I defended my PhD thesis!
Youtube recording of my PhD thesis defense at NYU Center for Neural Science.
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.
Youtube recording of my PhD thesis defense at NYU Center for Neural Science.
Geometric intuition for our recent paper on statistical whitening using overcomplete bases.
My (virtual) talk on our ICLR 2023 paper at Mila Quebec Neural AI RG.
Code snippet for generating QR codes with transparent backgrounds.
A no-math intuitive account of our method published in ICLR 2023.
My internship research project at Google on machine learning for video compression.
Can we rely on VAEs to generate reproducible latents?
Writing L1 and L2 vector norms with reverse- and forward-mode autodiff.
Training a multilayer perceptron built in pure C++.
Building a trainable multilayer perceptron in pure C++.
Creating a bare-bones linear algebra library to train a neural net.
Poisson-Identifiable Variational Autoencoder w/ PyTorch implementation.
Update: I wrote about how my internship experience went here.
Python implementation of adaptive spiking neural net proposed in Gutierrez and Deneve eLife 2019.
Simple code to save activations of a model’s intermediate layers.
A cool algorithm that adaptively approximates the column space of a matrix using random projections.