15 citations · 36 across the 11 of their papers we have counts for
6 papers · 1 filter
Harmonics of Learning: Universal Fourier Features Emerge in Invariant Networks
Giovanni Luca Marchetti, Christopher Hillar, Danica Kragic +1
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. Thi…
Identifying Interpretable Visual Features in Artificial and Biological Neural Systems
David Klindt, Sophia Sanborn, Francisco Acosta +2
Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. However, many neurons exhibit $\textit{mixed selectivi…
A General Framework for Robust G-Invariance in G-Equivariant Networks
Sophia Sanborn, Nina Miolane
We introduce a general method for achieving robust group-invariance in group-equivariant convolutional neural networks (-CNNs), which we call the -triple-correlation (-TC)…
ICML 2023 Topological Deep Learning Challenge : Design and Results
Mathilde Papillon, Mustafa Hajij, Helen Jenne +53
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 competi…
Architectures of Topological Deep Learning: A Survey of Message-Passing Topological Neural Networks
Mathilde Papillon, Sophia Sanborn, Mustafa Hajij +1
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 elec…
Equivariant Representation Learning in the Presence of Stabilizers
Luis Armando Pérez Rey, Giovanni Luca Marchetti, Danica Kragic +2
We introduce Equivariant Isomorphic Networks (EquIN) -- a method for learning representations that are equivariant with respect to general group actions over data. Differently from…