Jay Wang

Hi, I'm Jay. I'm a Machine Learning Ph.D. student in the College of Computing at Georgia Tech adviced by Polo Chau.

My research focuses on making AI more accessible, interpretable, and accountable, by designing and developing novel interactive interfaces for people to easily and enjoyably interact with machine learning systems at scale.

I recieved my B.S. from UW–Madison, where I worked closely with Anthony Gitter, Michael Gleicher, and Yu Hen Hu.

jayw@gatech.edu

News

Aug. 29, 2020

Two papers, CNN Explainer and Bluff, are accepted for IEEE VIS 2020!

June 18, 2020

Started my first internship at Bosch (Sunnyvale) , working with Liang Gou on visual analytics for autonomous driving.

April 30, 2020

Posted CNN Explainer paper on arXiv. CNN Explainer an interactive tool that helps beginners learn CNNs. It is also open-sourced on GitHub.

Jan 15, 2020

Two papers, CNN 101 and Massif, are accepted for CHI 2020 Late-Breaking Works!

Featured Publications

CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization

Zijie J. Wang, Robert Turko, Omar Shaikh, Haekyu Park, Nilaksh Das, Fred Hohman, Minsuk Kahng, Duen Horng (Polo) Chau

IEEE Transactions on Visualization and Computer Graphics (TVCG), 2021

BibTeX

Top of GitHub Trending

@article{wangCNNExplainerLearning2021,
  title = {{{CNN Explainer}}: {{Learning Convolutional Neural Networks}} with {{Interactive Visualization}}},
  shorttitle = {{{CNN Explainer}}},
  author = {Wang, Zijie J. and Turko, Robert and Shaikh, Omar and Park, Haekyu and Das, Nilaksh and Hohman, Fred and Kahng, Minsuk and Chau, Duen Horng},
  journal={IEEE Transactions on Visualization and Computer Graphics (TVCG)},
  publisher={IEEE},
  year={2021},
}

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

Nilaksh Das*, Haekyu Park*, Zijie J. Wang, Fred Hohman, Robert Firstman, Emily Rogers, Duen Horng (Polo) Chau

(*Authors contributed equally)

IEEE Visualization Conference (VIS), 2020

BibTeX

@article{dasBluffInteractivelyDeciphering2020,
  title={Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks},
  author={Das, Nilaksh and Park, Haekyu and Wang, Zijie J and Hohman, Fred and Firstman, Robert and Rogers, Emily and Chau, Duen Horng},
  booktitle={IEEE Visualization Conference (VIS)},
  publisher={IEEE},
  year={2020}
}

UnMask: Adversarial Detection and Defense Through Robust Feature Alignment

Scott Freitas, Shang-Tse Chen, Zijie J. Wang, Duen Horng (Polo) Chau

IEEE International Conference on Big Data (BigData), 2020

Project

PDF

Code

BibTeX

@article{freitasUnMaskAdversarialDetection2020,
  title = {{{UnMask}}: {{Adversarial Detection}} and {{Defense Through Robust Feature Alignment}}},
  shorttitle = {{{UnMask}}},
  author = {Freitas, Scott and Chen, Shang-Tse and Wang, Zijie J. and Chau, Duen Horng},
  year = {2020},
  archivePrefix = {arXiv},
  eprint = {2002.09576},
  eprinttype = {arxiv},
  journal = {arXiv:2002.09576}
}

A Comparative Analysis of Industry Human-AI Interaction Guidelines

Austin P. Wright, Zijie J. Wang, Haekyu Park, Grace Guo, Fabian Sperrle, Mennatallah El-Assady, Alex Endert, Daniel Keim, Duen Horng (Polo) Chau

IEEE Visualization Conference, Workshop on Trust and Expertise in Visual Analytics (TREX), 2020

BibTeX

@article{wrightComparativeAnalysisIndustry2020,
  title = {A {{Comparative Analysis}} of {{Industry Human}}-{{AI Interaction Guidelines}}},
  author = {Wright, Austin P. and Wang, Zijie J. and Park, Haekyu and Guo, Grace and Sperrle, Fabian and {El-Assady}, Mennatallah and Endert, Alex and Keim, Daniel and Chau, Duen Horng},
  year = {2020},
  month = oct,
  eprint = {2010.11761},
  journal = {arXiv:2010.11761}
}

see all publications

Fun Projects

Clip2imgur: Convenient macOS command line tool for uploading screen-shots from the clipboard to Imgur.

Code

Featured on Imgur

FaceData: MacOS GUI to auto-annotate facial landmarks from a video. Landmarks can be used to train GANs.

Code

( loading )

Graphics on the Web: Interactive 2D, 2.5D and 3D computational graphics with shaders and textures, created with HTML canvas and webGL.

Code

Demo

Group Assignment Problem: Flexible and robust Mixed Integer Quadratic Programming model written in Julia to solve a real-life optimization problem.

Code

Demo

Best project

Dean's list Vis: Interactive geo-visualization to explore where UW–Madison Chinese students are from.

Code

Demo

Yelp Sentiment: Predicting Yelp ratings based on text comments of restaurants at Madison Wisconsin.

Code

Kaggle winner

Zijie Jay Wang