AudioTech Refiner: Eliminating Noise and Distortion in Low-Bandwidth Audio

Improving Quality of Online Voice Calls

ECG Analysis Using Deep CNNs

An application of deep convolutional neural network model to specify cardiovascular diseases via analyzing ECG

Employee Attrition Factors Prediction

Using ML to identify and combat employee attrition factors

Handwriting Recognition Using Deep Learning

Recognizing Handwritten Text in Physical Documents

SmileDetector: Detecting and Rating Smiles

A web application that uses machine learning to detect and rate smiles

WallStreetBots: Stock Price Prediction

Price prediction and portfolio/market analysis using NLP and reinforcement learning.

Projects (2021-2022)

Our Projects in 2021-2022

Leading a Project

A Guide to Brainstorming and Leading a Project.

Projects (2020-2021)

Our Projects in 2020-2021

Out-Of-Distribution Detection (OoDD)

A Research Project on Benchmarking the Latest Generative Model Based OoOD Methods.

Rust for Machine Learning: Benchmarking Performance in One-shot

Reproducing "Siamese Neural Networks for One-shot Image Recognition" and benchmarking implementation performance and results.

Hand Gestures and Hand Tracking for Web Browsing

Developing hand gesture detection for controlling web browsing.

Musical Style Transfer

Transfer learning in the domain of musical styles.

Real Estate Price Prediction

Real estate price prediction and transfer learning with CNNs.

Stock Price Prediction

Predicting stock prices.

The Humerus Bot

An applied ML NLP project designed to win Cards Against Humanity, a popular humor-based party game. **[Full]**

GitLab Pages Website for UTMIST.

Projects (2019-2020)

Our projects in 2019-2020

NeurIPS 2019 Reproducibility: SMILe

Reproducing SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies (Zemel et al.)


The UofT Machine Intelligence Student Team Runner (MISTR) is a Discord bot serving the UTMIST Discord server.


Wrapper written around SchedJulia to schedule interviews.

Projects (2018-2019)

Our projects in 2018-2019

ICLR 2019 Reproducibility: Alarm Forgetting Example

An Empirical Study of Example Forgetting during Deep Neural Network Learning (Mariya Toneva*, Alessandro Sordoni*, Remi Tachet des Combes*, Adam Trischler, Yoshua Bengio, Geoffrey J. Gordon)

ICLR 2019 Reproducibility: Initialized Equilibrium Propagation

Reproducing Initialized Equilibrium Propagation for Backprop-free Training (Peter O'Connor, Efstratios Gavves, Max Welling)

GitHub Pages Website for UTMIST.