NEW! I spoke to CBC Radio about Vibe Coding.
Automatically identifying chess moves humans perceive as brilliant (as opposed to merely strong), with Kamron Zaidi (EngSci 2T4). ICCC 2024, covered in New Scientist and chess.com.
A mysterious interaction between architectures and datasets when using the rotation pretext task in self-supervised pretraining, with Paul Yan (EngSci 2T6) and Amy Saranchuk (EngSci 2T5). NeurIPS 2025 workshop.
Learning a compact representation of microstructures using a custom VAE, with Andy Cai (EngSci 2T5), Sajjad Hashemi (Indy 2T4), and Noah Paulson (Argonne National Laboratory). ICCV 2025 workshop.
How and whether modern vision architectures encode symmetry-based information in images, with Whitney (Zhi) Ji (EngSci 2T5). NeurIPS 2024 workshop.
A pipeline for gaining insights into complex diseases by training LLMs on social media data and analyzing their explanations, with Kexin Chen (MIE M.Eng. '24), Noelle Lim (EngSci 2T3), and Claire Lee (Princeton '20). ML4H @ NeurIPS 2024.
Position information emerges in causal transformers without positional encodings via similarity of nearby embeddings, with Jason Zuo (EngSci 2T4) and Pavel Guerzhoy (UH Mānoa Math). COLING 2025, summary.
Testing the "Honour Culture" theory using social media data, with Juho Kim. EMNLP 2024 workshop.
NΨ Nocturne 2T3: GPT is Coming to Class (as seen at NeurIPS Education Program 2025). NΨ Nocturne 2T4: Defying Gravity/Debugging Properly, Desafinado. NΨ Nocturne 2T3: re: Your Grades
About
I work in machine learning focusing on interpretability and representation learning, using interpretability to understand complex social phenomena, and AI applications, particularly in medicine. I teach computer science and machine learning in the Division of Engineering Science at the University of Toronto.
My last name is pronounced ger-JOY, with a hard "g", and with the "J" pronounced like the "s" in "measure."
Teaching
Recently Taught
- Data Science and Functional Programming in R Mini-Course Summer 2023
- ECE324 — Machine Intelligence, Software, and Neural Networks Winter 2022, Winter 2023
- ESC180 — Introduction to Computer Programming Fall 2009/2010/2014-2016, 2020-2025
- ESC190 — Algorithms and Data Structures Winter 2021-2026
- MIE490 — Mechanical and Industrial Engineering Capstone Fall-Winter 2022-2023
- SML201 — Introduction to Data Science Spring 2020
- SML480 — Pedagogy of Data Science (NEW!) Spring 2020
- SML310 — Research Projects in Data Science Fall 2019, Fall 2018
- SML201 — Introduction to Data Science Spring 2019
- CSC411/CSC2515 — Machine Learning and Data Mining Winter 2018
- CSC411 — Machine Learning and Data Mining Winter 2017
- CSC180 — Introduction to Computer Programming Fall 2014/2015/2016/2020
- STA303/STA1002 — Methods of Data Analysis II Summer 2016
- C4M — Computing for Medicine Winter-Summer 2016
- CSC321 — Introduction to Neural Networks and Machine Learning Winter 2016 (won the CSSU award for excellence in teaching)
- CSC320 — Introduction to Visual Computing Winter 2015
- CSC165 — Mathematical Expression and Reasoning for Computer Science Summer 2014
Grad Students
Sanjana Neelisetty Balaji,
Agentic Multi-Model Pipeline for Invoice Automation, MSc in Applied Computing industry project, 2025-2026
Dawn Duan,
LLMs for Information Extraction, UTIAS M. Eng. project and UTIAS reading course, 2023-2025
Kexin Chen,
Using Social Media Data to Explore Complex Disease, M. Eng. project, 2023-2024; Research and Development of an AI based Software to Recognize Realtime TV Commercials on Low-power Computing Equipment, Mitacs internship, 2024-2025
Chuyi Hou,
Research and Development of an AI based Software to Recognize Realtime TV Commercials on Low-power Computing Equipment, Mitacs internship, 2024-2025
Zixuan Wan,
Enabling Automatic Checking of Empirical Standards Criteria for Academic Publishers, M. Eng project, 2023-2024
Hauze Xu,
Text mining API for automated keywords extraction and tag analysis. Mitacs Business Partnership internship, 2023-2024 M.Eng
Vijaykumar Maraviya,
A Peer Reviewer Recommender System. MEng in Mechanical and Industrial Engineering project, University of Toronto, 2021 (co-supervised with Eldan Cohen).
