Regularizing Deep Neural Networks by Enhancing Diversity in Feature Extraction

Babajide O. Ayinde; Tamer Inanc; Jacek M. Zurada

首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Regularizing Deep Neural Networks by Enhancing Diversity in Feature Extraction

【24h】

Regularizing Deep Neural Networks by Enhancing Diversity in Feature Extraction

机译：通过增强特征提取中的多样性来规范化深度神经网络

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

This paper proposes a new and efficient technique to regularize the neural network in the context of deep learning using correlations among features. Previous studies have shown that oversized deep neural network models tend to produce a lot of redundant

机译：本文提出了一种新的高效技术，可以利用特征之间的相关性在深度学习的背景下对神经网络进行正则化。先前的研究表明，过大的深度神经网络模型往往会产生大量冗余

著录项

来源
《Neural Networks and Learning Systems, IEEE Transactions on》 |2019年第9期|2650-2661|共12页
作者
Babajide O. Ayinde; Tamer Inanc; Jacek M. Zurada;
展开▼
作者单位

Department of Electrical and Computer Engineering University of Louisville Louisville KY USA;

Department of Electrical and Computer Engineering University;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Feature extraction; Training; Neural networks; Correlation; Redundancy; Decorrelation; Deep learning;

机译：特征提取;训练;神经网络;相关性冗余;解相关深度学习;

相似文献

外文文献
中文文献
专利

1. Spam detection on social networks using cost-sensitive feature selection and ensemble-based regularized deep neural networks [J] . Neural computing & applications . 2020,第9期

机译：使用成本敏感特征选择和基于集成的正则化深神经网络的社交网络垃圾邮件检测
2. Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings [J] . Luo X. J., Oyedele Lukumon O., Ajayi Anuoluwapo O., Renewable & Sustainable Energy Reviews . 2020,第Octa期

机译：特征提取和遗传算法增强了建筑物能耗预测的自适应深神经网络
3. Deep learning neural network for texture feature extraction in oral cancer: enhanced loss function [J] . Bishal Bhandari, Abeer Alsadoon, P. W. C. Prasad, Multimedia Tools and Applications . 2020,第37a38期

机译：口腔癌中纹理特征提取深度学习神经网络：增强损失功能
4. Regularized Deep Convolutional Neural Networks for Feature Extraction and Classification [C] . Khaoula Jayech International conference on neural information processing . 2017

机译：用于特征提取和分类的正则化深度卷积神经网络
5. A Framework for Enhancing Speaker Age and Gender Classification by Using a New Feature Set and Deep Neural Network Architectures [D] . Abumallouh, Arafat. 2017

机译：通过使用新功能集和深度神经网络体系结构提高演讲者年龄和性别分类的框架
6. Task-specific feature extraction and classification of fMRI volumes using a deep neural network initialized with a deep belief network: Evaluation using sensorimotor tasks [O] . Hojin Jang, Sergey M. Plis, Vince D. Calhoun, -1

机译：使用初始化为深度置信网络的深度神经网络对功能磁共振成像体积进行任务特定的特征提取和分类：使用感觉运动任务进行评估
7. Task-specific feature extraction and classification of fMRI volumes using a deep neural network initialized with a deep belief network: Evaluation using sensorimotor tasks [O] . Hojin Jang, Sergey M. Plis, Vince D. Calhoun, 2017

机译：使用深度信仰网络初始化的Deep Neural网络的任务特定特征提取和分类FMRI卷：使用Sensorimotor任务进行评估

Regularizing Deep Neural Networks by Enhancing Diversity in Feature Extraction

摘要

著录项

相似文献

相关主题

期刊订阅