IPAB Workshop - 14/07/2022

Title: What is common to robots, proteins, genomics and video games?

The once familiar story of machine learning, specifically deep-learning, facilitating inordinate progress widely across disciplines quickly evolved into the realisation that they are data hungry and difficult to explain or analyse. In my research, I explore the benefits of incorporating a physics model within the learner to alleviate some of these problems. Although this could be included under the popular buzz-phrase ‘Physics Inspired AI’, my approach has been to use rapid (hence approximate) physics models by learning the discrepancy between their approximations and an accurate (hence computationally intensive) simulation model. In this talk I will be sharing problems, that I am excited by, in protein design and genomics and some progress that we have made. I will describe some of the opportunities and challenges that these problems introduce.

In addition to the above general ideas, I will describe recent work from my group on approximate learning of an NP-hard problem [2], our method for protein design [3] that appears to be the best we know of and a recent paper that uses functional analysis to explain why fixed sampling methods (such as NeRFs) will hit a fundamental roadblock when used to approximate light transport [1]. 

I would appreciate if you attend in person, rather than online. See you tomorrow!

[1] https://homepages.inf.ed.ac.uk/ksubr/research.html#SIGG22

[2] https://homepages.inf.ed.ac.uk/ksubr/research.html#AAAI22

[3] https://arxiv.org/pdf/2109.07925.pdf