filmov
tv
ICLR 2021 Keynote - 'Geometric Deep Learning: The Erlangen Programme of ML' - M Bronstein
Показать описание
Geometric Deep Learning: The Erlangen Programme of ML - ICLR 2021 Keynote by Michael Bronstein (Imperial College London / IDSIA / Twitter)
“Symmetry, as wide or as narrow as you may define its meaning, is one idea by which man through the ages has tried to comprehend and create order, beauty, and perfection.” This poetic definition comes from the great mathematician Hermann Weyl, credited with laying the foundation of our modern theory of the universe. Another great physicist, Philip Anderson, said that "it is only slightly overstating the case to say that physics is the study of symmetry."
In mathematics, symmetry was crucial in the foundation of geometry as we know it in the 19th century. Now it could have a similar impact on another emerging field. Deep Learning success in recent decades is significant – from revolutionising data science to landmark achievements in computer vision, board games, and protein folding. At the same time, a lack of unifying principles makes it is difficult to understand the relations between different neural network architectures resulting in the reinvention and re-branding of the same concepts.
Michael Bronstein is a professor at Imperial College London and Head of Graph ML Research at Twitter, who is working to bring geometric unification of deep learning through the lens of symmetry. In his ICLR 2021 keynote lecture, he presents a common mathematical framework to study the most successful network architectures, giving a constructive procedure to build future machine learning in a principled way that could be applied in new domains such as social science, biology, and drug design.
Animation: Jakub Makowski
“Symmetry, as wide or as narrow as you may define its meaning, is one idea by which man through the ages has tried to comprehend and create order, beauty, and perfection.” This poetic definition comes from the great mathematician Hermann Weyl, credited with laying the foundation of our modern theory of the universe. Another great physicist, Philip Anderson, said that "it is only slightly overstating the case to say that physics is the study of symmetry."
In mathematics, symmetry was crucial in the foundation of geometry as we know it in the 19th century. Now it could have a similar impact on another emerging field. Deep Learning success in recent decades is significant – from revolutionising data science to landmark achievements in computer vision, board games, and protein folding. At the same time, a lack of unifying principles makes it is difficult to understand the relations between different neural network architectures resulting in the reinvention and re-branding of the same concepts.
Michael Bronstein is a professor at Imperial College London and Head of Graph ML Research at Twitter, who is working to bring geometric unification of deep learning through the lens of symmetry. In his ICLR 2021 keynote lecture, he presents a common mathematical framework to study the most successful network architectures, giving a constructive procedure to build future machine learning in a principled way that could be applied in new domains such as social science, biology, and drug design.
Animation: Jakub Makowski
0:38:27
ICLR 2021 Keynote - 'Geometric Deep Learning: The Erlangen Programme of ML' - M Bronstein
1:00:09
Geometric deep learning, from Euclid to drug design
1:12:40
Geometry | Geometric Deep Learning by Michael Bronstein
0:24:48
Michael Bronstein: Geometric Deep Learning - The Erlangen Programme of ML
0:14:28
Graph Neural Networks - a perspective from the ground up
0:59:12
AMMI Course 'Geometric Deep Learning' - Lecture 1 (Introduction) - Michael Bronstein
0:00:17
ICML 2021: Unsupervised Learning of Visual 3D Keypoints for Control
0:53:15
INSAIT Tech Series: Prof. Michael Bronstein - Geometric Deep Learning
0:02:22
The Erlangen Program
0:54:28
Geometric Deep Learning: Past, Present, And Future, by Michael Bronstein
0:06:43
Space-Time Graph Neural Networks (ICLR 2022)
5:13:19
iGDL 2021 Israeli Geometric Deep Learning Workshop
0:55:17
MIUA 2021 Keynote Lecture: Prof. Mihaela van der Schaar - The Role of Imaging in Machine Learning
0:43:07
Maria Bånkestad: Geometric deep learning with graph neural networks
0:06:55
EQUIVARIANCE RULES! - Geometric Deep Learning Tutorial - Equivariant Neural Networks Visualised
1:09:06
MIA and CC&E Joint Seminar: Michael Bronstein, Geometric deep learning for function protein desi...
0:52:42
Petar Veličkovć - Geometric Deep Learning: Grids, Graphs, Groups, Geodesics and Gauges
0:01:50
Why ICLR?
0:18:58
What is multiset-equivariance? [ICLR 2022]
0:03:49
Writing a High-Quality Research Paper to Top Conferences: CVPR, NIPS, ICCV, ICML, and ICLR
0:09:33
Self-Construction Neural Networks through Random Mutation (ICLR 2021 NERL Workshop)
1:15:14
Beyond the Patterns 28 - Petar Veličković - Geometric Deep Learning
0:59:59
Modeling molecules with geometric ML methods - Hannes Stärk | The Science Circle
0:11:55
Dichotomy of Control - ICLR 2023 Oral
Комментарии