course-nlp VS ML-Workspace

fast.ai also has an NLP course.

fastai already has a course that covers traditional nlp as well

My question: How do you think high-quality online resources such as https://missing.csail.mit.edu/, https://fullstackopen.com/en/, http://allendowney.github.io/ThinkBayes2/, https://www.fast.ai/2019/07/08/fastai-nlp/ compare to the online education from OMSCS? Do any of my reasons above ring false for you?

8 - Code-First Introduction to Natural Language Processing - fast.ai

fast.ai are doing the best work democratizing AI (machine learning and neural networks), including natural language

Can't recommend the course enough and it's incredible that such a quality resource is available for essentially zero cost

https://github.com/fastai/course-nlp

https://www.youtube.com/playlist?list=PLtmWHNX-gukKocXQOkQju...

fastai nlp course

[1] Chapter on LSI from Introduction to Information Retrieval [2] A Code-First Approach to Natural Language Processing by fast.ai [3] Computational Linear Algebra by fast.ai [4] https://www.cc.gatech.edu/~hpark/papers/nmf_book_chapter.pdf

NLP

Also check out: https://github.com/ml-tooling/ml-workspace, it a nice open source project with lots of packages ready to use.

The other option - no reason why you couldn't host something on the desktop machine - web based IDE like R-Studio or Python - have a look at ml-workspace - https://github.com/ml-tooling/ml-workspace that runs in Docker and would provide interfaces for both Python and R, VSCode as well as a GPU accelerated variant for doing Tensorflow etc - either Windows or Linux can support Docker containers (Linux is less trouble apparently - I only have played with it in Linux personally)

It will be a web based IDE dev kit (like Jupyter Hub, or JupyterLab) if you are familiar with them)

I'll stick with https://github.com/ml-tooling/ml-workspace, is a docker with all tools installed, also the option of using GPU, so I think is better than only for debian. This way anyone can use it.