Chankyu Lee

Chankyu Lee

Deep Learning Software Engineer

NVIDIA Corporation

Biography

Currently, I am a senior deep learning software engineer at NVIDIA. I obtained my Ph.D. degree in Electrical and Computer Engineering at Purdue University, advised by Prof. Kaushik Roy. While there, I focused on developing energy-efficient and robust deep learning algorithms with special interests in spiking neural networks and computer vision for event-based cameras.

Interests

  • Efficient and Robust Deep Learning
  • Algorithm-Hardware Co-design
  • Neuromorphic Computing

Education

  • PhD in Electrical and Computer Engineering, Fall 2015 - Spring 2021

    Purdue University, West Lafayette, IN, USA

  • BS in Electrical and Electronics Engineering, Spring 2009 - Spring 2015

    Sungkyunkwan University (SKKU), Suwon, South Korea

  • Exchange Student Program, Electronic and Computer Engineering, Fall 2013

    Hong Kong University of Science and Technology (HKUST), Hong Kong

Experience

 
 
 
 
 

Largescale Machine Learning Engineer

Intel Corporation

Apr 2021 – Mar 2022 Austin, Texas, USA
AI workload performance optimization (i.e., improving the runtime, efficiency, scalability) on a largescale machine learning (BERT, ResNet50) training on Intel AI accelerators.
 
 
 
 
 

Graduate Internship

Bell Labs, Nokia

Jun 2018 – Aug 2018 Murray Hill, New Jersey, USA
Developed the functional simulator for mapping and scheduling convolutional neural network (AlexNet, VGG, ResNet) algorithms on a wave-front MIMD (Multi-Instruction Multi-Data) processor towards the accelerated/energy-efficient AI computing. Supervisor: Hungkei Chow and Joseph Galaro
 
 
 
 
 

Graduate Research Assistant

Purdue University

Aug 2016 – Dec 2020 West Lafayette, Indiana, USA

Overview: Exploratory research on neuromorphic computing for energy-efficient and robust machine learning, overcoming limitations of current artificial intelligence through algorithm-hardware co-design (Funded by the C-BRIC, one of six centers in JUMP, a SRC program). Advised by Prof. Kaushik Roy.

  • Topic 1: Developed novel unsupervised/supervised/semi-supervised learnings for deep convolutional Spiking Neural Networks (SNNs) to efficiently harness machine learning algorithms.
  • Topic 2: Developed energy-efficient motion estimation algorithms for event-based camera in challenging scenes such as high-speed and wide-dynamic range. Realtime demo is available.
  • Research Outputs: 13 publications including 6 first-authored papers (1 IEEE TCDS, 2 Frontiers in Neuroscience, 1 ECCV, 1 Neurocomputing, 1 IEEE ICRA).
 
 
 
 
 

Undergraduate Research Assistant

Graduate School of Convergence Science and Technology, Seoul National University

Jul 2014 – Aug 2014 Suwon, South Korea
Research on mid-field wireless powering for simulating neural signals in the brain-machine interface. Advised by Prof. Yoonkyu Song

Selected Publications

Fusion-FlowNet: Energy-Efficient Optical Flow Estimation using Sensor Fusion and Deep Fused Spiking-Analog Network Architectures

Standard frame-based cameras that sample light intensity frames are heavily impacted by motion blur for high-speed motion and fail to …
Chankyu Lee, Adarsh Kosta, Kaushik Roy. IEEE International Conference on Robotics and Automation (ICRA), 2022
PDF
Fusion-FlowNet: Energy-Efficient Optical Flow Estimation using Sensor Fusion and Deep Fused Spiking-Analog Network Architectures

Towards Understanding the Effect of Leak in Spiking Neural Networks

Spiking Neural Networks (SNNs) are being explored to emulate the astounding capabilities of human brain that can learn and compute …
Sayeed Shafayet Chowdhury*, Chankyu Lee*, Kaushik Roy (*Equal Contribution). Neurocomputing, 2021
PDF
Towards Understanding the Effect of Leak in Spiking Neural Networks

Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

Event-based cameras display great potential for a variety of conditions such as high-speed motion detection and enabling navigation in …
Chankyu Lee, Adarsh Kosta, Alex Zihao Zhu, Kenneth Chaney, Kostas Daniilidis, Kaushik Roy. In Proceedings of the European Conference on Computer Vision (ECCV) 2020
PDF Code Video
Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures

Spiking Neural Networks (SNNs) have recently emerged as a prominent neural computing paradigm. However, the typical shallow SNN …
Chankyu Lee*, Syed Shakib Sarwar*, Priyadarshini Panda, Gopalakrishnan Srinivasan, Kaushik Roy (*Equal Contribution). Frontiers in Neuroscience, Neuromorphic Engineering, 2020
PDF Code
Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures

Training Deep Spiking Convolutional Neural Networks with STDP-based Unsupervised Pre-training Followed by Supervised Fine-tuning

Spiking Neural Networks (SNNs) are fast becoming a promising candidate for brain-inspired neuromorphic computing because of their …
Chankyu Lee, Gopalakrishnan Srinivasan, Priyadarshini Panda, Kaushik Roy. Frontiers in Neuroscience, Neuromorphic Engineering, 2018
PDF
Training Deep Spiking Convolutional Neural Networks with STDP-based Unsupervised Pre-training Followed by Supervised Fine-tuning

Deep Spiking Convolutional Neural Network Trained With Unsupervised Spike-Timing-Dependent Plasticity

Spiking neural networks (SNNs) have emerged as a promising brain inspired neuromorphic-computing paradigm for cognitive system design …
Chankyu Lee, Gopalakrishnan Srinivasan, Priyadarshini Panda, Kaushik Roy. IEEE Transactions on Cognitive and Developmental Systems (TCDS), 2018
PDF
Deep Spiking Convolutional Neural Network Trained With Unsupervised Spike-Timing-Dependent Plasticity

Contact