Xuan Chen | 陈璇

Xuan Chen | 陈璇

CS Ph.D. Student

Purdue University

About

I am a first-year Ph.D. student in the Computer Science Dept. at Purdue University, advised by Professor Xiangyu Zhang. Before joining Purdue, I obtained my Master of Science degree in Electrical and Computer Engineering at Carnegie Mellon University and my bachelor degree from University of Science and Technology Beijing.

My research interests lie in interpretable artifical intelligence(AI) and reinforcement learning, machine learning(ML) security and privacy, the vibrant research field that focuses on reducing ML systems vulnerabilities and designing verifiable machine learning approaches with provable robustness. My enthusiasm is to develop trustworthy machine learning solutions as well as deploying reliable AI systems, to help end users trust the AI system and make humans empowered by machine learning.

Interests

  • Deep Learning
  • Machine Learning Security
  • Explainable Neural Network
  • Reinforcement Learning

Education

  • MSc in Electrical and Computer Engineering, 2020

    Carnegie Mellon University

  • BSc in Electrical Engineering, 2019

    University of Science and Technology Beijing

Projects

Explanation for Deep Reinforcement Learning

Behavior-level explanations of the Deep-Q-Network trained agents.

Fast Transfer Learning for GAN Style Transfer

A novel transfer learning method for GAN style transfer which consumes fewer computation resources and training time.

Uncertainty Calibration for Neural Network Output

Trainable and Diffientiable Loss for Classification Neural Network.

Publications

Quickly discover relevant content by filtering publications.

Towards Behavior-Level Explanation for Deep Reinforcement Learning

While Deep Neural Networks (DNNs) are becoming the state-of-the-art for many tasks including reinforcement learning (RL), they are …
**Xuan Chen**, Zifan Wang, Yucai Fan, Bonan Jin, Pitor Mardziel, Carlee Joe-Wong, Anupam Datta
Preprint Project