Learn how to get started with JAX in this Crash Course. JAX is NumPy on the CPU, GPU, and TPU, with great automatic differentiation for high-performance machine learning research. Get your Free Token for AssemblyAI Speech-To-Text API 👇https://www.assemblyai.com/?utm_source=youtube&utm_medium=referral&utm_campaign=yt_pat_43 Colab: https://colab.research.google.com/drive/1_-e5MUrGfS7r1veKiVADuiLI_9e1UAih?usp=sharing Website: https://jax.readthedocs.io/en/latest/index.html JAX blog post: https://www.assemblyai.com/blog/why-you-should-or-shouldnt-be-using-jax-in-2022/ ▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬▬ 🖥️ Website: https://www.assemblyai.com/ 🐦 Twitter: https://twitter.com/AssemblyAI 🦾 Discord: https://discord.gg/Cd8MyVJAXd ▶️ Subscribe: null 🔥 We're hiring! Check our open roles: https://www.assemblyai.com/careers ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 00:00 Intro & Outline 01:22 What is JAX 02:55 Speed comparison 05:00 Drop-in Replacement for NumPy 06:56 jit(): just-in-time compiler 11:32 Limitations of JIT 14:35 grad(): Automatic Gradients 19:57 vmap(): Automatic Vectorization 21:48 pmap(): Automatic Parallelization 22:18 Example Training Loop 24:38 What’s the catch? #MachineLearning #DeepLearning