Dr. Junwen Luo, Fudan University, China
Dr. Junwen Luo, MIEEE, MBNA, MIET, is a distinguished expert in neuromorphic computing and brain-machine interfaces (BMI). Currently serving as the Head of the BrainUp Research Lab at NaoluBrain Company in Beijing, Dr. Luo is renowned for his pioneering work in noninvasive BMI technologies and brain-inspired algorithms. He holds a Ph.D. in Microelectronics from Newcastle University, where his research focused on digital neural circuits. His academic journey also includes notable positions at leading institutions such as MIT, Imperial College London, and the City University of Hong Kong.
Professional Profile:
Summary of Suitability for Best Researcher Award:
Junwen Luo has demonstrated exceptional research capabilities in neuromorphic computing and Brain-Machine Interfaces (BMI). With over ten years of experience in both academia and industry, he has made significant contributions to the field, evidenced by his 30+ publications in high-impact journals and conferences such as ICML, TMBE, and Sensors. His work is recognized by leading experts like Tobi Delbruck (ETH) and Kea-Tiong Tang (NTH), highlighting his influence in the domain.
Education
- Ph.D. in Microelectronics
Newcastle University, United Kingdom
November 2010 – November 2014
Thesis Title: The Digital Neural Circuits: From Ions to Networks
- Neural Engineering Academy Visitor
Massachusetts Institute of Technology (MIT), United States
January 2011 – October 2011
Project Title: The Mechanisms of Stomatogastric Ganglion Nervous Network
- M.Sc. in Automation
Newcastle University, United Kingdom
September 2009 – September 2010
Thesis Title: The Fuzzy Logic Control of PMSM Machine
- B.Sc. in Automation
Huazhong University of Science and Technology, China
September 2005 – September 2009
Thesis Title: The Dynamic Control of Industrial Chemical Interactions
Work Experience
- Head of BrainUp Research Lab
NaoluBrain Company, Beijing
April 2022 – Present
- Develop noninvasive BMI Brain Touch products from concept to production DVT stage.
- Develop and release the first dream emotion related EEG dataset for sleep-related products.
Brain Touch Product
Dream Emotion EEG Dataset
- Research Scientist
Alibaba Group, Sunnyvale
June 2019 – April 2022
- Focused on sparse neural network CPU acceleration and brain-inspired algorithm development.
- Developed GEM5 based memory system modifications for accelerating SPMV/COV operations.
- Created Spike Gating Flow with few-shot online learning performances for action recognition.
Spike Gating Flow Code
- Engineering Lead/Research Associate
Newcastle University, Newcastle/London
November 2014 – June 2019
- Led the Controlling Abnormal Network Dynamics using Optogenetic (CANDO) project, developing an implantable brain chip system for optogenetic control of neural activity.
- Responsibilities included development of invasive BMI hardware computing architecture and Neural Processor Unit (NPU), bio-inspired brain signal processing algorithms, and system integration.
CANDO Project
- Research Assistant
City University of Hong Kong, Hong Kong
January 2013 – October 2013
- Worked on the Real-time Cerebellum Prosthesis project, focusing on the design and development of an FPGA-based artificial cerebellum system with AI computing capabilities.
- Responsibilities included development of on-chip multi-core learning systems, routers, and bio-inspired cerebellar timing learning algorithms.
Publication top Notes:
MLS-Net: An Automatic Sleep Stage Classifier Utilizing Multimodal Physiological Signals in Mice
The VEP Booster: A Closed-Loop AI System for Visual EEG Biomarker Auto-generation
Emotion Recognition from Few-Channel EEG Signals by Integrating Deep Feature Aggregation and Transfer Learning
A Consumer-tier based Visual-Brain Machine Interface for Augmented Reality Glasses Interactions
The SCEEGNet: An Efficient Learning Method for Emotion Recognition Based on the Few Channels