What is it about?

Genetic programming is used to optimize the structure of mathematical equations. Generally, a limitation of GP is that the evaluation is slow. By implementing GP in JAX, it runs on GPU, which reduces the runtime. Furthermore, Kozax can be applied flexibly to user defined problems and tasks.

Featured Image

Why is it important?

With GP, we can find interpretable solutions that give us more knowledge about the working of a solution compared to standard neural networks. Being able to run on GPU, better solutions can be found for more complex problems.

Read the Original

This page is a summary of: Kozax: Flexible and Scalable Genetic Programming in JAX, July 2025, ACM (Association for Computing Machinery),
DOI: 10.1145/3712255.3726681.
You can read the full text:

Read

Contributors

The following have contributed to this page