no code implementations • 14 Feb 2024 • Theodore Papamarkou, Tolga Birdal, Michael Bronstein, Gunnar Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Liò, Paolo Di Lorenzo, Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T. Schaub, Petar Veličković, Bei Wang, Yusu Wang, Guo-Wei Wei, Ghada Zamzmi
Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models.
1 code implementation • 4 Feb 2024 • Mustafa Hajij, Mathilde Papillon, Florian Frantzen, Jens Agerberg, Ibrahem AlJabea, Ruben Ballester, Claudio Battiloro, Guillermo Bernárdez, Tolga Birdal, Aiden Brent, Peter Chin, Sergio Escalera, Simone Fiorellino, Odin Hoff Gardaa, Gurusankar Gopalakrishnan, Devendra Govil, Josef Hoppe, Maneel Reddy Karri, Jude Khouja, Manuel Lecha, Neal Livesay, Jan Meißner, Soham Mukherjee, Alexander Nikitin, Theodore Papamarkou, Jaro Prílepok, Karthikeyan Natesan Ramamurthy, Paul Rosen, Aldo Guzmán-Sáenz, Alessandro Salatiello, Shreyas N. Samaga, Simone Scardapane, Michael T. Schaub, Luca Scofano, Indro Spinelli, Lev Telyatnikov, Quang Truong, Robin Walters, Maosheng Yang, Olga Zaghen, Ghada Zamzmi, Ali Zia, Nina Miolane
We introduce TopoX, a Python software suite that provides reliable and user-friendly building blocks for computing and machine learning on topological domains that extend graphs: hypergraphs, simplicial, cellular, path and combinatorial complexes.
2 code implementations • NeurIPS 2023 • Sophia Sanborn, Nina Miolane
We introduce a general method for achieving robust group-invariance in group-equivariant convolutional neural networks ($G$-CNNs), which we call the $G$-triple-correlation ($G$-TC) layer.
no code implementations • 17 Oct 2023 • David Klindt, Sophia Sanborn, Francisco Acosta, Frédéric Poitevin, Nina Miolane
Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features.
1 code implementation • 28 Sep 2023 • Adele Myers, Caitlin Taylor, Emily Jacobs, Nina Miolane
We seek to investigate this connection by developing tools that quantify 3D shape changes that occur in the brain during sex hormone fluctuations.
1 code implementation • 26 Sep 2023 • Mathilde Papillon, Mustafa Hajij, Helen Jenne, Johan Mathe, Audun Myers, Theodore Papamarkou, Tolga Birdal, Tamal Dey, Tim Doster, Tegan Emerson, Gurusankar Gopalakrishnan, Devendra Govil, Aldo Guzmán-Sáenz, Henry Kvinge, Neal Livesay, Soham Mukherjee, Shreyas N. Samaga, Karthikeyan Natesan Ramamurthy, Maneel Reddy Karri, Paul Rosen, Sophia Sanborn, Robin Walters, Jens Agerberg, Sadrodin Barikbin, Claudio Battiloro, Gleb Bazhenov, Guillermo Bernardez, Aiden Brent, Sergio Escalera, Simone Fiorellino, Dmitrii Gavrilev, Mohammed Hassanin, Paul Häusner, Odin Hoff Gardaa, Abdelwahed Khamis, Manuel Lecha, German Magai, Tatiana Malygina, Rubén Ballester, Kalyan Nadimpalli, Alexander Nikitin, Abraham Rabinowitz, Alessandro Salatiello, Simone Scardapane, Luca Scofano, Suraj Singh, Jens Sjölund, Pavel Snopov, Indro Spinelli, Lev Telyatnikov, Lucia Testa, Maosheng Yang, Yixiao Yue, Olga Zaghen, Ali Zia, Nina Miolane
This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning.
no code implementations • 12 Jun 2023 • Bongjin Koo, Julien Martel, Ariana Peck, Axel Levy, Frédéric Poitevin, Nina Miolane
Cryogenic electron microscopy (cryo-EM) has transformed structural biology by allowing to reconstruct 3D biomolecular structures up to near-atomic resolution.
4 code implementations • 20 Apr 2023 • Mathilde Papillon, Sophia Sanborn, Mustafa Hajij, Nina Miolane
The natural world is full of complex systems characterized by intricate relations between their components: from social interactions between individuals in a social network to electrostatic interactions between atoms in a protein.
1 code implementation • 20 Dec 2022 • Francisco Acosta, Sophia Sanborn, Khanh Dao Duc, Manu Madhav, Nina Miolane
The neural manifold hypothesis postulates that the activity of a neural population forms a low-dimensional manifold whose structure reflects that of the encoded task variables.
no code implementations • 21 Nov 2022 • Alice Le Brigant, Jules Deschamps, Antoine Collas, Nina Miolane
We introduce the information geometry module of the Python package Geomstats.
1 code implementation • 16 Nov 2022 • Thibault Niederhauser, Adam Lester, Nina Miolane, Khanh Dao Duc, Manu S. Madhav
Hippocampal place cells can encode spatial locations of an animal in physical or task-relevant spaces.
