courses

  1. Andrew Ng’s Coursera Machine Learning course
  2. fast.ai course part 1 v3
  3. Udacity Intro to deep learning with PyTorch
  4. fast.ai course part 2 v2
  5. (when it’s out) fast.ai part 2 v3
  6. fast.ai machine learning course
  7. deeplearning.ai Coursera Deep Learning Specialization

Personal projects

  1. Write a deep learning web app
  2. Blog about deep learning, preferably about a technical subject (like a dive in fast.ai source code)
  3. Contribute to the fast.ai library
  4. Take part in Kaggle competitions and reach top 10%
  5. Freelance to gain real world experience in deep learning

Books and blogs

  1. Deep learning, Ian Goodfellow et al.
  2. Neural Networks and Deep Learning, Michael Nielsen
  3. Colah’s blog
  4. Distill
  5. (when it comes out) Terence Parr and Jeremy Howard book (some material available at explained.ai)

General CS and Software Engineering resources

  1. Data Structures and Algorithms in Python by Michael T. Goodrich
  2. Cracking the Coding Interview by Gayle Laakmann McDowell
  3. Python 3 : Deep Dive (part 1 and part 2).