Danting Ada Dong,
Object Detection and Image Segmentation for Receipt Images. MSc in Applied Computing, University of Toronto, 2021 (co-supervised with Lueder Kahrs).
Elisa Du,
Enriched Understanding of Retail Receipts for Personalized Financial Insights. MSc in Applied Computing, University of Toronto, 2021 (co-supervised with Rohan Alexander).
Thi Hai Van Do,
Merchandise Classification with Machine Learning for E-commerce. MSc in Applied Computing, University of Toronto, 2018.
Undergraduate Student Projects
Kane Pan, Automatic Utterance Labelling with a Local LLM, local Toronto supervisor of collaboration undergraduate student collaboration with Hasson Lab at Princeton University, 2025-2026
Rachel Chan, Learnability of Representability of Patient Time Series Data with Transformers and LSTMs, EngSci thesis, 2025-2026
Lucia Sun, LLMs for large-scale social media analysis for insights on career trajectories in computing, EngSci thesis, 2025-2026
Zhi (Whitney) Ji, Shape-Based Features Complement CLIP Features and Features Learned from Voxels in 3D Object Classification, EngSci thesis, Summer 2025
Minchan Kim, Machine learning for exploring perception of brilliance in music, EngSci thesis, 2024-2025
Paul Yan, Interpreting rotation-variant features in image classification using vision transformers, EngSci thesis, 2024-2025
Andy Cai, Learning representations of microstructures in spatial statistics space for materials design, EngSci thesis, 2024-2025
Ritvik Singh, Optimizing optical spectrometry-based measurement of soil nutrients, EngSci thesis, 2024-2025
Sophie Lee, Quantifying the Complexity of Literary Fiction, EngSci thesis, 2023-2025
Gary Liang, Ronaldo Luo, Cindy Liu, Adam Kabbara, Minahil Bakhtawar, Kina Kim, Undergraduate project on the cognitive science of the game of Wordle, 2024-
Sajjad Hashemi, Improving the cost function of variational autoencoders for material design, Argonne National Laboratory project, 2023-
Haani Ahmed, Speeding Up Reinforcement Learning by Selecting Pretrained Models using Guided Backpropagation, EngSci thesis, 2023-2024
Juho Kim, Exploring the "Honour Culture" Theory Using Social Media Data, EngSci thesis, 2023-2024
Kailyn Yoon, Exploring the Moral Foundations Theory Using Social Media Data, EngSci thesis, 2023-2024
Jasmine Zhang, Robustness in the context of text classification with Transformers, EngSci thesis, 2023-2024
Yiping Wang, Interpretability of ViT when Colour is an Important Cue, EngSci thesis, 2023-2024
Cameron Smith, Interpretability of ConvNets when Colour is an Important Cue, EngSci thesis, 2023-2024
Amy Saranchuk, Interpretability for Self-Supervised Models, EngSci thesis, 2023-2024
Jason Zuo, How do Transformers Use (And Don't Use) Positional Encoding?, EngSci thesis, 2023-2024
Tracy Qian, WGANs for Model Checking of Hierarchical Models for Small Datasets, EngSci thesis, 2023-2024
Niko Marinkovich, Analyzing the Observed Phenomenon that Computer Chess Beat Humans Much Earlier than Computer Go, EngSci thesis, 2023-2024
Kamron Zaidi, Machine Learning of Understanding Brilliant Moves in Board Games, EngSci thesis, 2023-2024
Sadam Alabed Alrazak, Talal Alaeddine, Kevin Karam, Omar Samman, Ahmad Khater, Data Collection on Youth Sports Participation in Canada, MIE capstone project 2023-2024 (client: Sasha Gollish, Faculty of Kinesiology, University of Toronto)
Yichen Mao, Michael Simunec, Jiaming Li, Mavis Chen, Qingyi Xia, Designing, Building, and Validating an App for Coaching Athletes at the University of Toronto, MIE capstone project 2023-2024 (client: Sasha Gollish, Faculty of Kinesiology, University of Toronto)
Pavlos Constas, Vikram Rawal, Matthew Honorio Oliveira, Andreas Constas, Aditya Khan, Kaison Cheung, Najma Sultani, Carrie Chen, Micol Altomare, Michael Akzam, Jiacheng Chen, Vhea He, Lauren Altomare, Heraa Murqi, Asad Khan, Nimit Amikumar Bhanshali, Youssef Rachad, Toward A Reinforcement-Learning-Based System for Adjusting Medication to Minimize Speech Disfluency, summer research project
