Predictive Uncertainty in Deep Learning

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

• Andrey Malinin (University of Cambridge)
• Thursday 03 May 2018, 12:00-13:00
• Department of Engineering - LR5 Lecture Room.

If you have a question about this talk, please contact Anton Ragni.

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 CUED Speech Group Seminars series.

This talk is included in these lists:

• CUED Speech Group Seminars
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Department of Engineering - LR5 Lecture Room
• Guy Emerson's list
• Information Engineering Division seminar list
• PhD related

Note that ex-directory lists are not shown.