Jonathan Deaton

Research Engineer at Google X.

headshot.jpg

San Mateo, California

I’m a senior software engineer and machine learning researcher at X broadly interested in probabilistic ML.

I believe robust ML systems require theoretical foundations in probabilistic reasoning and statistics. I enjoy translating cutting-edge ML methods into practical applications.

My current interests include Equivariant Euclidian GNNs for molecular modeling, generative language models in biology, and diffusion/score-based generative modeling.

I have a background in Bioengineering and Computer Science at Stanford where I also completed premedical requirements.

I was a gymnast for 15 years, competing for Stanford Mens Gymnastics and represented the Unites States on the Junior National Team at competitions in China, England, and Colombia.

news

Nov 2, 2021 Joined Google X! Applied ML research in computational biology. :dna:
Sep 2, 2019 Joined Google Health working on AI in computer vision for medicine.
Mar 16, 2018 Starting Masters in Computer Science at Stanford!

selected publications

  1. Underspecification presents challenges for credibility in modern machine learning
    Alexander DAmour, Katherine Heller, Dan Moldovan, and 34 more authors
    Journal of Machine Learning Research, 2020
  2. Addressing the real-world class imbalance problem in dermatology
    Wei-Hung Weng, Jonathan Deaton, Vivek Natarajan, and 2 more authors
    Proceedings of the Machine Learning for Health NeurIPS Workshop, PMLR, 2020
  3. Mini‐Metagenomics and Nucleotide Composition Aid the Identification and Host Association of Novel Bacteriophage Sequences
    Jonathan Deaton, Feiqiao Brian Yu, and Stephen R Quake
    Advanced biosystems, 2019