Feature Extraction With Deep Neural Networks by a Generalized Discriminant Analysis

Stuhlsatz A.; Lippel J.; Zielke T.

首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Feature Extraction With Deep Neural Networks by a Generalized Discriminant Analysis

【24h】

Feature Extraction With Deep Neural Networks by a Generalized Discriminant Analysis

机译：基于深度判别分析的深度神经网络特征提取

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 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

We present an approach to feature extraction that is a generalization of the classical linear discriminant analysis (LDA) on the basis of deep neural networks (DNNs). As for LDA, discriminative features generated from independent Gaussian class conditionals are assumed. This modeling has the advantages that the intrinsic dimensionality of the feature space is bounded by the number of classes and that the optimal discriminant function is linear. Unfortunately, linear transformations are insufficient to extract optimal discriminative features from arbitrarily distributed raw measurements. The generalized discriminant

机译：我们提出了一种基于深度神经网络（DNN）的经典线性判别分析（LDA）的泛化特征提取方法。对于LDA，假定从独立的高斯类条件条件生成的判别特征。这种建模的优点是，特征空间的固有维数受类数的限制，并且最佳判别函数是线性的。不幸的是，线性变换不足以从任意分布的原始测量中提取最佳判别特征。广义判别式

著录项

来源
《Neural Networks and Learning Systems, IEEE Transactions on》 |2012年第4期|p.596-608|共13页
作者
Stuhlsatz A.; Lippel J.; Zielke T.;
展开▼
作者单位

Research and Development Division, SMS Siemag AG, Düsseldorf,;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Deep neural networks; dimensionality reduction; discriminant analysis; face detection; feature extraction; restricted Boltzmann machines; sensor fusion;

机译：深度神经网络;降维;判别分析;人脸检测;特征提取;受限玻尔兹曼机;传感器融合;

相似文献

外文文献
中文文献
专利

1. Separation of movement direction concepts based on independent component analysis algorithm, linear discriminant analysis, deep belief network, artificial and fuzzy neural networks [J] . Sabzevari Mohammadamin, Imani Ehsan Biomedical signal processing and control . 2020,第Sepa期

机译：基于独立分量分析算法，线性判别分析，深度信仰网络，人工和模糊神经网络的运动方向概念分离
2. Task-specific feature extraction and classification of fMRI volumes using a deep neural network initialized with a deep belief network: Evaluation using sensorimotor tasks [J] . Jang Hojin, Plis Sergey M., Calhoun Vince D., NeuroImage . 2017,第Pta2期

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
3. NON-LINEAR DISCRIMINANT FEATURE EXTRACTION USING GENERALIZED BACK-PROPAGATION NETWORK [J] . JIAN-HUI JIANG, JI-HONG WANG, XIA CHU, Journal of Chemometrics . 1996,第4期

机译：基于广义反向传播网络的非线性鉴别特征提取
4. Training data reduction and nonlinear feature extraction in classification based on greedy Generalized Discriminant Analysis [C] . Yang Chun, Liu Xiaofang International Conference on Natural Computation . 2013

机译：基于贪婪广义判别分析的分类中训练数据约简和非线性特征提取
5. Geometric Properties of the Gradient of Loss Functions in Discriminant Deep Neural Networks [D] . Li, Li. 2021

机译：判别深神经网络中损耗函数梯度的几何特性
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

Feature Extraction With Deep Neural Networks by a Generalized Discriminant Analysis

摘要

著录项

相似文献

相关主题

期刊订阅