Ali Asgari
Papers
1
Total Citations
5
H-Index
1
About
Ali Asgari is a leading researcher at the intersection of computer vision, safety-critical systems, and hardware reliability. His work focuses on ensuring that deep learning models, particularly convolutional neural networks (CNNs), can be trusted in high-stakes environments like automated driving and human-robot interaction. Asgari’s most cited paper, “Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision” (2021, 5 citations), introduces a novel framework for detecting and mitigating hardware soft errors that can corrupt neural network outputs. This contribution is pivotal for building robust, real-world AI systems where a single bit flip could lead to catastrophic failure. By proposing activation range supervision as a safety mechanism, Asgari provides a practical path toward certifying neural networks for safety-critical deployment. His work bridges the gap between theoretical model performance and the rigorous dependability requirements of industrial applications, making him a key voice in the emerging field of trustworthy AI.
Research Focus
Key Achievements
Top Papers
- 1