I am a research engineer at Preferred Networks, Tokyo, Japan. Before that, I received bachelar’s degree from Fudan University in 2018. My research interest focuses on applying generative models to Japanese anime.

Email: jinyh [at] preferred [dot] jp

Publications / Manuscripts

Amortized Nesterov’s Momentum: Robust and Lightweight Momentum for Deep Learning
Uncertainty in Artificial Intelligence (UAI) 2020
Kaiwen Zhou, Yanghua Jin, Qinghua Ding, James Cheng
[paper][supp][code]

Fast Soft Color Segmentation
Computer Vision and Pattern Recognition (CVPR) 2020
Naofumi Akimoto, Huachun Zhu, Yanghua Jin, Yoshimitsu Aoki
[paper][github]

Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
Advances in Neural Information Processing Systems (NIPS) 2017 Workshop on Machine Learning for Creativity and Design (spotlight) Yanghua Jin, Jiakai Zhang, Minjun Li, Yingtao Tian, Huachun Zhu
[paper][web site]

Invited Talk

Exploring the Anime Characters Creation with Generative Adversarial Networks
Deep Learning: Theory, Algorithms, and Applications, RikenAIP, Tokyo, Mar 19-22, 2018
Video is available on YouTube

Create Anime Characters using AI
AI for Manga & Anime, Anime Expo 2018, Los Angeles, 2018
[slides]

Timeline

Preferred Networks, Tokyo, Japan
2018.11 - present
Deep Learning R&D.

Crypko.AI, Founder
2018.5 - 2018.10
Building next-generation cryptocollectible game with GAN and Ethereum.
Director, Machine Learning Development, Backend Development Currently, this project belongs to Preferred Networks.

Fudan University, B.S. with honors in Computer Science, Shanghai, China
2013 - 2018

Kyoto University, General Exchange Program, Kyoto, Japan
2016.9 - 2017.9

Preferred Networks, Tokyo, Japan
2017.3 - 2017.8

Morgan Stanley, Technology Summer Analyst Program, Shanghai, China
2016.7 - 2016.9