gimseng
Links and relations to other code-based open source learning project
1.a. Curate a list of GitHub-hosted code examples/exercises. From the top of my head, I could think of joelgrus and ageron. Both are fantastic resources.
b. Since these other resources are great open source codes, perhaps we could incorporate some of them (with appropriate credit and source links of course).
- How do we distinguish our project, as compared to other projects from above in 1? Some suggestions/ideas:
a. Those textbook-to-github-hosted-codes examples are typically curated and maintained by the writers (with some contributions from everyone). However, for us, we are mainly community-driven, so there might be a difference in how we approach exercise. Perhaps a feature (or a bug?) for us is we might start with some solution that is very rough, purely styled and full of bugs, but the hope is we can slowly polish it as a community and learn good practice and style, and eventually reach a great code solution. It is a little bit like a learning code journey rather than trying to get the perfect code from the get-go.
b. Moreover, I'd really like this project to have a large contribution pools, for people from different levels and backgrounds. Since none of us is master in most things, this could give the project a large scope. I envision that we might branch into a few main umbrellas of either topics or coding-expertise, such that it will transcend a particular textbook or a particular field.
I found d2L.ai to be a fantastic resource as well. I think we are philosophically similar to their approach.
Link to https://github.com/dibgerge/ml-coursera-python-assignments as discussed in #35
Also found https://course.fullstackdeeplearning.com recently, very similar to our philosophy/method.
There is another website https://pyimagesearch.com which contains deep learning tutorials based on projects but one needs a good grip in python to understand them. Also, coursera had started some courses on Guided Projects with hands on coding experience.
Thanks @aarpit1010 , also another good resource: https://github.com/curiousily/Deep-Learning-For-Hackers
Another fantastic resource is : https://github.com/Avik-Jain/100-Days-Of-ML-Code All the cheatsheets / explanatory-posters are great !
Also there are other ML paper implementations that are not updated and throw errors when users try to run them now. Those could be added to this section as well.
