SGAI

UK Symposium on Knowledge Discovery
and Data Mining 2018

home | dates | registration | programme | committee
contact | location | previous symposia

BCS

Dr Andy Lundgren, Institute of Cosmology and Gravitation, University of Portsmouth

Keeping LIGO Healthy: Signal Processing versus Machine Learning

Abstract
The detection of gravitational waves requires very complex instruments to achieve unprecedented sensitivity. To keep these instruments healthy, we monitor thousands of diverse sensors and control loops for any changes. I will talk about some of the methods we use, and the challenges we face in trying to transition from classical signal processing and statistical methods to more modern machine learning. Our largest challenge is establishing causality - of all the many correlations and changes we see, which are accidental, which are effects, and which are truly the cause of problems in the LIGO detectors?

Dr. Andrew Lundgren was recently appointed a Reader of Gravitational Wave Science at the Institute of Cosmology and Gravitation at the University of Portsmouth. He is currently chair of the Detector Characterization group of the LIGO Scientific Collaboration. He did his PhD work in theoretical gravity at Cornell before joining LIGO as a postdoc. He was previously at the Albert Einstein Institute in Hannover.

SGAI

Organised by BCS SGAI
The Specialist Group on Artificial Intelligence
http://www.bcs-sgai.org

BCS