Ghattas Akkad

Centre National de la Recherche Scientifique

Papers

Total Citations

H-Index

About

Ghattas Akkad is a leading researcher at the forefront of embedded artificial intelligence, specializing in the design and optimization of deep learning accelerators for resource-constrained environments. His work bridges the critical gap between cutting-edge machine learning algorithms and practical, low-power hardware deployment. Akkad is best known for his comprehensive survey on embedded deep learning accelerators, which has garnered 38 citations since its publication in 2023, establishing itself as a key reference for researchers navigating the rapidly evolving landscape of efficient neural network inference. This seminal work systematically maps the architectural innovations—from systolic arrays to dataflow optimizations—that enable complex models to run on edge devices. By synthesizing advances in GPU and TPU technologies with the constraints of embedded systems, Akkad has provided a foundational roadmap for the next generation of intelligent IoT devices, autonomous systems, and mobile platforms. His contributions are instrumental in democratizing AI, making high-performance machine learning accessible beyond the data center and into everyday applications.