Home > Research > Publications & Outputs > Highly interpretable hierarchical deep rule-bas...

Electronic data

  • ASOC_106310_edit_report

    Rights statement: This is the author’s version of a work that was accepted for publication in Applied Soft Computing. 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 Applied Soft Computing, 92, 2020 DOI: 10.1016/j.asoc.2020.106310

    Accepted author manuscript, 1.56 MB, PDF document

    Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

Links

Text available via DOI:

View graph of relations

Highly interpretable hierarchical deep rule-based classifier

Research output: Contribution to journalJournal articlepeer-review

E-pub ahead of print

Standard

Highly interpretable hierarchical deep rule-based classifier. / Gu, Xiaowei; Angelov, Plamen.

In: Applied Soft Computing, Vol. 92, 20.04.2020.

Research output: Contribution to journalJournal articlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{7b041c7d767c43198d76c76a5978a4b0,
title = "Highly interpretable hierarchical deep rule-based classifier",
abstract = "Pioneering the traditional fuzzy rule-based (FRB) systems, deep rule-based (DRB) classifiers are able to offer both human-level performance and transparent system structure on image classification problems by integrating zero-order fuzzy rule base with a multi-layer image-processing architecture that is typical for deep learning. Nonetheless, it is frequently observed that the inner structure of DRB can become over sophisticated and not interpretable for humans when applied to large-scale, complex problems. To tackle the issue, one feasible solution is to construct a tree structural classification model by aggregating the possibly huge number of prototypes identified from data into a much smaller number of more descriptive and highly abstract ones. Therefore, in this paper, we present a novel hierarchical deep rule-based (H-DRB) approach that is capable of summarizing the less descriptive raw prototypes into highly generalized ones and self-arranging them into a hierarchical prototype-based structure according to their descriptive abilities. By doing so, H-DRB can offer high-level performance and, most importantly, full transparency and human-interpretability on various problems including large-scale ones. The proposed concept and generical principles are verified through numerical experiments based on a wide variety of popular benchmark image sets. Numerical results demonstrate that the promise of H-DRB.",
keywords = "Deep rule-based, Hierarchical, Prototype-based, Self-organizing",
author = "Xiaowei Gu and Plamen Angelov",
note = "This is the author{\textquoteright}s version of a work that was accepted for publication in Applied Soft Computing. 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 Applied Soft Computing, 92, 2020 DOI: 10.1016/j.asoc.2020.106310",
year = "2020",
month = apr,
day = "20",
doi = "10.1016/j.asoc.2020.106310",
language = "English",
volume = "92",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier Science B.V.",

}

RIS

TY - JOUR

T1 - Highly interpretable hierarchical deep rule-based classifier

AU - Gu, Xiaowei

AU - Angelov, Plamen

N1 - This is the author’s version of a work that was accepted for publication in Applied Soft Computing. 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 Applied Soft Computing, 92, 2020 DOI: 10.1016/j.asoc.2020.106310

PY - 2020/4/20

Y1 - 2020/4/20

N2 - Pioneering the traditional fuzzy rule-based (FRB) systems, deep rule-based (DRB) classifiers are able to offer both human-level performance and transparent system structure on image classification problems by integrating zero-order fuzzy rule base with a multi-layer image-processing architecture that is typical for deep learning. Nonetheless, it is frequently observed that the inner structure of DRB can become over sophisticated and not interpretable for humans when applied to large-scale, complex problems. To tackle the issue, one feasible solution is to construct a tree structural classification model by aggregating the possibly huge number of prototypes identified from data into a much smaller number of more descriptive and highly abstract ones. Therefore, in this paper, we present a novel hierarchical deep rule-based (H-DRB) approach that is capable of summarizing the less descriptive raw prototypes into highly generalized ones and self-arranging them into a hierarchical prototype-based structure according to their descriptive abilities. By doing so, H-DRB can offer high-level performance and, most importantly, full transparency and human-interpretability on various problems including large-scale ones. The proposed concept and generical principles are verified through numerical experiments based on a wide variety of popular benchmark image sets. Numerical results demonstrate that the promise of H-DRB.

AB - Pioneering the traditional fuzzy rule-based (FRB) systems, deep rule-based (DRB) classifiers are able to offer both human-level performance and transparent system structure on image classification problems by integrating zero-order fuzzy rule base with a multi-layer image-processing architecture that is typical for deep learning. Nonetheless, it is frequently observed that the inner structure of DRB can become over sophisticated and not interpretable for humans when applied to large-scale, complex problems. To tackle the issue, one feasible solution is to construct a tree structural classification model by aggregating the possibly huge number of prototypes identified from data into a much smaller number of more descriptive and highly abstract ones. Therefore, in this paper, we present a novel hierarchical deep rule-based (H-DRB) approach that is capable of summarizing the less descriptive raw prototypes into highly generalized ones and self-arranging them into a hierarchical prototype-based structure according to their descriptive abilities. By doing so, H-DRB can offer high-level performance and, most importantly, full transparency and human-interpretability on various problems including large-scale ones. The proposed concept and generical principles are verified through numerical experiments based on a wide variety of popular benchmark image sets. Numerical results demonstrate that the promise of H-DRB.

KW - Deep rule-based

KW - Hierarchical

KW - Prototype-based

KW - Self-organizing

U2 - 10.1016/j.asoc.2020.106310

DO - 10.1016/j.asoc.2020.106310

M3 - Journal article

VL - 92

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

ER -