A Caltech Library Service

Interpretable Machine Teaching via Feature Feedback

Su, Shihan and Chen, Yuxin and Mac Aodha, Oisin and Perona, Pietro and Yue, Yisong (2017) Interpretable Machine Teaching via Feature Feedback. In: NIPS 2017 Workshop on Teaching Machines, Robots, and Humans, December 4-9, 2017, Long Beach, CA.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


A student’s ability to learn a new concept can be greatly improved by providing them with clear and easy to understand explanations from a knowledgeable teacher. However, many existing approaches for machine teaching only give a limited amount of feedback to the student. For example, in the case of learning visual categories, this feedback could be the class label of the object present in the image. Instead, we propose a teaching framework that includes both instance-level labels as well as explanations in the form of feature-level feedback to the human learners. For image categorization, our feature-level feedback consists of a highlighted part or region in an image that explains the class label. We perform experiments on real human participants and show that learners that are taught with feature-level feedback perform better at test time compared to existing methods.

Item Type:Conference or Workshop Item (Paper)
Related URLs:
URLURL TypeDescription
Mac Aodha, Oisin0000-0002-5787-5073
Perona, Pietro0000-0002-7583-5809
Yue, Yisong0000-0001-9127-1989
Additional Information:The authors thank Google for supporting the Visipedia project, and kind donations from Northrop Grumman, Bloomberg, and AWS Research Credits. Yuxin Chen was supported in part by a Swiss NSF Mobility Postdoctoral Fellowship.
Funding AgencyGrant Number
Northrop Grumman CorporationUNSPECIFIED
Amazon Web ServicesUNSPECIFIED
Swiss National Science Foundation (SNSF)UNSPECIFIED
Record Number:CaltechAUTHORS:20180622-113758617
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:87329
Deposited By: Caroline Murphy
Deposited On:23 Jun 2018 16:02
Last Modified:09 Mar 2020 13:19

Repository Staff Only: item control page