CUED Publications database

Now you see me (CME): Concept-based model extraction

Kazhdan, D and Dimanov, B and Jamnik, M and Liò, P and Weller, A (2020) Now you see me (CME): Concept-based model extraction. In: UNSPECIFIED.

Full text not available from this repository.

Abstract

Deep Neural Networks (DNNs) have achieved remarkable performance on a range of tasks. A key step to further empowering DNN-based approaches is improving their explainability. In this work we present CME: a concept-based model extraction framework, used for analysing DNN models via concept-based extracted models. Using two case studies (dSprites, and Caltech UCSD Birds), we demonstrate how CME can be used to (i) analyse the concept information learned by a DNN model (ii) analyse how a DNN uses this concept information when predicting output labels (iii) identify key concept information that can further improve DNN predictive performance (for one of the case studies, we showed how model accuracy can be improved by over 14%, using only 30% of the available concepts).

Item Type: Conference or Workshop Item (UNSPECIFIED)
Uncontrolled Keywords: cs.LG cs.LG
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 11 Sep 2020 21:37
Last Modified: 15 Jul 2021 05:56
DOI: