ML libraries I've used in the past and liked (besides Keras & TensorFlow): Scikit-learn, XGBoost, and JAX. I want to learn more about JAX going forward. I haven't used it much so far
Show this thread
When you see a library that's a work of love, you can immediately tell. I've learned a lot from Scikit-learn in the past (Keras has many elements inspired by it) and I think I can learn a lot from JAX in the future
-
-
Jax is amazing! The ability to port simple numpy code to JIT compiled code plus vmap makes it very powerful even without the autodiff, which is the cherry on top. A problem that was running for days took seconds thanks to Jax with einsum.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Yes, scikit-learn is, indeed, amazing. It is not just a ML library, but kinda textbook at the same time.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Not familiar with JAX, but we like that mr. keras is still pushing himself.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.