Tons of resources online will get you distracted a lot, a good way is to have your own learning path and keep focus. I got this idea from two people:
Thanks a lot to them for sharing their own experiences.
This blog is a guideline that I will continue update. Side by side, I may post learning logs with details on what I learned.
Stage 1 - Foundations
This is to lay a good foundation for later machine learning, which includes:
Probability and Statistics
Bloomberg ML EDU course which I am following at this moment: https://bloomberg.github.io/foml/#about
More resources on statistics: https://cims.nyu.edu/~cfgranda/pages/DSGA1002_fall15/index.html
Problems and solutions: http://karlrosaen.com/ml/hw/
Some supporting materials:
- Mathematics background check: https://davidrosenberg.github.io/mlcourse/Notes/prereq-questions/math-questions.pdf
- Simple statistics crib-sheet: http://www.gatsby.ucl.ac.uk/teaching/courses/ml1-2008/cribsheet.pdf
Machine learning 101
Now you can have a glance of what machine learning is, and use your mathematics learned to understand concepts and practice on easy tasks.
Machine learning by Andrew Ng: https://www.coursera.org/learn/machine-learning
Python Machine Learning: https://github.com/rasbt/python-machine-learning-book-2nd-edition
There are some good podcasts:
- Talking machine podcasts:https://www.thetalkingmachines.com/
- Becoming a data scientist podcasts: https://www.becomingadatascientist.com/category/podcast/
- The Master Algorithm: https://player.fm/series/data-skeptic/the-master-algorithm
To complete this stage, 5 months are recommended.