University of Cambridge > Talks.cam > Rouse Ball Lectures > Causality-Inspired Machine Learning: A Path to More Robust AI Systems

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

Causality-Inspired Machine Learning: A Path to More Robust AI Systems

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact HoD Secretary, DPMMS.

The pursuit of reliable and robust machine learning has become a central focus, with statistics and data science playing pivotal roles in its advancement. We explore connections between distributional robustness and causality, providing methodological insights to enhance the reliability of AI systems. We examine the broader implications of these concepts through a case study in digital health and emphasize the crucial need for validating machine learning and AI algorithms in real-world applications.

This talk is part of the Rouse Ball Lectures series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Best Engineering College in Delhi Engineering Department Construction Talks Danby Society

Other talks

AI-Refined Radiative Transfer Modelling to Retrieve Biophysical Variables in Forests Graph Neural Networks for skillful weather forecasting Fluorogenetic interrogation of epigenetic pathways Statistics Clinic Lent 2024 V Restoring communication with intracortical brain-computer interfaces The Compilation Game: Unifying AI, Hardware Design, Quantum, Climate Modelling, and Verification
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity