On Kernel Method-Based Connectionist Models and Supervised Deep Learning Without Backpropagation
Shiyu Duan, Shujian Yu, Yunmei Chen, Jose C. Principe, Neural Computation, 2020
Curriculum Vitae
Education
University of Florida, Gainesville, FL, USA
- Ph.D. in Electrical and Computer Engineering Aug. 2017 - Dec. 2020
- Advisor: Dr. Jose Principe
- Minor in Mathematics
- M.S. in Statistics Jan. 2018 - Dec. 2020
Fudan University, Shanghai, China
- B.S. in Electrical and Computer Engineering Sep. 2012 - Jul. 2016
Experience
Apple, Cupertino, CA, USA
Machine Learning Engineer Jan. 2021 - Present
- Video quality enhancement
University of Florida, Gainesville, FL, USA
Research Assistant Aug. 2017 - Dec. 2020
- Modular deep learning
- Data-efficient deep learning
- Connecting kernel methods and neural networks
Apple, Cupertino, CA, USA
Intern May 2020 - Aug. 2020
- Image and video super-resolution
SenseTime Research, San Jose, CA, USA
Research Intern May 2019 - Aug. 2019
- Image and video compression
- Image and video synthesis from semantics
Bosch, Shanghai, China
Research Intern Jan. 2016 - Jun. 2016
- Data mining
Publications
Modularizing Deep Learning via Pairwise Learning With Kernels
Shiyu Duan, Shujian Yu, Jose C. Principe, IEEE Transactions on Neural Networks and Learning Systems, 2021
Labels, Information, and Computation: Efficient Learning Using Sufficient Labels
Shiyu Duan, Spencer Chang, Jose C. Principe, Journal of Machine Learning Research, 2023
Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methods
Shiyu Duan, Jose C. Principe, IEEE Computational Intelligence Magazine, 2022
JPD-SE: High-Level Semantics for Joint Perception-Distortion Enhancement in Image Compression
Shiyu Duan, Huaijin Chen, Jinwei Gu, IEEE Transactions on Image Processing, 2022