Zobrazeno 1 - 10
of 109
pro vyhledávání: '"HE Juncai"'
Publikováno v:
陆军军医大学学报, Vol 46, Iss 17, Pp 1934-1942 (2024)
Objective To explore the relationship between phenotypic changes of retinal microglia and retinal ganglion cells (RGCs) death after optic nerve injury. Methods Male C57BL/6J mice (6 to 8 weeks old) were randomly divided into 1-, 3-, 7-, and 14-day in
Externí odkaz:
https://doaj.org/article/1d0d1bce79064fd9920b8d696534d84f
This paper investigates the impact of multiscale data on machine learning algorithms, particularly in the context of deep learning. A dataset is multiscale if its distribution shows large variations in scale across different directions. This paper re
Externí odkaz:
http://arxiv.org/abs/2402.03021
Autor:
Yang, Yahong, He, Juncai
Constructing the architecture of a neural network is a challenging pursuit for the machine learning community, and the dilemma of whether to go deeper or wider remains a persistent question. This paper explores a comparison between deeper neural netw
Externí odkaz:
http://arxiv.org/abs/2402.00152
In this paper, we investigate the expressivity and approximation properties of deep neural networks employing the ReLU$^k$ activation function for $k \geq 2$. Although deep ReLU networks can approximate polynomials effectively, deep ReLU$^k$ networks
Externí odkaz:
http://arxiv.org/abs/2312.16483
Autor:
He, Juncai, Xu, Jinchao
In this study, we establish that deep neural networks employing ReLU and ReLU$^2$ activation functions can effectively represent Lagrange finite element functions of any order on various simplicial meshes in arbitrary dimensions. We introduce two nov
Externí odkaz:
http://arxiv.org/abs/2312.14276
In this work, we propose a concise neural operator architecture for operator learning. Drawing an analogy with a conventional fully connected neural network, we define the neural operator as follows: the output of the $i$-th neuron in a nonlinear ope
Externí odkaz:
http://arxiv.org/abs/2310.19809
Autor:
Huang, Huang, Yu, Fei, Zhu, Jianqing, Sun, Xuening, Cheng, Hao, Song, Dingjie, Chen, Zhihong, Alharthi, Abdulmohsen, An, Bang, He, Juncai, Liu, Ziche, Zhang, Zhiyi, Chen, Junying, Li, Jianquan, Wang, Benyou, Zhang, Lian, Sun, Ruoyu, Wan, Xiang, Li, Haizhou, Xu, Jinchao
This paper is devoted to the development of a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models. Significant concerns emerge when a
Externí odkaz:
http://arxiv.org/abs/2309.12053
Autor:
He, Juncai
This paper is devoted to studying the optimal expressive power of ReLU deep neural networks (DNNs) and its application in approximation via the Kolmogorov Superposition Theorem. We first constructively prove that any continuous piecewise linear funct
Externí odkaz:
http://arxiv.org/abs/2308.05509
In this paper, we study linear regression applied to data structured on a manifold. We assume that the data manifold is smooth and is embedded in a Euclidean space, and our objective is to reveal the impact of the data manifold's extrinsic geometry o
Externí odkaz:
http://arxiv.org/abs/2307.02478
By investigating iterative methods for a constrained linear model, we propose a new class of fully connected V-cycle MgNet for long-term time series forecasting, which is one of the most difficult tasks in forecasting. MgNet is a CNN model that was p
Externí odkaz:
http://arxiv.org/abs/2302.00962