JAX is a machine learning framework by Google.
The core of JAX handles things like calculating gradients or vectorizing operations. But there are libraries called Flax and Flax-Linen that implement neural networks on top of JAX.
There is an official tutorial that implements JAX from scratch, if you want to learn how it works. You can find it at https://docs.jax.dev/en/latest/autodidax.html.
Citation
If you find this work useful, please cite it as:
@article{yaltirakli,
title = "JAX",
author = "Yaltirakli, Gokberk",
journal = "gkbrk.com",
year = "2025",
url = "https://www.gkbrk.com/jax"
}
Not using BibTeX? Click here for more citation styles.
IEEE Citation Gokberk Yaltirakli, "JAX", March, 2025. [Online]. Available: https://www.gkbrk.com/jax. [Accessed Mar. 12, 2025].
APA Style Yaltirakli, G. (2025, March 12). JAX. https://www.gkbrk.com/jax
Bluebook Style Gokberk Yaltirakli, JAX, GKBRK.COM (Mar. 12, 2025), https://www.gkbrk.com/jax