Hanane Benmaghnia

Papers

Total Citations

H-Index

About

Hanane Benmaghnia is a researcher focused on the intersection of neural networks and embedded systems, with a key emphasis on fixed-point arithmetic. Her work addresses a critical challenge: deploying neural networks in safety-critical environments—such as robots, rockets, and autonomous vehicles—where computing resources are severely limited. Benmaghnia’s major contributions lie in developing code generation and synthesis techniques that convert floating-point neural networks into efficient fixed-point implementations, drastically reducing time and memory consumption without compromising performance. Her most-cited paper, "Code Generation for Neural Networks Based on Fixed-point Arithmetic" (2022, 7 citations), and its follow-up, "Fixed-Point Code Synthesis for Neural Networks" (2022, 4 citations), have laid foundational methods for enabling neural networks to operate on resource-constrained hardware. These works are particularly impactful for engineers and researchers aiming to integrate AI into real-time, embedded applications. Benmaghnia’s research not only advances the practical deployment of neural networks but also bridges the gap between high-performance AI and the stringent demands of safety-critical systems. Her achievements highlight a promising trajectory in making deep learning viable for the next generation of autonomous and embedded technologies.