This is the homepage of Lisa Zhang.

Me In a Nutshell

I am currently an Assistant Professor, Teaching Stream (CLTA) at the Department of Mathematical & Computational Sciences, University of Toronto Mississauga. My office is located at DH3068.

I held many roles during my career: startup founder, data scientist, machine learning researcher, pure math student, and now a computer science teacher. I am passionate about machine learning, teaching education, writing, and still have a soft spot for great data visualization and nerdy humour.

Current Teaching

CSC290 Communication Skills for Computer Science

CSC324 Programming Languages

Previous Teaching

CSC108 Introduction to Programming Summer 2018, University of Toronto

CSC411 Introduction to Machine Learning Winter 2018, University of Toronto

Bragging Bio

I have a publication upcoming in NIPS 2018.

I gave a talk at the Spark Summit East 2016 conference in New York.

won things.

In 2011, I founded a startup, Polychart. In 2012, I rejected an (non-trivial) acquisition offer, instead opting for a break-up of the entire team. In 2013, with a re-built team, we were one of five companies in the ExtremeStartups accelerator. In late 2013 Polychart was open sourced.

While studying pure math at University of Waterloo, I scored 33 points on the Putnam math contest (where median score is 0 most years). Sixteen (16) months of my undergrad was spent in California on internships at companies Facebook, ContextLogic (Wish), and Tagged. I wrote on the Facebook Data Science blog.

A few blog posts that I wrote have gone on the front page of Hacker News.

Research and Publications

Neural Guided Constraint Logic Programming for Program Synthesis

Lisa Zhang, Gregory Rosenblatt, Ethan Fetaya, Renjie Liao, William E. Byrd, Matthew Might, Raquel Urtasun, Richard Zemel
Accepted to NIPS 2018 [arxiv] [github] [workshop]

MSC Thesis

Leveraging Constraint Logic Programming for Neural Network Guided Program Synthesis
Supervisors: Richard Zemel, Raquel Urtasun

Reviving and Improving Recurrent Back-Propagation

Renjie Liao, Yuwen Xiong, Ethan Fetaya, Lisa Zhang, KiJung Yoon, Xaq Pitkow, Raquel Urtasun, Richard Zemel
ICML 2018 [arxiv]

Inference in probabilistic graphical models by Graph Neural Networks

KiJung Yoon, Renjie Liao, Yuwen Xiong, Lisa Zhang, Ethan Fetaya, Raquel Urtasun, Richard Zemel, Xaq Pitkow
ICLR Workshop Track 2018 [paper]

Learning deep structured active contours end-to-end

Diego Marcos, Devis Tuia, Benjamin Kellenberger, Lisa Zhang, Min Bai, Renjie Liao, Raquel Urtasun
CVPR 2018 [arxiv]

Old Projects

Tiny EpiphanyThis is my blog, formerly known as "A Notebook". I write about whatever comes to mind, technical and not.

PolychartData visualization software that connects directly to your database, and helps you explore the data using drag-and-drop.

Polychart.JSJavaScript library built on top of RaphaelJS. My take on the Grammar of Graphics and how to handle interactions. The way data transformations are handled are interesting here too.

My ResumeSlightly more structured overview of what I did.

Data In ColourA now defunct data (visualization) blog. I keep it up there still to keep links alive. I bought both domains  and because I am Canadian.


You can email me at lczhang [at] cs [dot] toronto [dot] edu. If you are emailing me regarding a course, please include the course code in the email subject. Please mention if you are a current or past student.