Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?

16 October 2020

Papers citing "Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?"

9 / 9 papers shown

Title
Towards Exact Computation of Inductive Bias Akhilan Boopathy William Yue Jaedong Hwang Abhiram Iyer Ila Fiete 44 0 0 22 Jun 2024
U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models Song Mei 3DV AI4CE DiffM 45 11 0 29 Apr 2024
Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning Yuxiao Wen Arthur Jacot 65 6 0 12 Feb 2024
Theoretical Analysis of Inductive Biases in Deep Convolutional Networks Zihao Wang Lei Wu 28 20 0 15 May 2023
Model-agnostic Measure of Generalization Difficulty Akhilan Boopathy Kevin Liu Jaedong Hwang Shu Ge Asaad Mohammedsaleh Ila Fiete 80 4 0 01 May 2023
Convolutional Visual Prompt for Robust Visual Perception Yun-Yun Tsai Chengzhi Mao Junfeng Yang VLM VPVLM 36 13 0 01 Mar 2023
Theory for Equivariant Quantum Neural Networks Quynh T. Nguyen Louis Schatzki Paolo Braccia Michael Ragone Patrick J. Coles F. Sauvage Martín Larocca M. Cerezo 45 89 0 16 Oct 2022
Learning with convolution and pooling operations in kernel methods Theodor Misiakiewicz Song Mei MLT 15 29 0 16 Nov 2021
Learning with invariances in random features and kernel models Song Mei Theodor Misiakiewicz Andrea Montanari OOD 55 89 0 25 Feb 2021