Contact
Experience
May 2019 – August 2019
Apple R&D Limited, Beijing, China
Automation Tool Development Intern, Deep-Learning
- Chinese Character Style Transfer, which, after learning a specific font from 20 Chinese characters, can produce other over 6000 characters with those fonts.
- Inpainting system for high-resolution images, which combines inpainting and super resolution functions to recover high-resolution(3000x4000) masked images.
- Internal ios App demo with SwiftUI and its node.js server.
June 2017 – March 2018
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
Research Assistant, Deep-Learning
- Responsibility: contributed to the Cosine Normalization in State Key Laboratory of Computer Architecture, ICT, CAS. In deep learning, previous studies on CN demonstrated its excellent performance of Normalization in FCN (Fully Connected Networks) and CNN (Convolutional Neural Networks), but the research about CN based on RNN is empty. My research aimed at applying CN on RNN and to ensure it could maintain excellent performance through various RNN experimental models.
- Earned: Outstanding Student in State Key Laboratory of Computer Architecture(Chinese Academy of Sciences) in 2017
Eduction
September 2019 – Now
Courant Institute of Mathematical Sciences, New York University, NYC, U.S.
Master of Science, Computer Science
September 2016 – May 2017
University of Minnesota, Twin Cities, Minneapolis, U.S.
Undergraduate Exchange Student, Computer Science
- Sponsored by: State Scholarship in China Scholarship Council
September 2014 – July 2018
Beijing Jiaotong University Beijing, China
Bachelor of Engineering, Software Engineering
- Earned: Outstanding Academic Records Scholarship in BJTU(2014-2015)
PUBLICATIONS
- Luo C, Zhan J, Xue X, et al. Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks: 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part I. 382-391. 10.1007/978-3-030-01418-6_38.