Siamak Ravanbakhsh

Laurence Perreault-Levasseur

Biographie

Siamak Ravanbakhsh est professeur adjoint à l’École d’informatique de l’Université McGill depuis août 2019. Avant de se joindre à McGill et à Mila – Institut québécois d’intelligence artificielle, il a occupé un poste similaire à l’Université de la Colombie-Britannique. De 2015 à 2017, il a été stagiaire postdoctoral au Département d’apprentissage automatique et à l’Institut de robotique de l’Université Carnegie Mellon, et il a obtenu un doctorat de l’Université de l’Alberta. Il s’intéresse aux problèmes de l’apprentissage de la représentation et de l’inférence dans l’IA.

Ses recherches actuelles portent sur le rôle de la symétrie et de l’invariance dans l’apprentissage profond des représentations.

Étudiants actuels

Tara Akhound-Sadegh

Doctorat - McGill

Co-superviseur⋅e :

Noah El Rimawi-Fine

Maîtrise recherche - McGill

Superviseur⋅e principal⋅e :

Mathieu Blanchette

Qianyi Gao

Maîtrise recherche - McGill

Daria Goptsii Goptsii

Maîtrise professionnelle - McGill

Vineet Jain

Doctorat - McGill

Oumar Kaba

Doctorat - McGill

Site web

Daniel Levy

Doctorat - McGill

Xiusi Li

Doctorat - McGill

Maîtrise recherche - McGill

Raphael Michnik

Stagiaire de recherche - McGill

Site web

Khang Ngo

Doctorat - McGill

David Nitchi

Collaborateur·rice de recherche - McGill

Mohammad Pedramfar

Postdoctorat - McGill

Kusha Sareen

Maîtrise recherche - McGill

Doctorat - McGill

Collaborateur·rice alumni - McGill

Publications

Equivariant Networks for Pixelized Spheres

Mehran Shakerinava

Pixelizations of Platonic solids such as the cube and icosahedron have been widely used to represent spherical data, from climate records to… (voir plus) Cosmic Microwave Background maps. Platonic solids have well-known global symmetries. Once we pixelize each face of the solid, each face also possesses its own local symmetries in the form of Euclidean isometries. One way to combine these symmetries is through a hierarchy. However, this approach does not adequately model the interplay between the two levels of symmetry transformations. We show how to model this interplay using ideas from group theory, identify the equivariant linear maps, and introduce equivariant padding that respects these symmetries. Deep networks that use these maps as their building blocks generalize gauge equivariant CNNs on pixelized spheres. These deep networks achieve state-of-the-art results on semantic segmentation for climate data and omnidirectional image processing. Code is available at https://git.io/JGiZA.

2021-06-30

Proceedings of the 38th International Conference on Machine Learning (publié)

proceedings.mlr.press

Deep Generative Models for Galaxy Image Simulations

François Lanusse

Rachel Mandelbaum

Chun-Liang Li

Peter Freeman

Barnabás Póczos

Image simulations are essential tools for preparing and validating the analysis of current and future wide-field optical surveys. However, t… (voir plus)he galaxy models used as the basis for these simulations are typically limited to simple parametric light profiles, or use a fairly limited amount of available space-based data. In this work, we propose a methodology based on Deep Generative Models to create complex models of galaxy morphologies that may meet the image simulation needs of upcoming surveys. We address the technical challenges associated with learning this morphology model from noisy and PSF-convolved images by building a hybrid Deep Learning/physical Bayesian hierarchical model for observed images, explicitly accounting for the Point Spread Function and noise properties. The generative model is further made conditional on physical galaxy parameters, to allow for sampling new light profiles from specific galaxy populations. We demonstrate our ability to train and sample from such a model on galaxy postage stamps from the HST/ACS COSMOS survey, and validate the quality of the model using a range of second- and higher-order morphology statistics. Using this set of statistics, we demonstrate significantly more realistic morphologies using these deep generative models compared to conventional parametric models. To help make these generative models practical tools for the community, we introduce GalSim-Hub, a community-driven repository of generative models, and a framework for incorporating generative models within the GalSim image simulation software.

2021-04-29

Monthly Notices of the Royal Astronomical Society (publié)

arxiv.org

Recovering the Wedge Modes Lost to 21-cm Foregrounds

Samuel Gagnon-Hartman

Yue Cui

Adrian Liu

One of the critical challenges facing imaging studies of the 21-cm signal at the Epoch of Reionization (EoR) is the separation of astrophysi… (voir plus)cal foreground contamination. These foregrounds are known to lie in a wedge-shaped region of

2021-04-21

Monthly Notices of the Royal Astronomical Society (inconnu)

arxiv.org

Universal Equivariant Multilayer Perceptrons

Group invariant and equivariant Multilayer Perceptrons (MLP), also known as Equivariant Networks, have achieved remarkable success in learni… (voir plus)ng on a variety of data structures, such as sequences, images, sets, and graphs. Using tools from group theory, this paper proves the universality of a broad class of equivariant MLPs with a single hidden layer. In particular, it is shown that having a hidden layer on which the group acts regularly is sufficient for universal equivariance (invariance). A corollary is unconditional universality of equivariant MLPs for Abelian groups, such as CNNs with a single hidden layer. A second corollary is the universality of equivariant MLPs with a high-order hidden layer, where we give both group-agnostic bounds and means for calculating group-specific bounds on the order of hidden layer that guarantees universal equivariance (invariance).

2020-11-20

Proceedings of the 37th International Conference on Machine Learning (publié)

proceedings.mlr.press

Equivariant Maps for Hierarchical Structures

Renhao Wang

Marjan Albooyeh

Laurence Perreault-Levasseur

2019-12-31

Advances in Neural Information Processing Systems 33 (NeurIPS 2020) (publié)

dblp.uni-trier.de

Machine Learning Advantages in Canadian Astrophysics

Kim Venn

Sébastien Fabbro

Adrian Liu

Yashar Hezaveh

Gwendolyn Eadie

Sara Ellison

Joanna Woo

JJ Kavelaars

Kwang Moo Yi

Renée Hložek

Jo Bovy

Hossen Teimoorinia

Locke Spencer

The application of machine learning (ML) methods to the analysis of astrophysical datasets is on the rise, particularly as the computing pow… (voir plus)er and complex algorithms become more powerful and accessible. As the field of ML enjoys a continuous stream of breakthroughs, its applications demonstrate the great potential of ML, ranging from achieving tens of millions of times increase in analysis speed (e.g., modeling of gravitational lenses or analysing spectroscopic surveys) to solutions of previously unsolved problems (e.g., foreground subtraction or efficient telescope operations). The number of astronomical publications that include ML has been steadily increasing since 2010.
With the advent of extremely large datasets from a new generation of surveys in the 2020s, ML methods will become an indispensable tool in astrophysics. Canada is an unambiguous world leader in the development of the field of machine learning, attracting large investments and skilled researchers to its prestigious AI Research Institutions. This provides a unique opportunity for Canada to also be a world leader in the application of machine learning in the field of astrophysics, and foster the training of a new generation of highly skilled researchers.

2019-10-01

ArXiv (prépublication)

arxiv.org

Equivariant Entity-Relationship Networks

Devon Graham