BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Leveraging Inductive Bias for Physically Consistent Machine Learni
 ng: Applications in Engineered Systems - Dr Olga Fink\, EPFL\, Switzerland
DTSTART:20251107T160000Z
DTEND:20251107T170000Z
UID:TALK235483@talks.cam.ac.uk
CONTACT:46601
DESCRIPTION:Abstract:\n\nIn the field of engineered systems\, the integrat
 ion of machine learning has enabled the development of advanced predictive
  models that ensure the reliable operation of complex assets. However\, ch
 allenges such as sparse\, noisy\, and incomplete data necessitate the inte
 gration of prior knowledge and inductive bias to improve generalization\, 
 interpretability\, and robustness.\n\nInductive bias\, the set of assumpti
 ons embedded in machine learning models\, plays a crucial role in guiding 
 these models to generalize effectively from limited training data to real-
 world scenarios. In engineered systems\, where physical laws and domain-sp
 ecific knowledge are fundamental\, the use of inductive bias can significa
 ntly enhance a model’s ability to predict system behavior under diverse 
 operating conditions. By embedding physical principles into learning algor
 ithms\, inductive bias reduces the reliance on large datasets\, ensures th
 at model predictions are physically consistent\, and enhances both the gen
 eralizability and interpretability of the models.\n\nThis talk will explor
 e various forms of inductive bias applied in engineered systems\, with a p
 articular focus on heterogenous spatio-temporal\, and physics-informed gra
 ph neural networks\, as well as symbolic regression with applications in v
 irtual sensing\, modelling multi-body dynamical systems and anomaly detect
 ion.\n\nOlga Fink\n\nAssistant Professor of Intelligent Maintenance and Op
 erations Systems\, EPFL\, Lausanne\n\nShort Bio:\n\nOlga Fink has been ass
 istant professor at EPFL since March 2022\, heading the Intelligent Mainte
 nance and Operations Systems (IMOS) laboratory. Olga’s research focuses 
 on Physics-Informed Machine Learning\, Multi-Modal Learning\, Domain Adapt
 ation and Generalization\, and Reinforcement Learning for Intelligent Main
 tenance and Operations of Infrastructure and Complex Assets.\n\nBefore joi
 ning EPFL faculty\, Olga was assistant professor of intelligent maintenanc
 e systems at ETH Zurich from 2018 to 2022\, being awarded the prestigious 
 professorship grant of the Swiss National Science Foundation (SNSF). Betwe
 en 2014 and 2018 she was heading the research group “Smart Maintenance
 ” at the Zurich University of Applied Sciences (ZHAW).\n\nOlga received 
 her Ph.D. degree from ETH Zurich\, and Diploma degree from Hamburg Univers
 ity of Technology. She has gained valuable industrial experience as reliab
 ility engineer with Stadler Bussnang AG and as reliability and maintenance
  expert with Pöyry Switzerland Ltd.\n\nOlga is serving as an editorial bo
 ard member of several prestigious journals\, including Mechanical Systems 
 and Signal Processing\, Engineering Applications of Artificial Intelligenc
 e and Reliability Engineering and System Safety.\n\nIn 2019\, Olga earned 
 the distinction of being recognized as a young scientist of the World Econ
 omic Forum. In 2020\, 2021\, and 2024 she was honored as a young scientist
  of the World Laureate Forum. In 2023\, she was distinguished as a fellow 
 by the Prognostics and Health Management Society
LOCATION:JDB Seminar Room\, CUED
END:VEVENT
END:VCALENDAR