An Ensemble of Degraded Neural Networks

机译：退化神经网络的集合

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

In this paper we present a new method to create neural network ensembles. In an ensemble method like bagging one needs to train multiple neural networks to create the ensemble. Here we present a scheme to generate different copies of a network from one trained network, and use those copies to create the ensemble. The copies are produced by adding controlled noise to a trained base network. We provide a preliminary theoretical justification for our method and experimentally validate the method on several standard data sets. Our method can improve the accuracy of a base network and give rise to considerable savings in training time compared to bagging.

机译：在本文中，我们提出了一种创建神经网络集成的新方法。在像装袋这样的合奏方法中，需要训练多个神经网络来创建合奏。在这里，我们提出了一种从一个训练有素的网络生成网络的不同副本的方案，并使用这些副本来创建集合。通过向受控的基础网络中添加受控噪声来生成副本。我们为我们的方法提供了初步的理论依据，并在几个标准数据集上通过实验验证了该方法。与装袋相比，我们的方法可以提高基本网络的准确性，并节省大量的培训时间。

著录项

来源
《Pattern recognition》|2011年|p.278-287|共10页
会议地点 Cancun(MX);Cancun(MX)
作者
Eduardo Vazquez-Santacruz; Debrup Cliakraborty;
展开▼
作者单位

Department of Electrical Engineering and Computer Science, CINVESTAV-IPN, Unidad Guadalajara, Av. Cientifica 1145, Colonia El Bajio, Zapopan, Jalisco 45015, Mexico,Department of Computer Science, CINVESTAV-IPN, Av. IPN 2508, Col: San Pedro Zacatenco, Mexico City 07360, Mexico;

Department of Electrical Engineering and Computer Science, CINVESTAV-IPN, Unidad Guadalajara, Av. Cientifica 1145, Colonia El Bajio, Zapopan, Jalisco 45015, Mexico,Department of Computer Science, CINVESTAV-IPN, Av. IPN 2508, Col: San Pedro Zacatenco, Mexico City 07360, Mexico;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类模式识别与装置;
关键词

相似文献

外文文献
中文文献
专利

1. Comparing the Fault Diagnosis Performances of Single Neural Networks and Two Ensemble Neural Networks Based on the Boosting Methods [J] . Pooria Karimi, Hooshang Jazayeri-Rad Journal of Automation and Control . 2014,第1期

机译：基于Boosting方法的单神经网络和两个集成神经网络故障诊断性能比较
2. Fractal Neural Network: A new ensemble of fractal geometry and convolutional neural networks for the classification of histology images [J] . Roberto Guilherme Freire, Lumini Alessandra, Neves Leandro Alves, Expert systems with applications . 2021,第Mara期

机译：分形神经网络：组织学图像分类的分形几何和卷积神经网络的新集合
3. Comparison of single best artificial neural network and neural network ensemble in modeling of palladium microextraction [J] . Dehghanian Effat, Kaykhaii Massoud, Mehrpur Maryam Monatshefte fur Chemie . 2015,第8期

机译：单个最佳人工神经网络和神经网络集成在钯微萃取建模中的比较
4. Neural Networks Ensembles Approach for Simulation of Solar Arrays Degradation Process [C] . Vladimir Bukhtoyarov, Eugene Semenkin, Andrey Shabalov International conference on hybrid artificial intelligent systems;HAIS 2012;Session on systems, man, and cybernetics by HAIS;Session on methods of classifier fusion;Session on HAIS for computer security;Session on data mining: data preparation and analysis;Session on hybrid artificial intelligence systems in management of production systems;Session on hybrid artificial intelligent systems for ordinal regression;Session on hybrid computational intelligence and lattice computing for image and signal processing;Session on hybrid metaheuristics for combinatorial optimization and modelling complex systems;Workshop on nonstationary models of pattern recognition and classifier combinations . 2012

机译：神经网络集成方法模拟太阳电池阵列降解过程
5. Neural Rule Ensembles: Encoding Feature Interactions Into Neural Networks [D] . Dawer, Gitesh. 2018

机译：神经规则集成：将特征交互编码到神经网络中
6. Bearing Fault Diagnosis with a Feature Fusion Method Based on an Ensemble Convolutional Neural Network and Deep Neural Network [O] . Hongmei Li, Jinying Huang, Shuwei Ji 2019

机译：基于集成卷积神经网络和深度神经网络的特征融合方法进行轴承故障诊断
7. An Ensemble of Degraded Neural Networks [O] . Eduardo Vázquez-Santacruz, Debrup Chakraborty 2011

机译：劣化神经网络的集合
8. When Networks Disagree: Ensemble Methods for Hybrid Neural Networks. [R] . Perrone, M. P., Cooper, L. N. 1993

机译：当网络不同意：混合神经网络的集合方法。

An Ensemble of Degraded Neural Networks

摘要

著录项

相似文献

相关主题

期刊订阅