Eriko Nurvitadhi

About

Eriko Nurvitadhi is a leading researcher in reconfigurable computing, with a primary focus on accelerating deep learning and computer vision workloads using FPGAs. His work bridges the gap between hardware architecture and practical AI deployment, particularly for edge and real-time systems. His most cited paper, "End-to-End FPGA-based Object Detection Using Pipelined CNN and Non-Maximum Suppression" (2021, 16 citations), demonstrates a complete, hardware-efficient pipeline for single-shot detectors, addressing critical bottlenecks in autonomous driving and robotics. Beyond this, Nurvitadhi has made foundational contributions to FPGA-based neural network inference, including pioneering work on binarized neural networks and efficient matrix multiplication engines that achieve orders-of-magnitude energy savings over GPUs. His research has been instrumental in showing that FPGAs can deliver competitive performance for AI tasks while maintaining low latency and power consumption. With a citation count reflecting growing industry and academic interest, Nurvitadhi’s work has influenced both commercial FPGA design tools and open-source hardware accelerators. He is also a sought-after speaker and collaborator, known for translating complex architectural innovations into deployable solutions for real-world vision systems.

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