Shane Josias

SJ_Nips1b.jpg

I am a junior lecturer in Applied Mathematics at Stellenbosch University, South Africa. I am also a PhD candidate, where I focus on the computational aspects and out-of-distribution properties of continuous-time normalising flows.

Prior to the above, I've worked as a software engineer writing complex events processing applications, as well as adding functionality to the framework on top of which those applications run. In addition, I also worked on various aspects of database integration.

I completed an MSc in Applied Mathematics at Stellenbosch University early 2020, where I tackled properties like a long-tailed data distribution and semantic ambiguity in visual relationship recognition. My experience with visual relationship recognition has inspired an interest in robust and generalisable visual representations.

news

Dec 8, 2022 Awarded a poster prize at the 65th Annual SAMS Congress.
Oct 24, 2022 Research assistant position available [closed].
Oct 23, 2022 Invited to attend the Nobel Symposium on Predictability in Science in the Age of AI.
Oct 6, 2022 Hosted the Standard Bank Lab Hackathon.

selected publications

  1. Jacobian norm regularisation and conditioning in neural ODEs
    Shane Josias, and Willie Brink
    Communications in Computer and Information Science, 2022
  2. Class-Selective Mini-Batching and Multitask Learning for Visual Relationship Recognition
    Shane Josias, and Willie Brink
    SAIEE Africa Research Journal, 2021