Zobrazeno 1 - 10
of 3 161
pro vyhledávání: '"Sanborn, P."'
Autor:
Sanborn, Sophia, Mathe, Johan, Papillon, Mathilde, Buracas, Domas, Lillemark, Hansen J, Shewmake, Christian, Bertics, Abby, Pennec, Xavier, Miolane, Nina
The enduring legacy of Euclidean geometry underpins classical machine learning, which, for decades, has been primarily developed for data lying in Euclidean space. Yet, modern machine learning increasingly encounters richly structured data that is in
Externí odkaz:
http://arxiv.org/abs/2407.09468
An important problem in signal processing and deep learning is to achieve \textit{invariance} to nuisance factors not relevant for the task. Since many of these factors are describable as the action of a group $G$ (e.g. rotations, translations, scali
Externí odkaz:
http://arxiv.org/abs/2407.07655
In this work, we formally prove that, under certain conditions, if a neural network is invariant to a finite group then its weights recover the Fourier transform on that group. This provides a mathematical explanation for the emergence of Fourier fea
Externí odkaz:
http://arxiv.org/abs/2312.08550
Autor:
Xie, Jingxu, Zhang, Zuocheng, Zhang, Haodong, Nagarajan, Vikram, Zhao, Wenyu, Kim, Haleem, Sanborn, Collin, Qi, Ruishi, Chen, Sudi, Kahn, Salman, Watanabe, Kenji, Taniguchi, Takashi, Zettl, Alex, Crommie, Michael, Analytis, James, Wang, Feng
Advanced microelectronics in the future may require semiconducting channel materials beyond silicon. Two-dimensional (2D) semiconductors, characterized by their atomically thin thickness, hold immense promise for high-performance electronic devices a
Externí odkaz:
http://arxiv.org/abs/2312.04849
Autor:
Sanborn, Sophia, Miolane, Nina
Publikováno v:
Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
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. The approach leverages the theory of the triple-correlation on
Externí odkaz:
http://arxiv.org/abs/2310.18564
Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. However, many neurons exhibit $\textit{mixed selectivity}$, i.e., they represent multiple unrelated features. A recent hypot
Externí odkaz:
http://arxiv.org/abs/2310.11431
Autor:
Papillon, Mathilde, Hajij, Mustafa, Jenne, Helen, Mathe, Johan, Myers, Audun, Papamarkou, Theodore, Birdal, Tolga, Dey, Tamal, Doster, Tim, Emerson, Tegan, Gopalakrishnan, Gurusankar, Govil, Devendra, Guzmán-Sáenz, Aldo, Kvinge, Henry, Livesay, Neal, Mukherjee, Soham, Samaga, Shreyas N., Ramamurthy, Karthikeyan Natesan, Karri, Maneel Reddy, Rosen, Paul, Sanborn, Sophia, Walters, Robin, Agerberg, Jens, Barikbin, Sadrodin, Battiloro, Claudio, Bazhenov, Gleb, Bernardez, Guillermo, Brent, Aiden, Escalera, Sergio, Fiorellino, Simone, Gavrilev, Dmitrii, Hassanin, Mohammed, Häusner, Paul, Gardaa, Odin Hoff, Khamis, Abdelwahed, Lecha, Manuel, Magai, German, Malygina, Tatiana, Ballester, Rubén, Nadimpalli, Kalyan, Nikitin, Alexander, Rabinowitz, Abraham, Salatiello, Alessandro, Scardapane, Simone, Scofano, Luca, Singh, Suraj, Sjölund, Jens, Snopov, Pavel, Spinelli, Indro, Telyatnikov, Lev, Testa, Lucia, Yang, Maosheng, Yue, Yixiao, Zaghen, Olga, Zia, Ali, Miolane, Nina
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. The competition asked participants to provide open-source implementations of topo
Externí odkaz:
http://arxiv.org/abs/2309.15188
Autor:
Sanborn, Luke, Sahagun, Matthew
The financial industry poses great challenges with risk modeling and profit generation. These entities are intricately tied to the sophisticated prediction of stock movements. A stock forecaster must untangle the randomness and ever-changing behavior
Externí odkaz:
http://arxiv.org/abs/2309.06559
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. Topological Deep Le
Externí odkaz:
http://arxiv.org/abs/2304.10031
Obtaining in situ measurements of biological microparticles is crucial for both scientific research and numerous industrial applications (e.g., early detection of harmful algal blooms, monitoring yeast during fermentation). However, existing methods
Externí odkaz:
http://arxiv.org/abs/2301.09638