Zobrazeno 1 - 10
of 7 848
pro vyhledávání: '"FENG Han"'
Graph convolutional networks (GCNs) have emerged as powerful models for graph learning tasks, exhibiting promising performance in various domains. While their empirical success is evident, there is a growing need to understand their essential ability
Externí odkaz:
http://arxiv.org/abs/2410.08473
In recent years, there has been growing interest in the field of functional neural networks. They have been proposed and studied with the aim of approximating continuous functionals defined on sets of functions on Euclidean domains. In this paper, we
Externí odkaz:
http://arxiv.org/abs/2410.01047
In this note, we comprehensively characterize the proximal operator of the $\ell_{1,q}$-norm with $0\!<\!q\!<\!1$ by exploiting the well-known proximal operator of the $\ell_q$-norm on the real line. In particular, much more explicit characterization
Externí odkaz:
http://arxiv.org/abs/2409.14156
In this work, we explore intersections between sparse coding and deep learning to enhance our understanding of feature extraction capabilities in advanced neural network architectures. We begin by introducing a novel class of Deep Sparse Coding (DSC)
Externí odkaz:
http://arxiv.org/abs/2408.05540
In this paper, we focus on analyzing the excess risk of the unpaired data generation model, called CycleGAN. Unlike classical GANs, CycleGAN not only transforms data between two unpaired distributions but also ensures the mappings are consistent, whi
Externí odkaz:
http://arxiv.org/abs/2407.11678
In this paper, we explore the approximation theory of functions defined on graphs. Our study builds upon the approximation results derived from the $K$-functional. We establish a theoretical framework to assess the lower bounds of approximation for t
Externí odkaz:
http://arxiv.org/abs/2407.01281
Estimating 3D full-body avatars from AR/VR devices is essential for creating immersive experiences in AR/VR applications. This task is challenging due to the limited input from Head Mounted Devices, which capture only sparse observations from the hea
Externí odkaz:
http://arxiv.org/abs/2405.20786
We study approximation and learning capacities of convolutional neural networks (CNNs) with one-side zero-padding and multiple channels. Our first result proves a new approximation bound for CNNs with certain constraint on the weights. Our second res
Externí odkaz:
http://arxiv.org/abs/2403.16459
Autor:
Shuangshuang Dong, Bo Shen, Xu Jiang, Jun Zhu, Haiying Zhang, Yang Zhao, Yaning Chen, Dongfeng Li, Yuanyuan Feng, Yi Chen, Yang Pan, Feng Han, Ben Liu, Li Zhang
Publikováno v:
npj Parkinson's Disease, Vol 10, Iss 1, Pp 1-9 (2024)
Abstract The vagus nerve (VN) is the main neural pathway linking the gut and brain in Parkinson’s disease (PD). In this study, we utilized high-resolution ultrasound to measure the VN cross-sectional area (CSA) in 96 healthy controls (HCs) and 75 P
Externí odkaz:
https://doaj.org/article/c2ffae62a28a42b683a23a77b863d6bf
Publikováno v:
MycoKeys, Vol 110, Iss , Pp 141-158 (2024)
Two new Cordyceps-like species, Perennicordyceps zongqii and Purpureocillium zongqii, isolated from a larva and soil, are introduced. Morphological comparisons and phylogenetic analyses based on multigene datasets (ITS, LSU, RPB2 and TEF) support the
Externí odkaz:
https://doaj.org/article/153b97bb09024162bdf0eede48ff5911