activity
20142025
most citedMachine Learning for Neuroimaging with Scikit-Learn

172 citations · 195 across the 13 of their papers we have counts for

collaborators
Showing 2023Show all

7 papers · 1 filter

astro-ph.CO20231 cited

SimBIG: Field-level Simulation-Based Inference of Galaxy Clustering

Pablo Lemos, Liam Parker, ChangHoon Hahn +8

We present the first simulation-based inference (SBI) of cosmological parameters from field-level analysis of galaxy clustering. Standard galaxy clustering analyses rely on analyzi…

astro-ph.CO20236 cited

: The First Cosmological Constraints from Non-Gaussian and Non-Linear Galaxy Clustering

ChangHoon Hahn, Pablo Lemos, Liam Parker +8

The 3D distribution of galaxies encodes detailed cosmological information on the expansion and growth history of the Universe. We present the first cosmological constraints that ex…

astro-ph.CO20231 cited

: The First Cosmological Constraints from the Non-Linear Galaxy Bispectrum

ChangHoon Hahn, Michael Eickenberg, Shirley Ho +7

We present the first cosmological constraints from analyzing higher-order galaxy clustering on non-linear scales. We use , a forward modeling framework…

astro-ph.IM20231 cited

Learnable wavelet neural networks for cosmological inference

Christian Pedersen, Michael Eickenberg, Shirley Ho

Convolutional neural networks (CNNs) have been shown to both extract more information than the traditional two-point statistics from cosmological fields, and marginalise over astro…

cs.LG2023

Adversarial Attacks on the Interpretation of Neuron Activation Maximization

Geraldin Nanfack, Alexander Fulleringer, Jonathan Marty +2

The internal functional behavior of trained Deep Neural Networks is notoriously difficult to interpret. Activation-maximization approaches are one set of techniques used to interpr…

cs.LG20232 cited

Can Forward Gradient Match Backpropagation?

Louis Fournier, Stéphane Rivaud, Eugene Belilovsky +2

Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding…