Presentations

Heisenberg v. Kac-Moody, at VUB, Brussels, Thursday, January 24, 2019
 I’ll discuss recent work on the structure of Heisenberg categories and their generalizations, especially the higher-level Heisenberg categorifications defined by Brundan.  This includes the long sought-after identification of their Grothendieck groups with Heisenberg algebras, and a construction of categorical Kac-Moody actions from Heisenberg actions which unifies essentially all examples of categorical Kac-Moody actions of interest to representation theorists.  This is joint work with Jonathan Brundan and Alistair Savage. Read more about Heisenberg v. Kac-Moody
ConvART: Improving Adaptive Resonance Theory for Unsupervised Image Clustering, at CVIS 2018, Tuesday, November 6, 2018
While supervised learning techniques have become increasingly adept at separating images into different classes, these techniques require large amounts of labelled data which may not always be available. We propose a novel neuro-dynamic method for unsupervised image clustering by combining 2 biologically-motivated models: Adaptive Resonance Theory (ART) and Convolutional Neural Networks (CNN). ART networks are unsupervised clustering algorithms that have high stability in preserving learned information while quickly learning new information. Meanwhile, a major property of CNNs is their... Read more about ConvART: Improving Adaptive Resonance Theory for Unsupervised Image Clustering
Breaking Into Deep Learning: 5 projects to get you inspired, at University of Waterloo: Data Science Club, Saturday, November 3, 2018
It's natural to feel lost when you want to start working in a new field. All you need is a little inspiration to get you going in the right direction. We will discuss 5 exciting projects that might spark your interest in one of the many areas of deep learning and give you some ideas of what to work on. Read more about Breaking Into Deep Learning: 5 projects to get you inspired
Making the Most of Graduate Research in AI, at StartAI 2018, Saturday, November 3, 2018
If you're willing to take the pay cut and make the time commitment to go to grad school, then your graduate research better be worth it. To help you find a graduate research topic you can be passionate about, we will discuss the different areas of AI you can study in grad school, the exciting applications being actively developed in these areas, and some of the technical details behind each of them.  Read more about Making the Most of Graduate Research in AI
Coherent sheaves on Hilbert schemes through the Coulomb lens, at University of Virginia, Friday, October 19, 2018:
UVA-2018.pdf
The Hilbert scheme of the plane (or more generally, the resolution of the type A Kleinian singularity) has a surprising description as a Coulombbranch in the sense of Braverman, Finkelberg and Nakajima; this gives a rather odd looking presentation of the projective coordinate ring of this variety.  It turns out that this presentation is very well adapted to describing the tilting generators constructed using Bezrukavnikov and Kaledin's perspective; of course, there are many other interesting aspects of the combinatorics of coherent sheaves on these varieties, which hopefully the... Read more about Coherent sheaves on Hilbert schemes through the Coulomb lens
Kinodynamic Planning with µ-Calculus Specifications, at University of Waterloo, Friday, August 10, 2018:
larocque_defense_extended.pdf

This presentation is an uncut version of my thesis defense. It includes many extra details and examples that were not presented at the defense presentation in order to provide viewers with a deeper overview of my Master's research.

Included in this talk is a section outlining µ-calculus syntax along with example specifications and explanations as to how such formulations can be parsed.

Many thanks to my spectacular supervisor, Jun Liu, as well as Brian Ingalls and Stephen Smith who were members of the defense committee.

Read more about Kinodynamic Planning with µ-Calculus Specifications

Pages