Mohamed Mejri
Papers
1
Total Citations
4
H-Index
1
About
Mohamed Mejri is a researcher at the forefront of ensuring the reliability and safety of deep neural networks (DNNs) in safety-critical applications. His work addresses a fundamental challenge: as DNNs are deployed in domains like autonomous driving and medical robotics, their underlying hardware becomes increasingly vulnerable to soft errors. Mejri’s key contribution lies in developing innovative error resilience techniques, most notably using neuron gradient statistics to detect and mitigate these hardware-induced faults without sacrificing performance. His highly cited 2023 paper on this topic has already garnered significant attention, establishing him as a rising voice in dependable AI. By bridging the gap between hardware reliability and deep learning, Mejri’s research is essential for building trustworthy AI systems that can operate safely in the real world. His work not only advances the field of fault-tolerant neural networks but also provides practical solutions for engineers designing robust autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1