Towards explainable deep neural networks (xDNN)

Angelov, Plamen and Soares, Eduardo (2020) Towards explainable deep neural networks (xDNN). Neural Networks, 130. pp. 185-194. ISSN 0893-6080

[img]
Text (xDNN_Neural_Network_Journal_Revised)
xDNN_Neural_Network_Journal_Revised.pdf - Accepted Version
Restricted to Repository staff only until 11 July 2021.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB)

Abstract

In this paper, we propose an elegant solution that is directly addressing the bottlenecks of the traditional deep learning approaches and offers an explainable internal architecture that can outperform the existing methods, requires very little computational resources (no need for GPUs) and short training times (in the order of seconds). The proposed approach, xDNN is using prototypes. Prototypes are actual training data samples (images), which are local peaks of the empirical data distribution called typicality as well as of the data density. This generative model is identified in a closed form and equates to the pdf but is derived automatically and entirely from the training data with no user- or problem-specific thresholds, parameters or intervention. The proposed xDNN offers a new deep learning architecture that combines reasoning and learning in a synergy. It is non-iterative and non-parametric, which explains its efficiency in terms of time and computational resources. From the user perspective, the proposed approach is clearly understandable to human users. We tested it on challenging problems as the classification of different lighting conditions for driving scenes (iROADS), object detection (Caltech-256, and Caltech-101), and SARS-CoV-2 identification via computed tomography scan (COVID CT-scans dataset). xDNN outperforms the other methods including deep learning in terms of accuracy, time to train and offers an explainable classifier.

Item Type:
Journal Article
Journal or Publication Title:
Neural Networks
Additional Information:
This is the author’s version of a work that was accepted for publication in Neural Networks. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neural Networks, 130, 2020 DOI: 10.1016/j.neunet.2020.07.010
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/2800/2805
Subjects:
ID Code:
146136
Deposited By:
Deposited On:
12 Aug 2020 15:15
Refereed?:
Yes
Published?:
Published
Last Modified:
15 Sep 2020 05:13