Maged Ghoneima

About

Maged Ghoneima is a researcher specializing in hardware acceleration for deep learning, with a focus on FPGA-based implementations. His work centers on designing efficient multiply-accumulate (MAC) units—the computational backbone of neural networks—to enable high-speed, parallel processing for convolutional neural networks (CNNs) and deep learning models. Ghoneima’s major contributions include the development of a concurrent MAC unit using VHDL, which achieved 19 citations for its innovative approach to accelerating deep neural network algorithms in applications like text recognition, multimedia processing, and robotics. He further advanced this field with a high-speed 2D parallel MAC unit hardware accelerator, demonstrating continued impact in optimizing CNN performance. His research addresses the critical challenge of overcoming computational bottlenecks in AI, offering scalable solutions for real-time, resource-constrained environments. With a citation count reflecting growing interest in hardware-software co-design, Ghoneima’s work is notable for bridging the gap between algorithmic complexity and practical FPGA deployment, making him a key figure in the evolution of energy-efficient, high-throughput AI accelerators.

Research Focus

Key Achievements

Top Papers

1. 1
   Concurrent MAC unit design using VHDL for deep learning networks on FPGA

   19 citations · 2018
2. 2
   High-Speed 2D Parallel MAC Unit Hardware Accelerator for Convolutional Neural Network

   4 citations · 2018

Key Collaborators

Contact & Links