Explore accelerated machine learning research through composable function transformations in Python with JAX in this 52-minute seminar presented by Matthew Johnson from Google. Delivered as part of the Machine Learning Advances and Applications Seminar series at the Fields Institute, learn how JAX can enhance and streamline your machine learning workflows, offering powerful tools for researchers and practitioners alike.
JAX- Accelerated Machine Learning Research via Composable Function Transformations in Python
Overview
Syllabus
JAX: accelerated machine learning research via composable function transformations in Python
Taught by
Fields Institute
Related Courses
-
Machine Learning for Accounting with Python
-
Support Vector Machines in Python, From Start to Finish
-
Discovering Black-Box Optimizers via Evolutionary Meta-Learning
-
Experiment Management for Machine Learning
-
Introduction to Python Libraries and Algorithms for Machine Learning
-
Obfuscation Classification via Machine Learning for JavaScript, Python, and PHP
