University of Cambridge > Talks.cam > Machine Learning @ CUED > Explaining Non-Linear Classifier Decisions with application to 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

ℹ️ Information

Explaining Non-Linear Classifier Decisions with application to Deep Learning

Download to your calendar using vCal

If you have a question about this talk, please contact Zoubin Ghahramani .

Understanding and interpreting classification decisions of automated image classification systems is of high value in many applications, as it allows to verify the reasoning of the system and provides additional information to the human expert. Although machine learning methods are solving very successfully a plethora of tasks, they have in most cases the disadvantage of acting as a black box, not providing any information about what made them arrive at a particular decision. This work proposes a general solution to the problem of understanding classification decisions by pixel-wise decomposition of non- linear classifiers. We introduce a methodology that allows to visualize the contributions of single pixels to predictions for kernel-based classifiers over Bag of Words features and for deep neural networks. Applications in computer vision and beyond are provided.

This talk is part of the Machine Learning @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Quastel Midgen LLP Presentation Museum of Archaeology & Anthropology Dept of Earth Sciences

Other talks

TBC Unveiling the curtain with ukubuyisa or go lata: complicated roles of museums and nation states in the cultural repatriation discourse and practice in southern Africa Title to be confirmed Title TBC Title to be confirmed Tea and Coffee Break
 

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