Ian Wu and Youssef Rachad, Developing materials for introductory computer science courses, work-study students, 2023
Jackson Kaunismaa, Mechanistic Interpretation of Neural Networks, work-study researcher student, 2023
Mustajab Azam, Sajjad Hashemi, Shahzeb Ahmed, Variational Autoencoders for Material Design, MIE Capstone Project, 2023
Sajjad Hashemi, Variational Autoencoders for Material Design (with Noah Paulson)
Jackson Kaunismaa, Mechanistic Interpretation of Neural Networks (independent project, 2022-2023)
Shardul Ghuge, Multivariate Time Series Forecasting of Patient's Health using LSTM (UofT EngSci thesis, 2022-2023)
Jonathan Spraggett, Sim2Real Reinforcement Learning for Soccer skills (UofT EngSci thesis, 2022-2023)
Noelle Lim, Using Machine Learning Transformers to Detect Comorbid Anxiety and ADHD (UofT EngSci thesis, 2022-2023)
Vo Yoang, Investigating How Meaning is Stored and Manipulated by Transformers (UofT EngSci thesis, 2022-2023)
George Saad, Using Pre-Training to Speed Up Deep Reinforcement Learning (UofT EngSci thesis, 2022-2023)
Michael Ruan, Improving Sample Efficiency of Deep Reinforcement Learning With State Representation Learning (UofT EngSci thesis, 2021-2022)
Morgan Sun, Generating Novel Hypotheses from Complex Models of Clinical Data (UofT EngSci thesis, 2021-2022)
Jonathan Spragett, Learning robot soccer-ball-kicking behaviour with reinforcement learning (UofT EngSci thesis, 2021-2022)
Eric Wang, Learning robot walking behaviour with reinforcement learning (UofT EngSci thesis, 2021-2022)
Yize Zhao, Improving content-based video retrieval (UofT EngSci thesis, 2021-2022)
Chi-Chung Cheung, Learning to play Go by playing on smaller Go boards (UofT EngSci thesis, 2021-2022)
Daniel Pinheiro Leal, Pretraining to speed up reinforcement learning for control tasks (UofT EngSci thesis, 2020-2021)
Theodore Block, The Triple Descent Curve when Training Single-Hidden-Layer Neural Networks (UofT EngSci thesis, 2020)
Calvin Tan, Pretraining to speed up Q-learning for card games with large feature spaces (UofT EngSci thesis, 2020-2021)
Coco Zhang, Guided backpropagation and non-monotonic output functions (UofT EngSci thesis, 2020-2021)
Vydhourie Thiyageswaran, May Jiang, and Anthony Hein, Developing an agent for Gin Rummy (Princeton summer work)
Vydhourie Thiyageswaran, Pretraining Transformer Architectures for Q-learning (Princeton CSML IW)
Ryan Lee, Investigating the Double Descent Curve (Princeton Math junior paper, 2020)
Claire S. Lee, Classifying and Understanding Affective States in Bipolar Disorder from Video (Princeton COS498, 2020-)
Daniel K. Chae, Generating Novel Hypotheses from Complex Models of Clinical Data (Princeton COS498, 2020)
Niranjan Shankar, Text Classification for Small Datasets (Princeton COS498, 2020)
Max Piasevoli, Generative Adversarial Networks for Model Checking (Princeton COS498, 2020)
Preeti Iyer, Understanding Urban Mobility in NYC with Latent Factor Models (Princeton undergrad thesis, 2020)
Georgy Noarov, Collecting a Large-Scale Dataset of Fake News (Princeton CSML certificate project 2019-2020)
Ananya Joshi, Creating an Automated Ideological Transformer Using Moral Reframing (Princeton undergrad thesis, 2019)
Navid Korhani, Information Extraction with Small Datasets (UofT EngSci thesis, 2018-2019)
Yoonsun You, Classification of Cervical Spine Fractures in CT Images (UofT EngSci thesis, 2018-2019)
Sam Banning, Information Extraction from Clinical Notes (UofT CSC494, Fall 2017)
Joshua Samson-Seltzer, Computer Vision for Camera Trap Data (UofT GGR417, 2016-2017)
Omobola Okesanjo, Demonstration in Reinforcement Learning (UofT CSC494, Fall 2016)
Ujash Joshi, Photo Orientation Detection with ConvNets (UofT CSC494/CSC495, 2016)
Karo Castro-Wunsch, RNN and Spectral Feature Based Music Analysis and Generation (UofT CSC492, 2016)
Ramaneek Gill, Twitter Hashtag Recommendation and Analysis (UofT CSC494/495, 2015-2016)
My Assignments Around the Web
I enjoy creating and sharing my assignments. I sometimes enjoy Googling my name to see who uses them.
