中文
相关论文

相关论文: Deep Neural Networks with Multi-Branch Architectur…

200 篇论文

We develop a convex analytic approach to analyze finite width two-layer ReLU networks. We first prove that an optimal solution to the regularized training problem can be characterized as extreme points of a convex set, where simple…

机器学习 · 计算机科学 2021-09-01 Tolga Ergen , Mert Pilanci

Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex. Diverse operations are connected by complicated connectivity patterns, e.g., various types of skip connections. Those…

机器学习 · 计算机科学 2022-10-13 Wuyang Chen , Wei Huang , Xinyu Gong , Boris Hanin , Zhangyang Wang

Deep neural networks (DNNs) exhibit a surprising structure in their final layer known as neural collapse (NC), and a growing body of works has currently investigated the propagation of neural collapse to earlier layers of DNNs -- a…

机器学习 · 计算机科学 2024-10-22 Peter Súkeník , Marco Mondelli , Christoph Lampert

Recently, several studies have proven the global convergence and generalization abilities of the gradient descent method for two-layer ReLU networks. Most studies especially focused on the regression problems with the squared loss function,…

机器学习 · 统计学 2020-03-19 Atsushi Nitanda , Geoffrey Chinot , Taiji Suzuki

Though learning has become a core component of modern information processing, there is now ample evidence that it can lead to biased, unsafe, and prejudiced systems. The need to impose requirements on learning is therefore paramount,…

机器学习 · 计算机科学 2022-10-20 Luiz F. O. Chamon , Santiago Paternain , Miguel Calvo-Fullana , Alejandro Ribeiro

The deployment of Deep Neural Networks (DNNs) on edge devices is hindered by the substantial gap between performance requirements and available processing power. While recent research has made significant strides in developing pruning…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Hamid Mousavi , Mohammad Loni , Mina Alibeigi , Masoud Daneshtalab

In this work, we build a generic architecture of Convolutional Neural Networks to discover empirical properties of neural networks. Our first contribution is to introduce a state-of-the-art framework that depends upon few hyper parameters…

计算机视觉与模式识别 · 计算机科学 2017-03-07 Edouard Oyallon

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…

机器学习 · 计算机科学 2026-01-21 Yahong Yang , Juncai He

Driver intention recognition studies increasingly rely on deep neural networks. Deep neural networks have achieved top performance for many different tasks, but it is not a common practice to explicitly analyse the complexity and…

机器学习 · 计算机科学 2024-11-22 Koen Vellenga , H. Joe Steinhauer , Alexander Karlsson , Göran Falkman , Asli Rhodin , Ashok Koppisetty

The growing capacity of neural networks has strongly contributed to their success at complex machine learning tasks and the computational demand of such large models has, in turn, stimulated a significant improvement in the hardware…

机器学习 · 计算机科学 2021-04-27 Mohammed Amer , Tomás Maul , Iman Yi Liao

A number of studies have shown that increasing the depth or width of convolutional networks is a rewarding approach to improve the performance of image recognition. In our study, however, we observed difficulties along both directions. On…

计算机视觉与模式识别 · 计算机科学 2017-07-18 Xingcheng Zhang , Zhizhong Li , Chen Change Loy , Dahua Lin

Although overparameterized models have achieved remarkable practical success, their theoretical properties, particularly their generalization behavior, remain incompletely understood. The well known double descents phenomenon suggests that…

机器学习 · 统计学 2026-01-06 Haoran Zhan , Yingcun Xia

We introduce a unified theoretical framework for the rigorous analysis and systematic construction of deep neural networks (DNNs). This framework addresses a gap in existing theory by explicitly modeling the structure of tensor operations…

Network design has been a central topic in machine learning. Large amounts of effort have been devoted towards creating efficient architectures through manual exploration as well as automated neural architecture search. However, todays…

计算机视觉与模式识别 · 计算机科学 2021-10-05 Albert Lee , Kang L. Wang

Many real world data analysis problems exhibit invariant structure, and models that take advantage of this structure have shown impressive empirical performance, particularly in deep learning. While the literature contains a variety of…

机器学习 · 计算机科学 2020-05-04 Clare Lyle , Mark van der Wilk , Marta Kwiatkowska , Yarin Gal , Benjamin Bloem-Reddy

In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contributing to the non-robustness of deep neural networks. We show…

机器学习 · 计算机科学 2025-03-04 Binghui Li , Zhixuan Pan , Kaifeng Lyu , Jian Li

Depth separation results propose a possible theoretical explanation for the benefits of deep neural networks over shallower architectures, establishing that the former possess superior approximation capabilities. However, there are no known…

机器学习 · 计算机科学 2023-02-03 Itay Safran , Jason D. Lee

State-of-the-art neural networks are getting deeper and wider. While their performance increases with the increasing number of layers and neurons, it is crucial to design an efficient deep architecture in order to reduce computational and…

神经与进化计算 · 计算机科学 2016-07-13 Hengyuan Hu , Rui Peng , Yu-Wing Tai , Chi-Keung Tang

While deep learning has outperformed other methods for various tasks, theoretical frameworks that explain its reason have not been fully established. To address this issue, we investigate the excess risk of two-layer ReLU neural networks in…

机器学习 · 统计学 2022-06-07 Shunta Akiyama , Taiji Suzuki

We introduce and analyze a new technique for model reduction for deep neural networks. While large networks are theoretically capable of learning arbitrarily complex models, overfitting and model redundancy negatively affects the prediction…

机器学习 · 计算机科学 2017-11-27 Alireza Aghasi , Afshin Abdi , Nam Nguyen , Justin Romberg