1 code implementation • 4 Oct 2022 • Adele Myers, Nina Miolane
We propose a metric learning paradigm, Regression-based Elastic Metric Learning (REML), which optimizes the elastic metric for geodesic regression on the manifold of discrete curves.
no code implementations • 29 Sep 2022 • Youssef Nashed, Ariana Peck, Julien Martel, Axel Levy, Bongjin Koo, Gordon Wetzstein, Nina Miolane, Daniel Ratner, Frédéric Poitevin
Cryogenic electron microscopy (cryo-EM) provides a unique opportunity to study the structural heterogeneity of biomolecules.
no code implementations • 20 Sep 2022 • Mathilde Papillon, Mariel Pettee, Nina Miolane
We summarize the model and results of PirouNet, a semi-supervised recurrent variational autoencoder.
no code implementations • 8 Aug 2022 • Saiteja Utpala, Praneeth Vepakomma, Nina Miolane
In that spirit, the only geometric statistical query for which a differential privacy mechanism has been developed, so far, is for the release of the sample Fr\'echet mean: the \emph{Riemannian Laplace mechanism} was recently proposed to privatize the Fr\'echet mean on complete Riemannian manifolds.
no code implementations • 23 Jul 2022 • Nicolas Legendre, Khanh Dao Duc, Nina Miolane
Recent advances in variational autoencoders (VAEs) have enabled learning latent manifolds as compact Lie groups, such as $SO(d)$.
1 code implementation • 21 Jul 2022 • Mathilde Papillon, Mariel Pettee, Nina Miolane
Using Artificial Intelligence (AI) to create dance choreography with intention is still at an early stage.
3 code implementations • 1 Jun 2022 • Mustafa Hajij, Ghada Zamzmi, Theodore Papamarkou, Nina Miolane, Aldo Guzmán-Sáenz, Karthikeyan Natesan Ramamurthy, Tolga Birdal, Tamal K. Dey, Soham Mukherjee, Shreyas N. Samaga, Neal Livesay, Robin Walters, Paul Rosen, Michael T. Schaub
Topological deep learning is a rapidly growing field that pertains to the development of deep learning models for data supported on topological domains such as simplicial complexes, cell complexes, and hypergraphs, which generalize many domains encountered in scientific computations.
1 code implementation • 15 Mar 2022 • Axel Levy, Frédéric Poitevin, Julien Martel, Youssef Nashed, Ariana Peck, Nina Miolane, Daniel Ratner, Mike Dunne, Gordon Wetzstein
We introduce cryoAI, an ab initio reconstruction algorithm for homogeneous conformations that uses direct gradient-based optimization of particle poses and the electron scattering potential from single-particle cryo-EM data.
no code implementations • 8 Jan 2022 • Claire Donnat, Axel Levy, Frederic Poitevin, Ellen Zhong, Nina Miolane
Recent breakthroughs in high-resolution imaging of biomolecules in solution with cryo-electron microscopy (cryo-EM) have unlocked new doors for the reconstruction of molecular volumes, thereby promising further advances in biology, chemistry, and pharmacological research.
no code implementations • 29 Nov 2021 • Faria Huq, Adrish Dey, Sahra Yusuf, Dena Bazazian, Tolga Birdal, Nina Miolane
Our experiments demonstrate that constraining the synchronization on the Riemannian manifold $SO(n)$ improves the estimation of the functional maps, while our RLFM sampler provides for the first time an uncertainty quantification of the results.
no code implementations • 27 Jul 2020 • Claire Donnat, Nina Miolane, Frederick de St Pierre Bunbury, Jack Kreindler
Computer-Aided Diagnosis has shown stellar performance in providing accurate medical diagnoses across multiple testing modalities (medical images, electrophysiological signals, etc.).
Applications
1 code implementation • ICLR 2019 • Nina Miolane, Alice Le Brigant, Johan Mathe, Benjamin Hou, Nicolas Guigui, Yann Thanwerdas, Stefan Heyder, Olivier Peltre, Niklas Koep, Hadi Zaatiti, Hatem Hajri, Yann Cabanes, Thomas Gerald, Paul Chauchat, Christian Shewmake, Bernhard Kainz, Claire Donnat, Susan Holmes, Xavier Pennec
We introduce Geomstats, an open-source Python toolbox for computations and statistics on nonlinear manifolds, such as hyperbolic spaces, spaces of symmetric positive definite matrices, Lie groups of transformations, and many more.
no code implementations • 19 Nov 2019 • Nina Miolane, Frédéric Poitevin, Yee-Ting Li, Susan Holmes
As such, it opens the door to geometric approaches for unsupervised estimations of orientations and camera parameters, making possible fast cryo-EM biomolecule reconstruction.
no code implementations • CVPR 2020 • Nina Miolane, Susan Holmes
One of the challenges that naturally arises consists of finding a lower-dimensional subspace for representing such manifold-valued data.
1 code implementation • 4 Feb 2019 • Johan Mathe, Nina Miolane, Nicolas Sebastien, Jeremie Lequeux
In this paper, we introduce a Long-Term Recurrent Convolutional Network using Numerical Weather Predictions (NWP) to predict, in turn, PV production in the 24-hour and 48-hour forecast horizons.
2 code implementations • ICLR 2019 • Nina Miolane, Johan Mathe, Claire Donnat, Mikael Jorda, Xavier Pennec
This paper also presents a review of manifolds in machine learning and an overview of the geomstats package with examples demonstrating its use for efficient and user-friendly Riemannian geometry.
1 code implementation • 2 May 2018 • Benjamin Hou, Nina Miolane, Bishesh Khanal, Matthew C. H. Lee, Amir Alansary, Steven McDonagh, Jo V. Hajnal, Daniel Rueckert, Ben Glocker, Bernhard Kainz
In this paper, we propose a general Riemannian formulation of the pose estimation problem.
no code implementations • 6 Sep 2016 • Nina Miolane, Susan Holmes, Xavier Pennec
We use tools from geometric statistics to analyze the usual estimation procedure of a template shape.