Nifty Assignments at SIGCSE 2017
Used in CPSC231 at the University of Calgary (2017) and in CS2230 at the University of Iowa (2017). Originally designed for CSC180 (2010-2016), with Jackie C.K. Cheung and François Pitt.
Model AI Assignments at EAAI 2018
Used in CSC321 at the University of Toronto (2017) and at Hacettepe University in CMP722 (2017) and CMP784 (2018). Originally designed for CSC321 (2016), with Renjie Liao.
Model AI Assignments at EAAI 2018
Used in part at Udacity as part of the Self-Driving Car Engineer Nanodegree (2016-). Some materials used at the Hebrew University of Jerusalem (2017) and at Yale University (2018). Used at Hacettepe University in BBM406, CMP722, and CMP784 (2017-2018). Used at the University of Toronto in ECE521 (2018). Used by the Intel AI Academy (Week 6). Originally designed for CSC321 and CSC411 (2016-2017).
Nifty Assignments at SIGCSE 2018
Posted on NCWIT's EngageCSEdu. Used in part in the Deep Learning and Artificial Intelligence program at LMU Munich (2019). Originally designed for CSC180 and for contests at the University of Toronto (2014-2016). Used in COMP 202 at McGill University (2020).
Model AI Assignments at EAAI 2019
Used in part in CSC411/2515 at the University of Toronto (Fall 2018). Originally designed for CSC411/2515 (Winter 2018), with Lisa Zhang.
Model AI Assignments at EAAI 2020
Used at NYU 2024-. Originally designed for SML 201 (Spring 2019), with Stephen Keeley.
Tips, Techniques, and Courseware at ITiCSE 2020
Originally designed for SML 201 (Spring 2019), with Claire S. Lee and Jeremy Du.
Conferences
Co-chair, Nifty Assignments at SIGCSE TS (2023-2027).
Co-chair, Symposium on Educational Advances in Artificial Intelligence (EAAI) 2021-2023, co-located with AAAI.
International Scientific Committee, International Olympiad on Artificial Intelligence (IOAI) (2024-).
(Inaugaural) Program Committee: Toronto Machine Learning Summit (2017-2018)
Media
TV appearances around Geoffrey Hinton's Nobel Prize win, including CTV News, Global TV, CityTV, and CBC Television (2024).
Interviewed by CBC Radio on vibe coding (follow-up article) (2025).
New Scientist covered our work on human perception of chess brilliance (2024), also featured in a Chess.com Blog of the Month winner.
Quoted in MIT Technology Review (2017) on teaching machine learning with TensorFlow; also in Business Insider.
Quoted in The Varsity (2017) on AI for literature search and careers in ML/data science; quoted in The Cannon on grading policies.
Computing for Medicine profiled in UofT News (2016).
Miscellania
Just for Fun
Back in grad school, I used to co-ordinate the weekly CSGSBS cookie breaks.
Re: Your Grades at the NΨ 2017 Nocturne Talent Show (lyrics).
How Deep is Your Love with Gradient Descent (note the lyrics: "How deep is your love? I really need to learn.") Source code.