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
Show this thread
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
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
What hyper-parameter optimization libraries you recommend for hyper-parameter search?
-
KerasTuner. A little known fact is that it can be used for any model, not just Keras models. In fact, it has a built-in Scikit-learn tunerhttps://keras.io/keras_tuner/
- Show replies
New conversation -
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Keras for jax would be great idea.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
TensorFlow is the best
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
JAX is not exactly an ML library
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It seems that PyMC3, another one I like very much, will use JAX in the future.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Jax is excellent for accelerating and parallelizing custom linear algebra. That is why It is going to be big in math optimization community besides ML
-
One example of using Jax to accelerate custom optimization algorithms.
@SingularMattrix https://ieeexplore.ieee.org/document/9361261/ …
End of conversation
New conversation -
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.