University of Cambridge > Talks.cam > NLIP Seminar Series > Predictive Uncertainty in Deep Learning

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

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

ℹī¸ Information

Predictive Uncertainty in Deep Learning

Download to your calendar using vCal

If you have a question about this talk, please contact Andrew Caines .

Estimating uncertainty is important to improving the safety of AI systems. Current methods do not explicitly model predictive uncertainty arising from distributional mismatch between training and test data, either conflating distributional uncertainty with data uncertainty or implicitly modeling it via model uncertainty. Thus, a new framework for modeling predictive uncertainty, called Prior Networks (PNs), is proposed. Prior Networks allow each source of predictive uncertainty – data, distributional and model uncertainty, to be modeled explicitly. This work examines predictive uncertainty in the context of classification. Prior Networks are evaluated on the tasks of identifying out-of-distribution (OOD) samples and detecting misclassification on the MNIST dataset, where they are found to outperform previous methods.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Register in advance at https://cam-ac-uk.zoom.us/meeting/register/tJcocOCrrzsvGtHekrkuOl2nTRs9zeAjSZT1 Faculty of Education, 184 Hills Road, Cambridge, room GS3 Webinar - https://zoom.us/j/92208122335?pwd=UGJIN3k3TnJYNWloNFBhVDlOaldZUT09

Other talks

Together Now: Cooperation and Collaboration in Social Art Practice Morning Break Nationalising Oil and Knowledge in Iran: Labour, Decolonisation and Colonial Modernity, 1933–51 Optimal metric and approximation of free boundary minimal surfaces Coming soon Rothschild Public Lecture | Forty years of causal inference: Report of a great-grandfather
 

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