中文
相关论文

相关论文: Learning Curves for Deep Neural Networks: A Gaussi…

200 篇论文

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

机器学习 · 计算机科学 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

Deep learning has received considerable empirical successes in recent years. However, while many ad hoc tricks have been discovered by practitioners, until recently, there has been a lack of theoretical understanding for tricks invented in…

机器学习 · 计算机科学 2020-12-29 Cong Fang , Hanze Dong , Tong Zhang

Deep neural networks (DNNs) in the infinite width/channel limit have received much attention recently, as they provide a clear analytical window to deep learning via mappings to Gaussian Processes (GPs). Despite its theoretical appeal, this…

机器学习 · 计算机科学 2021-06-09 Gadi Naveh , Zohar Ringel

Background: It is still an open research area to theoretically understand why Deep Neural Networks (DNNs)---equipped with many more parameters than training data and trained by (stochastic) gradient-based methods---often achieve remarkably…

机器学习 · 计算机科学 2018-11-30 Zhiqin John Xu

Deep Neural Networks (DNNs) are widely used for their ability to effectively approximate large classes of functions. This flexibility, however, makes the strict enforcement of constraints on DNNs an open problem. Here we present a framework…

机器学习 · 计算机科学 2023-02-10 Eric Marcus , Ray Sheombarsing , Jan-Jakob Sonke , Jonas Teuwen

Deep neural networks (DNN) are the state of the art on many engineering problems such as computer vision and audition. A key factor in the success of the DNN is scalability - bigger networks work better. However, the reason for this…

机器学习 · 计算机科学 2015-02-13 Andrew J. R. Simpson

This paper proposes a new mean-field framework for over-parameterized deep neural networks (DNNs), which can be used to analyze neural network training. In this framework, a DNN is represented by probability measures and functions over its…

机器学习 · 统计学 2020-07-06 Cong Fang , Jason D. Lee , Pengkun Yang , Tong Zhang

Analysis of over-parameterized neural networks has drawn significant attention in recentyears. It was shown that such systems behave like convex systems under various restrictedsettings, such as for two-level neural networks, and when…

机器学习 · 计算机科学 2019-11-19 Cong Fang , Yihong Gu , Weizhong Zhang , Tong Zhang

Deep learning has been the engine powering many successes of data science. However, the deep neural network (DNN), as the basic model of deep learning, is often excessively over-parameterized, causing many difficulties in training,…

机器学习 · 统计学 2021-03-09 Yan Sun , Qifan Song , Faming Liang

A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considerable advances have been made in formalizing what functions…

机器学习 · 计算机科学 2024-06-19 Chenxiao Yang , Qitian Wu , David Wipf , Ruoyu Sun , Junchi Yan

In this work, we describe a new approach that uses deep neural networks (DNN) to obtain regularization parameters for solving inverse problems. We consider a supervised learning approach, where a network is trained to approximate the…

数值分析 · 数学 2021-04-15 Babak Maboudi Afkham , Julianne Chung , Matthias Chung

Developing Intelligent Systems involves artificial intelligence approaches including artificial neural networks. Here, we present a tutorial of Deep Neural Networks (DNNs), and some insights about the origin of the term "deep"; references…

神经与进化计算 · 计算机科学 2016-03-24 Juan C. Cuevas-Tello , Manuel Valenzuela-Rendon , Juan A. Nolazco-Flores

In recent years, deep neural networks (DNNs) have known an important rise in popularity. However, although they are state-of-the-art in many machine learning challenges, they still suffer from several limitations. For example, DNNs require…

Deep learning achieves remarkable generalization capability with overwhelming number of model parameters. Theoretical understanding of deep learning generalization receives recent attention yet remains not fully explored. This paper…

机器学习 · 计算机科学 2017-11-22 Guanhua Zheng , Jitao Sang , Changsheng Xu

Overparametrized Deep Neural Networks (DNNs) have demonstrated remarkable success in a wide variety of domains too high-dimensional for classical shallow networks subject to the curse of dimensionality. However, open questions about…

机器学习 · 计算机科学 2025-07-04 David A. Danhofer , Davide D'Ascenzo , Rafael Dubach , Tomaso Poggio

Deep Neural Networks (DNNs) have become very popular for prediction in many areas. Their strength is in representation with a high number of parameters that are commonly learned via gradient descent or similar optimization methods. However,…

机器学习 · 统计学 2016-10-11 Anthony Caterini , Dong Eui Chang

Deep neural networks (DNNs) play a crucial role in the field of machine learning, demonstrating state-of-the-art performance across various application domains. However, despite their success, DNN-based models may occasionally exhibit…

机器学习 · 计算机科学 2024-07-02 Guy Amir , Osher Maayan , Tom Zelazny , Guy Katz , Michael Schapira

Deep learning has arguably achieved tremendous success in recent years. In simple words, deep learning uses the composition of many nonlinear functions to model the complex dependency between input features and labels. While neural networks…

机器学习 · 统计学 2019-04-16 Jianqing Fan , Cong Ma , Yiqiao Zhong

Deep neural networks (DNNs) generalize remarkably well without explicit regularization even in the strongly over-parametrized regime where classical learning theory would instead predict that they would severely overfit. While many…

机器学习 · 统计学 2019-04-23 Guillermo Valle-Pérez , Chico Q. Camargo , Ard A. Louis

Deep Neural Networks (DNNs) excel at many tasks, often rivaling or surpassing human performance. Yet their internal processes remain elusive, frequently described as "black boxes." While performance can be refined experimentally, achieving…

无序系统与神经网络 · 物理学 2025-02-03 Sebastiano Ariosto
‹ 上一页 1 2 3 10 下一页 ›