Hyungjun Kim is currently a PhD Candidate at Pohang University of Science and Technology (POSTECH), Korea. He is advised by Professor Jae-Joon Kim in Device and Integrated Circuit Engineering (DICE) Lab.
Hyungjun’s research interest is about energy-efficient Deep Learning Accelerators. Especially, he is currently working on In-Memory Computing (or Compute-In-Memory) scheme. He is also very interested in neural network compression techniques such as low-precision quantization.
You may contact Hyungjun for more discussion on his research via hyungjun.kim /.at./ postech.ac.kr.
- Hyungjun’s paper entitled “Algorithm-Hardware Co-Design for In-Memory Neural Network Computing with Minimal Peripheral Circuit Overhead” is accepted to Design Automation Conference (DAC) 2020.
- Hyungjun’s paper with Kyungsu entitled “BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations” is accepted to ICLR 2020.