| Description | |
|---|---|
| Pros | - Beginner friendly - one of the first and best courses in ML - Theory-driven and in-depth coverage of algorithms |
| Cons | - Taught in Matlab/Octave (more research-oriented language than Python) - Course made in 2011, introduction-level course to ML |
| In Details | - Useful resources section including informative Websites / ML Datasets / Useful papers - Assignment and Project solutions |
| Description | |
|---|---|
| Pros | - Taught entirely in Python ( + other ML libraries such as Tensorflow or Keras) - Course made in 2017-2018 |
| Cons | |
| In Details | Assignment and Project solutions |
-
Tensorflow - crash course by Google
- Mathematics for machine learning, Marc Peter Deisenroth et al.
- The Elements of Statistical Learning, Trevor Hastie, Robert Tibshirani, Jerome Friedman
- Deep Learning with Python, Francois Chollet + GitHub link of Jupyter notebooks in the book
amitness/learning - github repo containing a quite exhaustive list of online courses + e-books ossu/data-science - github repo EbookFoundation/free-programming-books - github repo rushter/data-science-blogs: github repo of lists of data science blogs vinta/awesome-python: curated list of Python frameworks, libraries, ressources...
Data skeptic on spotify including
-Podcast of entry level : MINI series
-Podcast of intermediate to advanced level : interviews with ML experts
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent