about me

I'm a Machine Learning and Vision Scientist at Apple, working at the intersection of graphics, image/video coding, and human & computer vision.

I have a PhD in Neuroscience from NYU, where I was advised by Eero Simoncelli and David Heeger. My dissertation focuses on theories of adaptive efficient coding in neural networks, and representational geometry. Formerly, I was a PhD intern on the Open Codecs team at Google where I worked on adaptive ML models for video compression.

I was born and raised in Yellowknife, Northwest Territories, Canada 🥶🍁. My BSc is in Physiology and Physics from McGill University, where I began working on what would eventually become my MSc at the University of Western Ontario (our lab migrated), modeling neural correlates of visual attention and memory, advised by Julio Martinez-Trujillo.

recent notes

I defended my PhD thesis!

less than 1 minute read

Youtube recording of my PhD thesis defense at NYU Center for Neural Science.

Statistical whitening with 1D projections

3 minute read

Geometric intuition for our recent paper on statistical whitening using overcomplete bases.

I gave a talk on stochastic shape metrics

less than 1 minute read

My (virtual) talk on our ICLR 2023 paper at Mila Quebec Neural AI RG.

Python QR code generator for poster presentations

1 minute read

Code snippet for generating QR codes with transparent backgrounds.

Stochastic shape metrics without the agonizing pain

9 minute read

A no-math intuitive account of our method published in ICLR 2023.

My Google PhD internship experience

3 minute read

My internship research project at Google on machine learning for video compression.

Reproducible latents

1 minute read

Can we rely on VAEs to generate reproducible latents?

My first C++ open source contribution – Stan Library

5 minute read

Writing L1 and L2 vector norms with reverse- and forward-mode autodiff.

C++ neural networks from scratch – Pt 3. model training

3 minute read

Training a multilayer perceptron built in pure C++.

C++ neural networks from scratch – Pt 2. building an MLP

4 minute read

Building a trainable multilayer perceptron in pure C++.

C++ neural networks from scratch – Pt 1. building a matrix library

12 minute read

Creating a bare-bones linear algebra library to train a neural net.

Nonlinear neural data dimensionality reduction with PI-VAE

6 minute read

Poisson-Identifiable Variational Autoencoder w/ PyTorch implementation.

How I prepared for (and passed!) the Google coding interviews

7 minute read

Update: I wrote about how my internship experience went here.

Adaptive recurrent spiking autoencoder

7 minute read

Python implementation of adaptive spiking neural net proposed in Gutierrez and Deneve eLife 2019.

Saving PyTorch activations w/ forward hooks

1 minute read

Simple code to save activations of a model’s intermediate layers.

PyTorch Randomized adaptive range finder

7 minute read

A cool algorithm that adaptively approximates the column space of a matrix using random projections.