On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems
Open accessThe DOI matches its Crossref record; 14 of the 15 references it cites were found in a registry or an index.
Abstract
An increasing number of critical functionalities integrated in embedded critical systems rely on deep learning (DL) technology. This article summarizes certain key aspects of DL’s intrinsic stochastic and training-data-dependent nature that are at odds with current domain-specific functional safety standards. We exemplify how redundancy and diversity of neural networks can help to reconcile DL technology and functional safety requirements.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“However, IEC 61508:2010 is interpreted such that it does not recommend the use of AI methods, even for diagnostics, solutions as part of safety-related systems are based on performing system decompositions [10] so that e.g., a non-AI-based deterministic monitor adopts its safety requirements together with those of the AI-based component it is monitoring [20].”
From A requirements model for AI algorithms in functional safety-critical systems with an explainable self-enforcing network from a developer perspective (2024) · cites this paper as [20]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
Kendall, A., & Gal, Y. (2017) · arXiv · doi:10.48550/arxiv.1703.04977 · Cited by 3,088
Aleatory or epistemic? Does it matter?
Kiureghian, A. D., & Ditlevsen, O. (2009) · Structural Safety · doi:10.1016/j.strusafe.2008.06.020 · Cited by 2,454
Dong, X., Yu, Z., Cao, W., Shi, Y., & Ma, Q. (2020) · Frontiers of Computer Science · doi:10.1007/s11704-019-8208-z · Cited by 1,928
The German Traffic Sign Recognition Benchmark: A multi-class classification competition
Stallkamp, J., Schlipsing, M., Salmen, J., & Igel, C. (2011) · The 2011 International Joint Conference on Neural Networks · doi:10.1109/ijcnn.2011.6033395 · Cited by 1,144
Deep Reinforcement Learning framework for Autonomous Driving
Sallab, A. E., Abdou, M., Perot, E., & Yogamani, S. (2017) · Electronic Imaging · doi:10.2352/issn.2470-1173.2017.19.avm-023 · Cited by 1,045
Generative Adversarial Active Learning for Unsupervised Outlier Detection
Liu, Y., Li, Z., Zhou, C., Jiang, Y., Sun, J., Wang, M., & He, X. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2905606 · Cited by 335
Rethinking Importance Weighting for Deep Learning under Distribution ShiftPreprint
Fang, T., Lu, N., Niu, G., & Sugiyama, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.04662 · Cited by 142
Depth Uncertainty in Neural NetworksPreprint
Antorán, J., Allingham, J. U., & Hernández-Lobato, J. M. (2020) · arXiv (Cornell University) · doi:10.17863/cam.69875 · Cited by 115
What Are Bayesian Neural Network Posteriors Really Like?
Izmailov, P., Vikram, S., Hoffman, M. D., & Wilson, A. G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.14421 · Cited by 93
Timing of Autonomous Driving Software: Problem Analysis and Prospects for Future Solutions
Alcon, M., Tabani, H., Kosmidis, L., Mezzetti, E., Abella, J., & Cazorla, F. J. (2020) · IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS) · doi:10.1109/rtas48715.2020.000-1 · Cited by 84
Self-citation
Research works printed but not linked: 1
- Schneider, V. Artificial intelligence and functional safety -a summary of the current challenges. Report, TÜV SUD Rail GmbH, 27th May 2021
Cited by
Corradini, F., Flammini, F., & Antonucci, A. (2023) · International Symposium on Trustworthy Autonomous Systems (TAS) · doi:10.1145/3597512.3599716 · Cited by 9
Klüver, C., Greisbach, A., Kindermann, M., & Püttmann, B. (2024) · Security and Safety · doi:10.1051/sands/2024020 · Cited by 8
“…the use of AI methods, even for diagnostics, solutions as part of safety-related systems are based on performing system decompositions [10] so that e.g. , a non-AI-based deterministic monitor adopts its safety requirements together with those of the AI-based component it is monitoring [20].”
AI-FSM: Towards Functional Safety Management for Artificial Intelligence-based Critical Systems
Fernández, J., Agirre, I., Perez-Cerrolaza, J., Belategi, L., Adell, A., Donzella, C., & Abella, J. (2024) · HAL · Cited by 6
Self-citationPerformance Isolation for Inference Processes in Edge GPU SystemsPreprint
Martín, J. J., Flich, J., & Hernández, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.07600 · Cited by 6
Zero-Space In-Weight and In-Bias Protection for Floating-Point-based CNNs
Ruiz, J., Andrés, D. P., Saiz-Adalid, L.-J., & Gracia-Morán, J. (2024) · European Dependable Computing Conference · doi:10.1109/edcc61798.2024.00028 · Cited by 4
Metadata
- Authors
- Brando, A., Serra, I., Mezzetti, E., Cazorla, F. J., Perez-Cerrolaza, J., & Abella, J.
- Affiliations
- Barcelona Supercomputing Center (ES)
- Ikerlan (ES)
- ORCID
- Venue
- Computer
- Published
- 2023-05
- Volume
- 56
- Issue
- 5
- Pages
- 41-50
- ISSN
- 0018-9162 (ISSN-L)
- 1558-0814
- OpenAlex
- W4367044454
- Cited by
- 9
- References
- 15
- Citations by year
- 2026: 3 · 2025: 2 · 2024: 3 · 2023: 1
- FWCI
- 1.55
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- Locations
- Computer (publishedVersion)
- UPCommons institutional repository (Universitat Politècnica de Catalunya) (submittedVersion, cc-by-nc-nd)
- Funders
- European Research Council (772773)
- Horizon Europe Program (101069595)
- Spanish Ministry of Science and Innovation (PID2019-107255GBC21/AEI/10.13039/501100011033)
- Topics
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Safety Systems Engineering in Autonomy
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Hardware and Architecture › Real-Time Systems Scheduling
- Keywords
- deep learning, functional safety, safety-critical systems, embedded systems, safety standards
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.

