中文
相关论文

相关论文: Stochastic Training of Residual Networks: a Differ…

200 篇论文

Dropout is a regularization technique widely used in training artificial neural networks to mitigate overfitting. It consists of dynamically deactivating subsets of the network during training to promote more robust representations. Despite…

机器学习 · 统计学 2025-09-10 Francesco Mori , Francesca Mignacco

Regularization plays a major role in modern deep learning. From classic techniques such as L1,L2 penalties to other noise-based methods such as Dropout, regularization often yields better generalization properties by avoiding overfitting.…

机器学习 · 统计学 2021-06-08 Soufiane Hayou , Fadhel Ayed

Stochastic regularization of neural networks (e.g. dropout) is a wide-spread technique in deep learning that allows for better generalization. Despite its success, continuous-time models, such as neural ordinary differential equation (ODE),…

机器学习 · 计算机科学 2020-06-29 Viktor Oganesyan , Alexandra Volokhova , Dmitry Vetrov

Dropout is a widely utilized regularization technique in the training of neural networks, nevertheless, its underlying mechanism and its impact on achieving good generalization abilities remain poorly understood. In this work, we derive the…

机器学习 · 计算机科学 2023-05-26 Zhongwang Zhang , Yuqing Li , Tao Luo , Zhi-Qin John Xu

Dropout is a very effective way of regularizing neural networks. Stochastically "dropping out" units with a certain probability discourages over-specific co-adaptations of feature detectors, preventing overfitting and improving network…

神经与进化计算 · 计算机科学 2017-08-04 Pietro Morerio , Jacopo Cavazza , Riccardo Volpi , Rene Vidal , Vittorio Murino

Deep neural networks have had an enormous impact on image analysis. State-of-the-art training methods, based on weight decay and DropOut, result in impressive performance when a very large training set is available. However, they tend to…

机器学习 · 计算机科学 2019-09-02 Amal Rannen Triki , Matthew B. Blaschko

Dropout and similar stochastic neural network regularization methods are often interpreted as implicitly averaging over a large ensemble of models. We propose STE (stochastically trained ensemble) layers, which enhance the averaging…

机器学习 · 计算机科学 2019-11-22 Alex Labach , Shahrokh Valaee

Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and then prunes away…

We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of…

机器学习 · 计算机科学 2021-06-22 Benedict Leimkuhler , Tiffany Vlaar , Timothée Pouchon , Amos Storkey

Incorporating stochasticity into the training process of deep convolutional networks is a widely used technique to reduce overfitting and improve regularization. Existing techniques often require modifying the architecture of the network by…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Evgeny Hershkovitch Neiterman , Gil Ben-Artzi

Today artificial neural networks are applied in various fields - engineering, data analysis, robotics. While they represent a successful tool for a variety of relevant applications, mathematically speaking they are still far from being…

神经与进化计算 · 计算机科学 2015-11-30 K. G. Kapanova , I. Dimov , J. M. Sellier

Areas of computational mechanics such as uncertainty quantification and optimization usually involve repeated evaluation of numerical models that represent the behavior of engineering systems. In the case of complex nonlinear systems…

机器学习 · 计算机科学 2024-10-03 A. O. M. Kilicsoy , J. Liedmann , M. A. Valdebenito , F. -J. Barthold , M. G. R. Faes

Dropout is a widely-used regularization technique, often required to obtain state-of-the-art for a number of architectures. This work demonstrates that dropout introduces two distinct but entangled regularization effects: an explicit effect…

机器学习 · 计算机科学 2020-10-16 Colin Wei , Sham Kakade , Tengyu Ma

This work theoretically studies stochastic neural networks, a main type of neural network in use. We prove that as the width of an optimized stochastic neural network tends to infinity, its predictive variance on the training set decreases…

机器学习 · 计算机科学 2022-05-25 Liu Ziyin , Hanlin Zhang , Xiangming Meng , Yuting Lu , Eric Xing , Masahito Ueda

Neural networks are often over-parameterized and hence benefit from aggressive regularization. Conventional regularization methods, such as Dropout or weight decay, do not leverage the structures of the network's inputs and hidden states.…

机器学习 · 计算机科学 2021-01-07 Hieu Pham , Quoc V. Le

We introduce a novel stochastic regularization technique for deep neural networks, which decomposes a layer into multiple branches with different parameters and merges stochastically sampled combinations of the outputs from the branches…

机器学习 · 计算机科学 2019-10-04 Wonpyo Park , Paul Hongsuck Seo , Bohyung Han , Minsu Cho

Deep neural networks possess strong representational capacity yet remain vulnerable to overfitting, primarily because neurons tend to co-adapt in ways that, while capturing complex and fine-grained feature interactions, also reinforce…

机器学习 · 计算机科学 2025-12-16 Gelesh G Omathil , Sreeja CS

Dropout is a widely used regularization technique which improves the generalization ability of a model by randomly dropping neurons. In light of this, we propose Dropout Prompt Learning, which aims for applying dropout to improve the…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Biao Chen , Lin Zuo , Mengmeng Jing , Kunbin He , Yuchen Wang

Recently, the training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has been proved to improve generalization performance of neural networks. In contrast to the individually…

机器学习 · 计算机科学 2017-09-19 Sungrae Park , Jun-Keon Park , Su-Jin Shin , Il-Chul Moon

Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs). Dropout techniques for RNNs were introduced to respond to these demands, but we…

机器学习 · 计算机科学 2019-04-23 Sungrae Park , Kyungwoo Song , Mingi Ji , Wonsung Lee , Il-Chul Moon
‹ 上一页 1 2 3 10 下一页 ›