Andrew Boutros

About

Andrew Boutros is a leading researcher in reconfigurable computing and FPGA-based acceleration for machine learning. His work focuses on bridging the gap between high-performance deep learning algorithms and efficient hardware implementation. Boutros made significant contributions to end-to-end FPGA-based object detection, demonstrating how pipelined convolutional neural networks (CNNs) and non-maximum suppression can be integrated directly onto FPGAs for real-time, low-latency inference. His 2021 paper on this topic, which has garnered 16 citations, exemplifies his impact in enabling practical computer vision applications such as autonomous driving and smart surveillance. Beyond object detection, Boutros has advanced the design of domain-specific FPGA architectures, including neural network accelerators and reconfigurable dataflow engines. His work is widely recognized for its emphasis on bridging algorithmic innovation with hardware efficiency, making him a key figure in the field of reconfigurable systems for AI.

Research Focus

Key Achievements

Top Papers

1. 1
   End-to-End FPGA-based Object Detection Using Pipelined CNN and Non-Maximum Suppression

   16 citations · 2021

Key Collaborators

Contact & Links