Data Science Seminar: Research and Engineering of Robust Machine Learning Systems
11 Jun 2021, by Sponsored events in25 February 2021 (Online)
Tom Diethe, Applied Science Manager, Amazon Research, Cambridge UK and Honorary Research Fellow at the University of Bristol.
It can now be argued that Machine Learning has become ubiquitous in many industry sectors such as retail, supply chains, advertising, and media. If we are to avoid the so-called “technical debt” associated with deploying ML systems, we need to ensure that they are efficient in long-term usage, robust to changes in the environment, and that potential errors are discoverable. Furthermore, if the data that is collected for model training and prediction is collected from individuals, systems that protect the privacy of individual data in the face of potential adversaries are paramount. In this talk I’ll cover some recent research that aims to tackle these issues, and outline some engineering-based solutions to some of these that are being made available through the AWS SageMaker cloud Machine Learning services.
In cooperation with the Jean Golding Institute, University of Bristol
More information: the Bristol Data Science Seminar Series