Assistant Professor

Bryant University

I currently hold the position of Assistant Professor of Information Systems and Business Analytics at Bryant University. Before this role, I served as a TRIPODS postdoctoral research associate in the College of Computer Science and the Department of Mathematics and Statistics at UMass Amherst, working under the guidance of Professor Patrick Flaherty. Prior to that, I worked as a postdoctoral research associate in the Department of Electrical and Computer Engineering at Northeastern University, under the supervision of Professor Jennifer Dy. Additionally, I am honored to hold the position of Research Fellow at Brigham and Women’s Hospital of Harvard Medical School.

My academic journey led me to earn my Ph.D. in Statistics from the Department of Statistics at the University of British Columbia in December 2018, where I had the privilege of being mentored by Professor Alexandre Bouchard-Côté.

Interests

  • Deep Learning
  • Business Analytics
  • Explainable AI

Education

  • PhD in in Statistics, 2018

    UBC

  • MSc in Statistics, 2013

    UBC

  • BSc in Mathematics, 2011

    ZheJiang University

Experience

 
 
 
 
 

Assistant Professor

Bryant University

Jan 2022 – Present Rhode Island, US
 
 
 
 
 

Tripods Postdoctoral Research Associate

UMass Amherst

Dec 2020 – Dec 2021 Amherst, US
 
 
 
 
 

Joint Sponsored Research Fellow

Brigham and Women’s Hospital of Harvard Medical School

Jan 2019 – Dec 2020 Boston, US
Groupwise and individual feature selection in deep learning using knockoff construction with applications to Chronic Obstructive Pulmonary Disease (COPD). Developed novel machine learning methodology to improve prediction accuracy of exacerbations in COPD.
 
 
 
 
 

Postdoctoral Researcher

Department of Electrical and Computer Engineering, Northeastern University

Jan 2019 – Dec 2020 Boston, US
Proposed a nonparametric Bayesian modelling framework combined with deep learning and developed a novel online algorithm for deep representation and clustering for streaming data. Developed a novel instancewise feature selection method for model interpretation.

Projects

*

Deep-gKnock

Deep-gKnock: nonlinear group-feature selection with controlled group-wise False Discovery Rate

Talks / Workshops

Recent Publications

Quickly discover relevant content by filtering publications.
Deep bayesian unsupervised lifelong learning
Improved prediction of smoking status via isoform-aware RNA-seq deep learning models
Instance-wise feature grouping
Bayesian analysis of continuous time Markov chains with application to phylogenetic modelling
Study on RMB number recognition based on genetic algorithm artificial neural network

Contact

Send me a note

  • 1150 Douglas Pike, Smithfield, RI 02917