27.8 C
New York

P2ExNet: Patch-based Prototype Explanation Network. (arXiv:2005.02006v1 [cs.AI])


[Submitted on 5 May 2020]

Download PDF

Abstract: Deep learning methods have shown great success in several domains as they
process a large amount of data efficiently, capable of solving complex
classification, forecast, segmentation, and other tasks. However, they come
with the inherent drawback of inexplicability limiting their applicability and
trustworthiness. Although there exists work addressing this perspective, most
of the existing approaches are limited to the image modality due to the
intuitive and prominent concepts. Conversely, the concepts in the time-series
domain are more complex and non-comprehensive but these and an explanation for
the network decision are pivotal in critical domains like medical, financial,
or industry. Addressing the need for an explainable approach, we propose a
novel interpretable network scheme, designed to inherently use an explainable
reasoning process inspired by the human cognition without the need of
additional post-hoc explainability methods. Therefore, class-specific patches
are used as they cover local concepts relevant to the classification to reveal
similarities with samples of the same class. In addition, we introduce a novel
loss concerning interpretability and accuracy that constraints P2ExNet to
provide viable explanations of the data including relevant patches, their
position, class similarities, and comparison methods without compromising
accuracy. Analysis of the results on eight publicly available time-series
datasets reveals that P2ExNet reaches comparable performance when compared to
its counterparts while inherently providing understandable and traceable

Submission history

From: Dominique Mercier [view email]
Tue, 5 May 2020 08:45:43 UTC (753 KB)

Source: http://arxiv.org/abs/2005.02006

Related articles


Recent articles