Jacob Kelly

Jacob Kelly

I'm an undergrad in Computer Science, Math, and Stats at the University of Toronto working with David Duvenaud at the Vector Institute. I'm interested in latent variable models, neural ODEs, variational inference, and genomics. My long term research goal is to combine machine learning with novel sources of data to develop new tools for improved diagnosis and treatment of patients.

Previously, I did computational biology research with Benjamin Haibe-Kains at Princess Margaret Cancer Research. Some of my hobbies include running, rock climbing, and reading. I'm always open to meeting new people, feel free to get in touch if you'd like to chat.


Learning Differential Equations that are Easy to Solve

Neural ODEs become expensive to solve numerically as training progresses. We introduce a differentiable surrogate for the time cost of standard numerical solvers using higher-order derivatives of solution trajectories. These derivatives are efficient to compute with Taylor-mode automatic differentiation. Optimizing this additional objective trades model performance against the time cost of solving the learned dynamics.

Jacob Kelly*, Jesse Bettencourt*, Matthew James Johnson, David Duvenaud

pdf | code | bibtex

*equal contribution


Elastic Net Regression to Predict Drug Response from Gene Expression

We develop drug-specific models to detect biomarkers in gene expression data for predicting the area under the drug-dose response curve (AUC) of cell lines for acute myeloid leukemia (AML). We apply our model to two pharmacogenomic datasets, one consisting of data from immortalized cell lines, the other ex-vivo primary cell lines from patients. We use linear regression with elastic net regularization as our model and compare methods for feature selection.

Jacob Kelly, Arvind Mer, Sisira Nair, Hassan Mahmoud, Benjamin Haibe-Kains


Genomic Sequencing

To learn about genomic sequencing, I implemented Boyer-Moore for performing exact sequence alignment. I also implemented the Z algorithm to efficiently generate indices of the query string needed for the Boyer-Moore algorithm.

Jacob Kelly


ICLR 2019 Reproducibility Challenge

We implemented the ICLR 2019 submission (later accepted) "Initialized Equilibrium Propagation for Backprop-Free Training" by O'Connor et al. as part of the ICLR 2019 Reproducibility Challenge.

Matthieu Chan Chee, Jad Ghalayini, Jacob Kelly, Winnie Xu



I implemented a sequence to sequence model to learn to sort numbers. I used an encoder-decoder LSTM architecture with a "pointer" attention mechanism developed by Vinyals et al. (Pointer Networks) to take advantage of the fact that the output of the model is a permutation of its input.

Jacob Kelly

blog | code

Pocket Guide

We developed an Android app for indoor navigation through SickKids hospital using bluetooth signals from Estimote Beacons. We use SPFA on a map of beacon locations to efficiently generate the shortest path from the user's current location to their destination. We estimate the current location using signal strengths from nearby beacons and track over time using an exponentially weighted average. Developed in summer 2016 at Cossette.

Bruno Almeida, Jacob Kelly, Gabriel Yeung

slides | code

alphabetical order


I have been a Teaching Assistant for the following: