Guides / tips / primers for Nx?

Hey @AstonJ I have written a few posts on the DY blog: Blog - DockYard

I also have some posts on Medium through Pragmatic Bookshelf: https://medium.com/@seanmor5

And some tips on my blog: https://seanmoriarity.com/

Finally, there may be something in the works through everybody’s favorite publisher coming out sometime soon

I’m also in the same boat: I’m really interested in everything ML related, but I’m “just an average trained programmer”, who has forgotten all about matrixes in highschool/university.

Although i really really like the content you’re creating @seanmor5, I can’t seem to grok most of it, given my modest background. Anything targetted to mere mortals would be great. Even if it’s a one year course, I’d probably take it, on my own pace.

An nice, I was wondering when we’d be seeing more books on the topic! Can you share whether it’s going to be a book best read before/after Genetic Algorithms in Elixir?

Thanks also for the links to your blog posts, in terms of reading order, do you think it’s worth approaching something like this:

• What is Machine Learning Anyway? - DockYard
• Nx for Absolute Beginners - DockYard
• Up and Running Nx - DockYard
• https://seanmoriarity.com/2021/04/08/axon-deep-learning-in-elixir/
• Getting Started with Axon - DockYard
• Your book (Genetic Algorithms in Elixir (PragProg))
• https://medium.com/pragmatic-programmers/a-short-nx-quiz-3549c6bb826b

Thanks also for all your work on this aspect of Elixir - I have no doubt it’s going to play a big role in Elixir’s continued success

Industry standard advice for getting up to speed as quick as possible on ML is the free fastai course: https://course.fast.ai. I’ve heard it’s required for new OpenAI engineers. I found it to be very helpful in explaining most key concepts.

The Hugging Face transformers course is also a great follow-up: Introduction · Hugging Face. Given that Bumblebee allows you to use pre-trained Hugging Face models, it’s probably a particularly helpful follow-up to the fastai course.

Of course you’re stuck with using Python if you follow these tutorials but it’s probably the best way to start to get a conceptual understanding of all this stuff before using Nx/Axon/Bumblebee.

I got some familiarity with ML via two books, one by The Pragmatic Programmer and one by no starch press. The first uses Python and the second is a visual approach.
Of course, they have nothing to do with Nx… Maybe @seanmor5 will come with a new book (wishful thinking).

Hey @AstonJ
I’m definitely interested to join the book club.

Then, I can only second the book suggested by @bdarla , “Programming Machine Learning”. I’m almost finished it (16 out 20 chapters) and I rewritten all the examples with Nx/Axon so far (althought, I suspect not the best ML code ).

Thanks Michael that’s very helpful!

Did you miss his post @bdarla Maybe in the meantime you can join us for the book club on his first book Genetic Algorithms in Elixir (PragProg) in preparation for it

Awesome, have added you to the list - will PM you when we’ve got enough people interested in it

I’m kinda interested in the book club as well
It would depend on when you plan on doing it, but if it fits my schedule, I’d love to re-read the book and to actually make things with current Nx tooling

When do you start the book club? If it’s in February I can join. I got the book and probably only read a chapter and a half so far.

@polvalente @code-shoily - awesome, have added you both to the list

We’ll probably start the Tailwind book club first (let me know if you want to join that as well!) and so hope to get this one started some time after that depending on when we reach at least 10 people interested (currently at 6 for this book)