Explaining Inaccurate Predictions of Models through k-Nearest Neighbors

Zeki Bilgin, Murat Gunestas

Abstract

Deep Learning (DL) models exhibit dramatic success in a wide variety of fields such as human-machine interaction, computer vision, speech recognition, etc. Yet, the widespread deployment of these models partly depends on earning trust in them. Understanding how DL models reach a decision can help to build trust on these systems. In this study, we present a method for explaining inaccurate predictions of DL models through post-hoc analysis of k-nearest neighbours. More specifically, we extract k-nearest neighbours from training samples for a given mispredicted test instance, and then feed them into the model as input to observe the model’s response which is used for post-hoc analysis in comparison with the original mispredicted test sample. We apply our method on two different datasets, i.e. IRIS and CIFAR10, to show its feasibility on concrete examples.

Download


Paper Citation


in Harvard Style

Bilgin Z. and Gunestas M. (2021). Explaining Inaccurate Predictions of Models through k-Nearest Neighbors.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-484-8, pages 228-236. DOI: 10.5220/0010257902280236


in Bibtex Style

@conference{icaart21,
author={Zeki Bilgin and Murat Gunestas},
title={Explaining Inaccurate Predictions of Models through k-Nearest Neighbors},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2021},
pages={228-236},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010257902280236},
isbn={978-989-758-484-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Explaining Inaccurate Predictions of Models through k-Nearest Neighbors
SN - 978-989-758-484-8
AU - Bilgin Z.
AU - Gunestas M.
PY - 2021
SP - 228
EP - 236
DO - 10.5220/0010257902280236