Hey, I’m Jan (or janEbert on GitHub)! I like optimizing loops, thinking in parallel, applying mathematics, and hardcore challenges.
For some years, I’ve been heavily invested in deep learning; my favorite projects include:
- Super Mario World level generation framework
- Reinforcement learning for Durak
- Generative adversarial network framework
I’m currently working at the Helmholtz AI division of the Jülich Supercomputing Centre. Some of the projects I’m currently working on include:
- AlphaNumerics Zero: Using reinforcement learning to optimize a numerical solver.
- Reproducing OpenAI’s DALL-E model.
- MLCommons MLPerf benchmarks.
Recently, I’ve also become interested in Triton, the next machine learning kernel compiler running on your GPU! I hope to be able to invest some time in this.