How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review

Tambon, Florian; Laberge, Gabriel; An, Le; Nikanjam, Amin; Mindom, Paulina Stevia Nouwou; Pequignot, Yann; Khomh, Foutse; Antoniol, Giulio; Merlo, Ettore; Laviolette, François

doi:10.48550/arxiv.2107.12045

Cited by 3 publications

(3 citation statements)

References 209 publications

(269 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, a crucial but not well addressed topic is the relation between approximate computing and the standardization of ML-based systems in safety critical applications. Safety standards for systems ML-based are yet to be formalized [117] and as a result, the impact of approximate computing on the system's certification remains unclear. The examined hardware approximation techniques are deterministic and are not expected to impact the certification process.…”

Section: Conclusion Challenges and Perspectivementioning

confidence: 99%

Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey

et al. 2022

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) are very popular because of their high performance in various cognitive tasks in Machine Learning (ML). Recent advancements in DNNs have brought beyond human accuracy in many tasks, but at the cost of high computational complexity. To enable efficient execution of DNN inference, more and more research works, therefore, exploit the inherent error resilience of DNNs and employ Approximate Computing (AC) principles to address the elevated energy demands of DNN accelerators. This article provides a comprehensive survey and analysis of hardware approximation techniques for DNN accelerators. First, we analyze the state of the art and by identifying approximation families, we cluster the respective works with respect to the approximation type. Next, we analyze the complexity of the performed evaluations (with respect to the dataset and DNN size) to assess the efficiency, the potential, and limitations of approximate DNN accelerators. Moreover, a broad discussion is provided, regarding error metrics that are more suitable for designing approximate units for DNN accelerators as well as accuracy recovery approaches that are tailored to DNN inference. Finally, we present how Approximate Computing for DNN accelerators can go beyond energy efficiency and address reliability and security issues, as well.

show abstract

Section: Conclusion Challenges and Perspectivementioning

confidence: 99%

Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Previous review works have focused on specific techniques-for example, learning-based model predictive control (MPC) (9), iterative learning control (10,11), model-based RL (12), dataefficient policy search (13), imitation learning (14), or the use of RL in robotics (15,16) and in optimal control (17)-without emphasizing the safety aspect. Recent surveys on safe learning control have focused on either control-theoretic (18) or RL (19) approaches and do not provide a unifying perspective.…”

Section: Introductionmentioning

confidence: 99%

Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning

Brunke¹,

Greeff

Hall³

et al. 2022

Annu. Rev. Control Robot. Auton. Syst.

303

136

View full text Add to dashboard Cite

The last half decade has seen a steep rise in the number of contributions on safe learning methods for real-world robotic deployments from both the control and reinforcement learning communities. This article provides a concise but holistic review of the recent advances made in using machine learning to achieve safe decision-making under uncertainties, with a focus on unifying the language and frameworks used in control theory and reinforcement learning research. It includes learning-based control approaches that safely improve performance by learning the uncertain dynamics, reinforcement learning approaches that encourage safety or robustness, and methods that can formally certify the safety of a learned control policy. As data- and learning-based robot control methods continue to gain traction, researchers must understand when and how to best leverage them in real-world scenarios where safety is imperative, such as when operating in close proximity to humans. We highlight some of the open challenges that will drive the field of robot learning in the coming years, and emphasize the need for realistic physics-based benchmarks to facilitate fair comparisons between control and reinforcement learning approaches. Expected final online publication date for the Annual Review of Control, Robotics, and Autonomous Systems, Volume 5 is May 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

show abstract

“…Previous review works focused on specific techniques-for example, learning-based model predictive control (MPC) (7), iterative learning control (ILC) (8,9), model-based RL (10), data-efficient policy search (11), imitation learning (12), or the use of RL in robotics (13,14) and in optimal control (15)-without emphasizing the safety aspect. Recent surveys on safe learning control focus on either control-theoretic (16) or RL approaches (17), and do not provide a unifying perspective.…”

Section: Introductionmentioning

confidence: 99%

Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning

Brunke¹,

Greeff²,

Hall³

et al. 2021

Preprint

View full text Add to dashboard Cite

The last half-decade has seen a steep rise in the number of contributions on safe learning methods for real-world robotic deployments from both the control and reinforcement learning communities. This article provides a concise but holistic review of the recent advances made in using machine learning to achieve safe decision making under uncertainties, with a focus on unifying the language and frameworks used in control theory and reinforcement learning research. Our review includes: learning-based control approaches that safely improve performance by learning the uncertain dynamics, reinforcement learning approaches that encourage safety or robustness, and methods that can formally certify the safety of a learned control policy. As dataand learning-based robot control methods continue to gain traction, researchers must understand when and how to best leverage them in real-world scenarios where safety is imperative, such as when operating in close proximity to humans. We highlight some of the open challenges that will drive the field of robot learning in the coming years, and emphasize the need for realistic physics-based benchmarks to facilitate fair comparisons between control and reinforcement learning approaches.

show abstract

How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review

Cited by 3 publications

References 209 publications

Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey

Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey

Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning

Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning

Contact Info

Product

Resources

About