Erjin Zhou

About

Erjin Zhou has made transformative contributions to the intersection of deep learning and hardware acceleration, with a primary focus on deploying convolutional neural networks (CNNs) on embedded FPGA platforms. His seminal 2016 paper, “Going Deeper with Embedded FPGA Platform for Convolutional Neural Network,” has garnered over 1,260 citations, establishing him as a pioneer in efficient, real-time AI inference on resource-constrained devices. Zhou’s work directly addresses the critical challenge of making computationally intensive CNN models practical for edge applications, such as autonomous systems and mobile vision, by designing optimized hardware architectures that balance performance, power, and accuracy. His research has not only advanced the field of embedded AI but also provided a foundational blueprint for subsequent FPGA-based neural network accelerators. Beyond this landmark study, Zhou’s broader portfolio explores efficient model compression and hardware-software co-design, enabling deep learning to operate beyond the cloud. His achievements have been widely recognized in top venues, and his work continues to inspire engineers and researchers seeking to bridge the gap between cutting-edge algorithms and real-world deployment.

Research Focus

Key Achievements

Top Papers

1. 1
   Going Deeper with Embedded FPGA Platform for Convolutional Neural Network

   1,260 citations · 2016

Key Collaborators

Contact & Links