English
Related papers

Related papers: A Kernel Perspective of Skip Connections in Convol…

200 papers

We present hyper-connections, a simple yet effective method that can serve as an alternative to residual connections. This approach specifically addresses common drawbacks observed in residual connection variants, such as the seesaw effect…

Machine Learning · Computer Science 2025-03-19 Defa Zhu , Hongzhi Huang , Zihao Huang , Yutao Zeng , Yunyao Mao , Banggu Wu , Qiyang Min , Xun Zhou

In this paper, we develop a concise but efficient network architecture called linear compressing based skip-connecting network (LCSCNet) for image super-resolution. Compared with two representative network architectures with skip…

Image and Video Processing · Electrical Eng. & Systems 2020-01-08 Wenming Yang , Xuechen Zhang , Yapeng Tian , Wei Wang , Jing-Hao Xue , Qingmin Liao

Residual networks (ResNets) have displayed impressive results in pattern recognition and, recently, have garnered considerable theoretical interest due to a perceived link with neural ordinary differential equations (neural ODEs). This link…

Machine Learning · Computer Science 2021-06-11 Alain-Sam Cohen , Rama Cont , Alain Rossier , Renyuan Xu

We study scaling convolutional neural networks (CNNs), specifically targeting Residual neural networks (ResNet), for analyzing electrocardiograms (ECGs). Although ECG signals are time-series data, CNN-based models have been shown to…

Machine Learning · Computer Science 2025-05-01 Byeong Tak Lee , Yong-Yeon Jo , Joon-Myoung Kwon

We analyze the generalization properties of two-layer neural networks in the neural tangent kernel (NTK) regime, trained with gradient descent (GD). For early stopped GD we derive fast rates of convergence that are known to be minimax…

Machine Learning · Statistics 2023-09-18 Mike Nguyen , Nicole Mücke

An interesting observation in artificial neural networks is their favorable generalization error despite typically being extremely overparameterized. It is well known that the classical statistical learning methods often result in vacuous…

Machine Learning · Computer Science 2021-10-12 Sattar Vakili , Michael Bromberg , Jezabel Garcia , Da-shan Shiu , Alberto Bernacchia

We empirically evaluate common assumptions about neural networks that are widely held by practitioners and theorists alike. In this work, we: (1) prove the widespread existence of suboptimal local minima in the loss landscape of neural…

Machine Learning · Computer Science 2020-04-29 Micah Goldblum , Jonas Geiping , Avi Schwarzschild , Michael Moeller , Tom Goldstein

In this paper, we present a novel framework for enhancing the performance of Quanvolutional Neural Networks (QuNNs) by introducing trainable quanvolutional layers and addressing the critical challenges associated with them. Traditional…

Machine Learning · Computer Science 2025-07-18 Muhammad Kashif , Muhammad Shafique

Recent theoretical work has shown that massively overparameterized neural networks are equivalent to kernel regressors that use Neural Tangent Kernels(NTK). Experiments show that these kernel methods perform similarly to real neural…

Machine Learning · Computer Science 2020-11-17 Amnon Geifman , Abhay Yadav , Yoni Kasten , Meirav Galun , David Jacobs , Ronen Basri

The mining and utilization of features directly affect the classification performance of models used in the classification and recognition of hyperspectral remote sensing images. Traditional models usually conduct feature mining from a…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Yunsong Zhao , Yin Li , Zhihan Chen , Tianchong Qiu , Guojin Liu

Transformer models have emerged as fundamental tools across various scientific and engineering disciplines, owing to their outstanding performance in diverse applications. Despite this empirical success, the theoretical foundations of…

Machine Learning · Computer Science 2026-04-14 Zhen Qin , Jinxin Zhou , Jiachen Jiang , Zhihui Zhu

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…

Machine Learning · Computer Science 2019-06-12 Difan Zou , Quanquan Gu

Recent research shows that for training with $\ell_2$ loss, convolutional neural networks (CNNs) whose width (number of channels in convolutional layers) goes to infinity correspond to regression with respect to the CNN Gaussian Process…

Machine Learning · Computer Science 2019-11-05 Zhiyuan Li , Ruosong Wang , Dingli Yu , Simon S. Du , Wei Hu , Ruslan Salakhutdinov , Sanjeev Arora

In this paper we propose a novel 3D CNN network with localized residual connections for hyperspectral image classification. Our work chalks a comparative study with the existing methods employed for abstracting deeper features and propose a…

Computer Vision and Pattern Recognition · Computer Science 2019-12-09 Shivangi Dwivedi , Murari Mandal , Shekhar Yadav , Santosh Kumar Vipparthi

Graph convolutional networks are a popular class of deep neural network algorithms which have shown success in a number of relational learning tasks. Despite their success, graph convolutional networks exhibit a number of peculiar features,…

Machine Learning · Computer Science 2022-08-22 Thomas Gebhart

We prove rates of convergence in the statistical sense for kernel-based least squares regression using a conjugate gradient algorithm, where regularization against overfitting is obtained by early stopping. This method is directly related…

Statistics Theory · Mathematics 2010-09-30 Gilles Blanchard , Nicole Kraemer

We show that Residual Networks (ResNet) is equivalent to boosting feature representation, without any modification to the underlying ResNet training algorithm. A regret bound based on Online Gradient Boosting theory is proved and suggests…

Machine Learning · Statistics 2019-09-27 Chapman Siu

Recently, Convolutional Neural Networks (CNNs) have shown promising performance in super-resolution (SR). However, these methods operate primarily on Low Resolution (LR) inputs for memory efficiency but this limits, as we demonstrate, their…

Computer Vision and Pattern Recognition · Computer Science 2019-05-17 Muneeb Aadil , Rafia Rahim , Sibt ul Hussain

Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors. In this paper, we analyze the propagation formulations behind the residual building blocks, which…

Computer Vision and Pattern Recognition · Computer Science 2016-07-26 Kaiming He , Xiangyu Zhang , Shaoqing Ren , Jian Sun

This paper proposes a novel method for deep learning based on the analytical convolution of multidimensional Gaussian mixtures. In contrast to tensors, these do not suffer from the curse of dimensionality and allow for a compact…

Machine Learning · Computer Science 2022-02-21 Adam Celarek , Pedro Hermosilla , Bernhard Kerbl , Timo Ropinski , Michael Wimmer
‹ Prev 1 8 9 10 Next ›