Jonghoon Jin

About

Jonghoon Jin is a leading researcher in efficient deep learning hardware, specializing in the acceleration of deep convolutional neural networks (DCNNs) for real-time, embedded applications. His major contributions lie in bridging the gap between powerful neural network models and resource-constrained mobile and autonomous platforms. Jin’s most-cited work, “Embedded Streaming Deep Neural Networks Accelerator With Applications” (2016, 122 citations), pioneered a streaming architecture that dramatically improves throughput and power efficiency for DCNNs in autonomous robots, security systems, and automobiles. His earlier seminal paper, “An efficient implementation of deep convolutional neural networks on a mobile coprocessor” (2014, 43 citations), demonstrated a hardware-accelerated, real-time DCNN implementation that overcame the memory and computational bottlenecks of mobile devices. By optimizing the management of hundreds of intermediate results, Jin’s research has directly enabled practical, low-power visual perception systems. His work is foundational for engineers and researchers developing embedded AI, showcasing how algorithmic and hardware co-design can bring deep learning to the edge.

Research Focus

Key Achievements

Top Papers

1. 1
   Embedded Streaming Deep Neural Networks Accelerator With Applications

   122 citations · 2016
2. 2
   An efficient implementation of deep convolutional neural networks on a mobile coprocessor

   43 citations · 2014

Key Collaborators

Contact & Links