Eugenio Culurciello

About

Eugenio Culurciello is a pioneering figure in the design of efficient, hardware-accelerated deep learning systems, with a focus on embedded vision and robotics. His research bridges the gap between complex neural network algorithms and real-time, low-power hardware, making advanced AI feasible for autonomous systems. A major contribution is his work on FPGA-based and custom chip accelerators for deep convolutional neural networks (DCNNs). His seminal 2011 paper, "Large-Scale FPGA-Based Convolutional Networks," and his 2016 work on an "Embedded Streaming Deep Neural Networks Accelerator" (each with 122 citations) laid the groundwork for deploying vision systems in micro-robots, UAVs, and mobile phones. He also developed the "NeuFlow" dataflow vision system-on-a-chip (86 citations), a bio-inspired processor for high-speed convolution operations. By enabling efficient, real-time object recognition on resource-constrained devices, Culurciello's work has been instrumental in advancing autonomous navigation and embedded AI, directly impacting fields from security systems to automotive perception.

Research Focus

Key Achievements

Top Papers

1. 1
   Large-Scale FPGA-Based Convolutional Networks

   122 citations · 2011
2. 2
   Embedded Streaming Deep Neural Networks Accelerator With Applications

   122 citations · 2016
3. 3
   NeuFlow: Dataflow vision processing system-on-a-chip

   86 citations · 2012
4. 4
   An efficient implementation of deep convolutional neural networks on a mobile coprocessor

   43 citations · 2014
5. 5
   Clustering Learning for Robotic Vision

   3 citations · 2013

Key Collaborators

Contact & Links