Course review: JAX accelerated machine learning research via composable function transformations in Python

I was searching the net and quite by accident found a post that said Tensorflow, developed by Google, is being replaced by a library called Jax, which is also made by Google.

I personally have been studying Tensorflow for the last six months or so in an attempt to learn as much as I can about how to engage in deep learning with this library. There is so much to learn about Tensorflow because this library can carry out a multitude of deep learning tasks to include computer vision, sound, and language to name just a few of the genres of this fantastic library. In addition, the documentation for Tensorflow is pretty good, but not as good as the documentation for the sci-kit learn library, if I do say so myself.

I am not sure exactly when Tensorflow will be phased out, but decided that I had better get a head start and begin learning Jax. I therefore took a small course on Jax, hosted by Class Central, which was composed of a YouTube video that lasted just short of an hour.

I tried out all of the code presented in the course and, unfortunately, some of the code in the Jax library is already deprecated, so I was unable to complete the last section of code because my knowledge of Jax is not good enough to replace deprecated code.

What is Jax?

JAX (Just After eXecution) is a recent machine/deep learning library developed by DeepMind and is…