Towards Dependability Metrics for Neural Networks

被引：0

作者：

Cheng, Chih-Hong ^{[1
]}

Nuhrenberg, Georg ^{[1
]}

Huang, Chung-Hao ^{[1
]}

Ruess, Harald ^{[1
]}

Yasuoka, Hirotoshi ^{[2
]}

机构：

[1] Fortiss Res Inst Free State Bavaria, Munich, Germany

[2] DENSO CORP, Kariya, Aichi, Japan

来源：

PROCEEDINGS OF THE 2018 16TH ACM/IEEE INTERNATIONAL CONFERENCE ON FORMAL METHODS AND MODELS FOR SYSTEM DESIGN (MEMOCODE) | 2018年

关键词：

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Artificial neural networks (NN) are instrumental in realizing highly-automated driving functionality. An overarching challenge is to identify best safety engineering practices for NN and other learning-enabled components. In particular, there is an urgent need for an adequate set of metrics for measuring allimportant NN dependability attributes. We address this challenge by proposing a number of NN-specific and efficiently computable metrics for measuring NN dependability attributes including robustness, interpretability, completeness, and correctness.

引用

页码：43 / 46

页数：4

共 50 条

[1] Assessing dependability of wireless networks using neural networks
Snow, A.
Rastogi, P.
Weckman, G.
[J]. MILCOM 2005 - 2005 IEEE MILITARY COMMUNICATIONS CONFERENCE, VOLS 1-5, 2005, : 2809 - 2815
[2] Neural metrics - Software metrics in artificial neural networks
Leung, WK
Simpson, R
[J]. KES'2000: FOURTH INTERNATIONAL CONFERENCE ON KNOWLEDGE-BASED INTELLIGENT ENGINEERING SYSTEMS & ALLIED TECHNOLOGIES, VOLS 1 AND 2, PROCEEDINGS, 2000, : 209 - 212
[3] Introduction to dependability metrics
Eusgeld, Irene
Freiling, Felix C.
[J]. DEPENDABILITY METRICS: ADVANCED LECTURES, 2008, 4909 : 1 - +
[4] Metrics Applied to Brain Neural Networks
Delahaye, E. M.
de Arriba, P.
Buenamaizon, R. B.
Graffigna, J. P.
Otoya, R.
Galiana, G.
[J]. ADVANCES IN BIOENGINEERING AND CLINICAL ENGINEERING, SABI 2022, 2024, 105 : 388 - 395
[5] Riemannian metrics for neural networks I: feedforward networks
Ollivier, Yann
[J]. INFORMATION AND INFERENCE-A JOURNAL OF THE IMA, 2015, 4 (02) : 108 - 153
[6] Towards Path Quality Metrics for Overlay Networks
Lareida, Andri
Meier, Daniel
Bocek, Thomas
Stiller, Burkhard
[J]. 2016 IEEE 41ST CONFERENCE ON LOCAL COMPUTER NETWORKS (LCN), 2016, : 156 - 159
[7] Dependability Evaluation of Numerical Control Machine Based on Fuzzy Neural Networks
Zhang Hong-bin
Jia Zhi-xin
Xi An-min
[J]. 2009 INTERNATIONAL CONFERENCE ON FUTURE BIOMEDICAL INFORMATION ENGINEERING (FBIE 2009), 2009, : 453 - 456
[8] Towards the evolution of neural networks
Macukow, B
Grzenda, M
[J]. OPTO-ELECTRONICS REVIEW, 2001, 9 (03) : 316 - 319
[9] Software Dependability Assessment Using DevOps Metrics
Popentiu-Vladicescu, Florin
Albeanu, Grigore
[J]. 2022 6TH INTERNATIONAL CONFERENCE ON BUSINESS AND INFORMATION MANAGEMENT, ICBIM, 2022, : 168 - 172
[10] Software Security, Privacy, and Dependability Metrics and Measurement
Hatzivasilis, George
Papaefstathiou, Ioannis
Manifavas, Charalampos
[J]. IEEE SOFTWARE, 2016, 33 (04) : 46 - 54

← 1 2 3 4 5 →