Siamak Ravanbakhsh

Mila > About Mila > Team > Siamak Ravanbakhsh
Core Academic Member
Siamak Ravanbakhsh
Professor, Assistant Professor, McGill University
Siamak Ravanbakhsh

Siamak Ravanbaksh has been an assistant professor at McGill University’s School of Computer Science since August 2019. Before joining McGill and Mila as an assistant professor, he held a similar position at the University of British Columbia. Prior to that, he was a postdoctoral fellow at the Machine Learning Department and the Robotics Institute at Carnegie Mellon University and received his Ph.D. from the University of Alberta. He is broadly interested in the problems of representation learning and inference in AI. His current research focuses on the role of invariance and symmetry in deep representation learning.

Publications

2021-07

Equivariant Networks for Pixelized Spheres
Mehran Shakerinava and Siamak Ravanbakhsh

2021-05

Deep generative models for galaxy image simulations
François Lanusse, Rachel Mandelbaum, Siamak Ravanbakhsh, Chun-Liang Li, Peter Freeman and Barnabás Póczos
Monthly Notices of the Royal Astronomical Society
(2021-05-21)
PDF
Deep generative models for galaxy image simulations
François Lanusse, Rachel Mandelbaum, Siamak Ravanbakhsh, Chun-Liang Li, Peter Freeman and Barnabás Póczos
Monthly Notices of the Royal Astronomical Society
(2021-05-21)
academic.oup.comPDF
Recovering the wedge modes lost to 21-cm foregrounds
Samuel Gagnon-Hartman, Yue Cui, Adrian Liu and Siamak Ravanbakhsh
Monthly Notices of the Royal Astronomical Society
(2021-05-17)
academic.oup.comPDF[LATEST on arXiv: Cosmology and Nongalactic Astrophysics (2021-05-25)]

2020-07

Universal Equivariant Multilayer Perceptrons
Incidence Networks for Geometric Deep Learning
Marjan Albooyeh, Daniele Bertolini and Siamak Ravanbakhsh
ICML 2020
(2020-07-12)
icml.ccPDF

2020-06

Equivariant Maps for Hierarchical Structures.
Renhao Wang, Marjan Albooyeh and Siamak Ravanbakhsh
arXiv preprint arXiv:2006.03627
(2020-06-05)
ui.adsabs.harvard.eduPDF

2020-01

Designing networks to accurately learn 2D turbulence closures
Keaton Burns, Ronan Legin, Adrian Liu, Laurence Perreault-Levasseur, Yashar Hezaveh, Siamak Ravanbakhsh and Gregory Wagner
APS Division of Fluid Dynamics Meeting Abstracts
(2020-01-01)
ui.adsabs.harvard.edu
Equivariant Networks for Hierarchical Structures
Renhao Wang, Marjan Albooyeh and Siamak Ravanbakhsh
NEURIPS 2020
(2020-01-01)
papers.nips.ccPDF

2019-10

LRP2020: Machine Learning Advantages in Canadian Astrophysics
K.A. Venn, S. Fabbro, A Liu, Y. Hezaveh, L. Perreault-Levasseur, G. Eadie, S. Ellison, J. Woo, Jj. Kavelaars, K.M. Yi, R. Hlozek, J. Bovy, H. Teimoorinia, S. Ravanbakhsh and L. Spencer
arXiv preprint arXiv:1910.00774
(2019-10-02)
export.arxiv.orgPDF
Low-Dimensional Perturb-and-MAP Approach for Learning Restricted Boltzmann Machines
Jakub M. Tomczak, Szymon Zaręba, Siamak Ravanbakhsh and Russell Greiner
Neural Processing Letters
(2019-10-01)
link.springer.comPDF

2019-09

Equivariant Entity-Relationship Networks
Devon Graham and Siamak Ravanbakhsh
arXiv preprint arXiv:1903.09033
(2019-09-25)
ui.adsabs.harvard.eduPDF

2019-07

Improved Knowledge Graph Embedding Using Background Taxonomic Information
Bahare Fatemi, Siamak Ravanbakhsh and David Poole
AAAI 2019
(2019-07-17)
aaai.org

Publications collected and formatted using Paperoni

array(1) { ["wp-wpml_current_language"]=> string(2) "en" }