learning_path_1.md

Here is the suggested learning path provided by the mephistopheies

1. start with https://www.coursera.org/learn/machine-learning, it is the easiest one, but it gives everything but doesn't explains why it works, so you almost don't need to understand math (but there are a lot of formulas there, but Ng's superpower is to explain such stuff) then:
2. if you want to recap calculus, then take
   • https://www.coursera.org/learn/single-variable-calculus
   • https://www.coursera.org/learn/differentiation-calculus
   • https://www.coursera.org/learn/integration-calculus
   • https://www.coursera.org/learn/applications-calculus
3. if you want to refresh linear algebra https://www.edx.org/course/linear-algebra-foundations-to-frontiers-0
4. same for probability theory https://www.edx.org/course/introduction-to-probability-0
5. same for statistics https://lagunita.stanford.edu/courses/course-v1:OLI+ProbStat+Open_Jan2017/about
6. or short version of all of these https://www.coursera.org/specializations/mathematics-machine-learning but i'm not sure about it -)
7. then it is time for machine learning courses:
8. intro:
   • https://lagunita.stanford.edu/courses/HumanitiesSciences/StatLearning/Winter2016/about
   • https://www.edx.org/course/learning-data-caltechx-cs1156x-0
   • https://lagunita.stanford.edu/courses/course-v1:ComputerScience+MMDS+SelfPaced/about
9. advanced
   • https://ru.coursera.org/specializations/aml
   • https://ru.coursera.org/specializations/probabilistic-graphical-models
   • http://web.stanford.edu/class/cs224n/
10. deep learning:
11. intro:
    • https://www.deeplearning.ai/ Ng's style
12. advanced
    • http://cs231n.stanford.edu/ computer vision
    • http://cs224d.stanford.edu/
13. books (better to read after some courses):
    • https://www.amazon.com/Machine-Learning-Probabilistic-Perspective-Computation/dp/0262018020
    • https://www.amazon.com/Elements-Statistical-Learning-Prediction-Statistics/dp/0387848576