scicloj.ml VS deep-diamond

This weekend at #ml-study we will have learning sessions about machine learning with Carsten Behring's scicloj.ml library and some other parts of the emerging data science stack.

In here you find links to the draft user guides, partially in form of tutorials, partially of reference guides. https://github.com/scicloj/scicloj.ml

In the last couple of months, the Clojure story for ML has been reorganizing and evolving, mainly around the amazing work of Carsten Behring. This is the current draft, where most activity takes place: https://github.com/scicloj/scicloj.ml It is not stable yet but is worth learning imho. I think the experience with scicloj.ml is very refreshing, comparing to typical Python ML practices.

I had some "classical ML" knowledge and knew a bit about the math behind DL and tensors in general thanks to the book Deep Learning for Programmers showcased in this repo: https://github.com/uncomplicate/deep-diamond (it's not in Rust, and I'm not sure what the current state of it is, though!).

Plase check out clojars, or https://neanderthal.uncomplicate.org/ https://clojurecuda.uncomplicate.org/ https://github.com/uncomplicate/deep-diamond

Do clojure as a side gig or in free time. Let day job pay the bills. If you can, maybe incorporate clojure into work job to solve small problems (https://github.com/clj-python/libpython-clj and https://github.com/scicloj/clojisr provide bridges to/from python and r). There is a lot of effort going into the data science side as well; the scicloj effort has resulted in a lot of growth over the last 2 years. tech.ml.dataset, tech.ml (now scicloj.ml). Dragan has a bunch of excellent stuff in neanderthal and deep diamond. There are also bindings to other jvm libraries from multiple languages.