How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model

5 July 2023

Papers citing "How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model"

10 / 10 papers shown

Title
A distributional simplicity bias in the learning dynamics of transformers Riccardo Rende Federica Gerace A. Laio Sebastian Goldt 68 8 0 17 Feb 2025
Analyzing (In)Abilities of SAEs via Formal Languages Abhinav Menon Manish Shrivastava David M. Krueger Ekdeep Singh Lubana 35 7 0 15 Oct 2024
How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning Arthur Jacot Seok Hoan Choi Yuxiao Wen AI4CE 81 2 0 08 Jul 2024
U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models Song Mei 3DV AI4CE DiffM 31 11 0 29 Apr 2024
How deep convolutional neural networks lose spatial information with training Umberto M. Tomasini Leonardo Petrini Francesco Cagnetta M. Wyart 27 9 0 04 Oct 2022
Data-driven emergence of convolutional structure in neural networks Alessandro Ingrosso Sebastian Goldt 48 38 0 01 Feb 2022
Sifting out the features by pruning: Are convolutional networks the winning lottery ticket of fully connected ones? Franco Pellegrini Giulio Biroli 44 6 0 27 Apr 2021
The Intrinsic Dimension of Images and Its Impact on Learning Phillip E. Pope Chen Zhu Ahmed Abdelkader Micah Goldblum Tom Goldstein 183 256 0 18 Apr 2021
Towards Learning Convolutions from Scratch Behnam Neyshabur SSL 214 70 0 27 Jul 2020
Geometric compression of invariant manifolds in neural nets J. Paccolat Leonardo Petrini Mario Geiger Kevin Tyloo M. Wyart MLT 42 34 0 22 Jul 2020