Sources of risk of AI systems

A Steimers, M Schneider - … Journal of Environmental Research and Public …, 2022 - mdpi.com
Artificial intelligence can be used to realise new types of protective devices and assistance
systems, so their importance for occupational safety and health is continuously increasing …

A systematic literature review on hardware reliability assessment methods for deep neural networks

MH Ahmadilivani, M Taheri, J Raik… - ACM Computing …, 2024 - dl.acm.org
Artificial Intelligence (AI) and, in particular, Machine Learning (ML), have emerged to be
utilized in various applications due to their capability to learn how to solve complex …

Understanding and mitigating hardware failures in deep learning training systems

Y He, M Hutton, S Chan, R De Gruijl… - Proceedings of the 50th …, 2023 - dl.acm.org
Deep neural network (DNN) training workloads are increasingly susceptible to hardware
failures in datacenters. For example, Google experienced" mysterious, difficult to identify …

Investigating data representation for efficient and reliable convolutional neural networks

A Ruospo, E Sanchez, M Traiola, I O'connor… - Microprocessors and …, 2021 - Elsevier
Abstract Nowadays, Convolutional Neural Networks (CNNs) are widely used as prediction
models in different fields, with intensive use in real-time safety-critical systems. Recent …

State of health assessment for echelon utilization batteries based on deep neural network learning with error correction

Z Wei, X Han, J Li - Journal of Energy Storage, 2022 - Elsevier
The accurate prediction of the state of health for retired batteries is the premise to ensure the
safe and efficient operation of echelon utilization batteries. Aiming at the problems of limited …

Fast and accurate error simulation for cnns against soft errors

C Bolchini, L Cassano, A Miele… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The great quest for adopting AI-based computation for safety-/mission-critical applications
motivates the interest towards methods for assessing the robustness of the application wrt …

Gradient descent-particle swarm optimization based deep neural network predictive control of pressurized water reactor power

DA Ejigu, X Liu - Progress in Nuclear Energy, 2022 - Elsevier
A pressurized water reactor (PWR) is an integrated system of various interdependent
subsystems that show highly nonlinear behavior, and each component is prone to …

Deep neural network and molecular docking supported toxicity profile of prometryn

F Çakir, F Kutluer, E Yalçin, K Çavuşoğlu, A Acar - Chemosphere, 2023 - Elsevier
In this study, the versatile toxicity profile of prometryn herbicide on Allium cepa was
investigated. In this context, 4 different groups were formed. While the control group was …

FireNN: Neural networks reliability evaluation on hybrid platforms

C De Sio, S Azimi, L Sterpone - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Modern neural network complexity has grown dramatically in recent years, leading to the
adoption of hardware-accelerated solutions to cope with the computational power required …

Special session: Approximation and fault resiliency of dnn accelerators

MH Ahmadilivani, M Barbareschi… - 2023 IEEE 41st VLSI …, 2023 - ieeexplore.ieee.org
Deep Learning, and in particular, Deep Neural Network (DNN) is nowadays widely used in
many scenarios, including safety-critical applications such as autonomous driving. In this …