中文
相关论文

相关论文: On the Stability of Deep Networks

200 篇论文

The reliability of deep learning algorithms is fundamentally challenged by the existence of adversarial examples, which are incorrectly classified inputs that are extremely close to a correctly classified input. We explore the properties of…

机器学习 · 统计学 2021-07-23 Giacomo De Palma , Bobak T. Kiani , Seth Lloyd

We propose extrinsic and intrinsic deep neural network architectures as general frameworks for deep learning on manifolds. Specifically, extrinsic deep neural networks (eDNNs) preserve geometric features on manifolds by utilizing an…

机器学习 · 统计学 2023-02-20 Yihao Fang , Ilsang Ohn , Vijay Gupta , Lizhen Lin

Regression neural networks (NNs) are most commonly trained by minimizing the mean squared prediction error, which is highly sensitive to outliers and data contamination. Existing robust training methods for regression NNs are often limited…

机器学习 · 统计学 2026-02-10 Abhik Ghosh , Suryasis Jana

Deep neural networks (DNNs) have gained prominence in various applications, such as classification, recognition, and prediction, prompting increased scrutiny of their properties. A fundamental attribute of traditional DNNs is their…

机器学习 · 计算机科学 2023-08-15 Roman Garaev , Bader Rasheed , Adil Khan

Deep neural networks (DNN) have been used successfully in many scientific problems for their high prediction accuracy, but their application to genetic studies remains challenging due to their poor interpretability. In this paper, we…

机器学习 · 计算机科学 2021-10-01 Peyman H. Kassani , Fred Lu , Yann Le Guen , Zihuai He

Recently, methods have been developed to accurately predict the testing performance of a Deep Neural Network (DNN) on a particular task, given statistics of its underlying topological structure. However, further leveraging this newly found…

计算机视觉与模式识别 · 计算机科学 2021-12-01 Stuart Synakowski , Fabian Benitez-Quiroz , Aleix M. Martinez

Deep Neural Networks (DNNs) are a revolutionary force in the ongoing information revolution, and yet their intrinsic properties remain a mystery. In particular, it is widely known that DNNs are highly sensitive to noise, whether adversarial…

机器学习 · 计算机科学 2020-05-01 Netanel Raviv , Siddharth Jain , Pulakesh Upadhyaya , Jehoshua Bruck , Anxiao Jiang

Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem…

机器学习 · 计算机科学 2023-01-02 Clara Lucía Galimberti , Luca Furieri , Liang Xu , Giancarlo Ferrari-Trecate

Deep Neural Networks (DNN) have emerged as an effective approach to tackling real-world problems. However, like human-written software, DNNs are susceptible to bugs and attacks. This has generated significant interests in developing…

机器学习 · 计算机科学 2024-01-29 Hai Duong , Dong Xu , ThanhVu Nguyen , Matthew B. Dwyer

Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn…

计算机视觉与模式识别 · 计算机科学 2014-02-20 Christian Szegedy , Wojciech Zaremba , Ilya Sutskever , Joan Bruna , Dumitru Erhan , Ian Goodfellow , Rob Fergus

The distribution of the weights of modern deep neural networks (DNNs) - crucial for uncertainty quantification and robustness - is an eminently complex object due to its extremely high dimensionality. This paper proposes one of the first…

机器学习 · 统计学 2023-10-13 Olivier Laurent , Emanuel Aldea , Gianni Franchi

Learning accurate low-dimensional embeddings for a network is a crucial task as it facilitates many downstream network analytics tasks. For large networks, the trained embeddings often require a significant amount of space to store, making…

机器学习 · 计算机科学 2022-03-22 Tao He , Lianli Gao , Jingkuan Song , Yuan-Fang Li

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

Deep neural networks (DNNs) have become increasingly important due to their excellent empirical performance on a wide range of problems. However, regularization is generally achieved by indirect means, largely due to the complex set of…

机器学习 · 计算机科学 2018-07-02 Amal Rannen Triki , Maxim Berman , Matthew B. Blaschko

The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sparsifying DNNs before, during, and after training by pruning…

机器学习 · 计算机科学 2018-09-17 Ryan A. Robinett , Jeremy Kepner

Neural networks are nowadays highly successful despite strong hardness results. The existing hardness results focus on the network architecture, and assume that the network's weights are arbitrary. A natural approach to settle the…

机器学习 · 计算机科学 2020-10-15 Amit Daniely , Gal Vardi

Unsupervised dimensionality reduction is one of the commonly used techniques in the field of high dimensional data recognition problems. The deep autoencoder network which constrains the weights to be non-negative, can learn a low…

计算机视觉与模式识别 · 计算机科学 2020-09-18 Anyong Qin , Zhaowei Shang , Zhuolin Tan , Taiping Zhang , Yuan Yan Tang

Understanding the per-layer learning dynamics of deep neural networks is of significant interest as it may provide insights into how neural networks learn and the potential for better training regimens. We investigate learning in Deep…

机器学习 · 计算机科学 2020-12-02 Ayush Manish Agrawal , Atharva Tendle , Harshvardhan Sikka , Sahib Singh , Amr Kayid

This article gives a new proof that fully connected neural networks with random weights and biases converge to Gaussian processes in the regime where the input dimension, output dimension, and depth are kept fixed, while the hidden layer…

概率论 · 数学 2021-07-06 Boris Hanin

Deep neural networks (DNNs) have emerged as key enablers of machine learning. Applying larger DNNs to more diverse applications is an important challenge. The computations performed during DNN training and inference are dominated by…

机器学习 · 计算机科学 2018-12-17 Jeremy Kepner , Vijay Gadepally , Hayden Jananthan , Lauren Milechin , Sid Samsi