Robust Explainability A tutorial on gradient-based attribution methods for deep neural networks

被引：43

作者：

Nielsen, Ian E. ^{[1
]}

Dera, Dimah ^{[2
]}

Rasool, Ghulam ^{[3
,4
,5
]}

Ramachandran, Ravi P. ^{[6
,7
]}

Bouaynaya, Nidhal Carla ^{[8
,9
]}

机构：

[1] Rowan Univ, Glassboro, NJ 08028 USA

[2] Univ Texas Rio Grande Valley, Elect & Comp Engn, Edinburg, TX 78500 USA

[3] H Lee Moffitt Canc Ctr & Res Inst, Machine Learning Dept, Tampa, FL 33612 USA

[4] Rehabil Inst Chicago, Chicago, IL 60611 USA

[5] Northwestern Univ, Evanston, IL 60208 USA

[6] AT&T Bell Labs, Speech Res Dept, Atlanta, GA USA

[7] Rowan Univ, Dept Elect & Comp Engn, Glassboro, NJ 08028 USA

[8] Rowan Univ, ECE, Glassboro, NJ 08028 USA

[9] Rowan Univ, Res & Grad Studies, Glassboro, NJ 08028 USA

来源：

IEEE SIGNAL PROCESSING MAGAZINE | 2022年 / 39卷 / 04期

关键词：

DECISIONS;

D O I：

10.1109/MSP.2022.3142719

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The rise in deep neural networks (DNNs) has led to increased interest in explaining their predictions. While many methods for this exist, there is currently no consensus on how to evaluate them. On the other hand, robustness is a popular topic for deep learning (DL) research; however, it has been hardly talked about in explainability until very recently. © 1991-2012 IEEE.

引用

页码：73 / 84

页数：12

共 50 条

[1] Gradient-based feature-attribution explainability methods for spiking neural networks
Bitar, Ammar
Rosales, Rafael
Paulitsch, Michael
FRONTIERS IN NEUROSCIENCE, 2023, 17
[2] A Gradient-Based Algorithm to Deceive Deep Neural Networks
Xie, Tianying
Li, Yantao
NEURAL INFORMATION PROCESSING (ICONIP 2019), PT IV, 2019, 1142 : 57 - 65
[3] Correcting gradient-based interpretations of deep neural networks for genomics
Antonio Majdandzic
Chandana Rajesh
Peter K. Koo
Genome Biology, 24
[4] Correcting gradient-based interpretations of deep neural networks for genomics
Majdandzic, Antonio
Rajesh, Chandana
Koo, Peter K.
GENOME BIOLOGY, 2023, 24 (01)
[5] Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning
Wang, Hanjing
Joshi, Dhiraj
Wang, Shiqiang
Ji, Qiang
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 12044 - 12053
[6] SpotOn: A Gradient-based Targeted Data Poisoning Attack on Deep Neural Networks
Khare, Yash
Lakara, Kumud
Mittal, Sparsh
Kaushik, Arvind
Singhal, Rekha
2023 24TH INTERNATIONAL SYMPOSIUM ON QUALITY ELECTRONIC DESIGN, ISQED, 2023, : 391 - 398
[7] Structural optimization by gradient-based neural networks
Iranmanesh, A
Kaveh, A
INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING, 1999, 46 (02) : 297 - 311
[8] Gradient-based PIV using neural networks
I. Kimura
Y. Susaki
R. Kiyohara
A. Kaga
Y. Kuroe
Journal of Visualization, 2002, 5 : 363 - 370
[9] Gradient-based PIV using neural networks
Kimura, I
Susaki, Y
Kiyohara, R
Kaga, A
Kuroe, Y
JOURNAL OF VISUALIZATION, 2002, 5 (04) : 363 - 370
[10] Robust Beamforming With Gradient-Based Liquid Neural Network
Wang, Xinquan
Zhu, Fenghao
Huang, Chongwen
Alhammadi, Ahmed
Bader, Faouzi
Zhang, Zhaoyang
Yuen, Chau
Debbah, Merouane
IEEE WIRELESS COMMUNICATIONS LETTERS, 2024, 13 (11) : 3020 - 3024

← 1 2 3 4 5 →