咨询与建议

限定检索结果

文献类型

  • 158 篇 期刊文献
  • 92 篇 会议
  • 2 篇 学位论文

馆藏范围

  • 252 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 235 篇 工学
    • 124 篇 计算机科学与技术...
    • 87 篇 电气工程
    • 40 篇 控制科学与工程
    • 33 篇 信息与通信工程
    • 24 篇 机械工程
    • 18 篇 软件工程
    • 15 篇 生物医学工程(可授...
    • 14 篇 仪器科学与技术
    • 12 篇 石油与天然气工程
    • 8 篇 材料科学与工程(可...
    • 8 篇 动力工程及工程热...
    • 8 篇 电子科学与技术(可...
    • 8 篇 测绘科学与技术
    • 5 篇 土木工程
    • 4 篇 化学工程与技术
    • 2 篇 建筑学
    • 2 篇 纺织科学与工程
    • 2 篇 农业工程
  • 47 篇 理学
    • 19 篇 生物学
    • 11 篇 物理学
    • 9 篇 化学
    • 8 篇 地球物理学
    • 4 篇 数学
    • 3 篇 地理学
    • 3 篇 系统科学
    • 2 篇 统计学(可授理学、...
  • 30 篇 医学
    • 13 篇 基础医学(可授医学...
    • 13 篇 临床医学
    • 3 篇 医学技术(可授医学...
  • 23 篇 管理学
    • 21 篇 管理科学与工程(可...
  • 8 篇 农学
  • 1 篇 法学
  • 1 篇 教育学

主题

  • 252 篇 sparse autoencod...
  • 63 篇 deep learning
  • 24 篇 fault diagnosis
  • 18 篇 feature extracti...
  • 16 篇 deep neural netw...
  • 11 篇 machine learning
  • 9 篇 dimensionality r...
  • 7 篇 support vector m...
  • 7 篇 deep belief netw...
  • 7 篇 convolutional ne...
  • 6 篇 image classifica...
  • 6 篇 feature selectio...
  • 6 篇 convolutional ne...
  • 6 篇 unsupervised lea...
  • 5 篇 compressed sensi...
  • 5 篇 anomaly detectio...
  • 5 篇 face recognition
  • 5 篇 autoencoder
  • 5 篇 unsupervised fea...
  • 5 篇 convolutional au...

机构

  • 6 篇 xian univ techno...
  • 6 篇 tianshui normal ...
  • 3 篇 nanyang technol ...
  • 2 篇 nanjing normal u...
  • 2 篇 zhongnan univ ec...
  • 2 篇 northeast petr u...
  • 2 篇 chinese acad sci...
  • 2 篇 hong kong univ s...
  • 2 篇 northeastern uni...
  • 2 篇 china univ petr ...
  • 2 篇 northwestern pol...
  • 2 篇 hebei univ affil...
  • 2 篇 kasetsart univ g...
  • 2 篇 ming chuan univ ...
  • 2 篇 hubei key lab ad...
  • 2 篇 shenzhen institu...
  • 2 篇 china univ geosc...
  • 2 篇 zhengzhou univ l...
  • 2 篇 natl cent univ d...
  • 2 篇 natl inst techno...

作者

  • 7 篇 xie guo
  • 7 篇 yang jing
  • 7 篇 yang yanxi
  • 3 篇 hu jun
  • 3 篇 nair madhu s.
  • 3 篇 zhang yu-dong
  • 3 篇 wang tianzhen
  • 3 篇 xin bin
  • 3 篇 wang shui-hua
  • 2 篇 zhu zhongkui
  • 2 篇 chen kunjin
  • 2 篇 li xin
  • 2 篇 wu min
  • 2 篇 shen changqing
  • 2 篇 kim ji-seon
  • 2 篇 liu ming
  • 2 篇 liu hongyi
  • 2 篇 lin feng
  • 2 篇 hou xiao-xia
  • 2 篇 hou zengguang

语言

  • 242 篇 英文
  • 5 篇 中文
  • 4 篇 其他
  • 1 篇 法文
检索条件"主题词=Sparse AutoEncoder"
252 条 记 录,以下是241-250 订阅
排序:
A sparse feature representation for genetic data analysis
A sparse feature representation for genetic data analysis
收藏 引用
International Conference on Machine Learning and Cybernetics (ICMLC)
作者: Hua-Hao Liu Pei-Jie Huang Pi-Yuan Lin Wen-Hu Lin Pei-Heng Qi Chong-Hua Song College of Mathematics and Informatics South China Agricultural University Guangzhou China
Feature representation is one of the key research issues in machine learning. In some applications with high dimensionality of data, e.g. genomie microarray data, obtaining a good feature representation with effective... 详细信息
来源: 评论
Semi-Supervised autoencoder : A Joint Approach of Representation And Classification  7
Semi-Supervised Autoencoder : A Joint Approach of Representa...
收藏 引用
7th International Conference on Computational Intelligence and Communication Networks (CICN)
作者: Wu Haiyan Yang Haomin Li Xueming Ren Haijun Chongqing Univ Coll Comp Sci Chongqing Peoples R China
Recent years have witnessed the significant success of representation learning and deep learning in various prediction and recognition applications. Most of these previous studies adopt the two-phase procedures, namel... 详细信息
来源: 评论
No-reference image quality assessment using statistical characterization in the shearlet domain
收藏 引用
SIGNAL PROCESSING-IMAGE COMMUNICATION 2014年 第7期29卷 748-759页
作者: Li, Yuming Po, Lai-Man Xu, Xuyuan Feng, Litong City Univ Hong Kong Dept Elect Engn Hong Kong Hong Kong Peoples R China
Image and video quality measurements are crucial for many applications, such as acquisition, compression, transmission, enhancement, and reproduction. Nowadays, no-reference (NR) image quality assessment (IQA) methods... 详细信息
来源: 评论
Post-Processing of Unsupervised Dictionary Learning in Handwritten Digit Recognition  14
Post-Processing of Unsupervised Dictionary Learning in Handw...
收藏 引用
International Symposium on Communications and Information Technologies
作者: Phaisangittisagul, Ekachai Chongprachawat, Rapeepol Kasetsart Univ Fac Engn Dept Elect Engn Bangkok 10900 Thailand Kasetsart Univ Grad Sch Bangkok 10900 Thailand
To achieve high performance in object recognition, a high-level feature representation is play an essential role to transform a raw input data (low-level) into a new representation. Unsupervised feature learning is on... 详细信息
来源: 评论
Training Large Scale Deep Neural Networks on the Intel Xeon Phi Many-core Coprocessor  28
Training Large Scale Deep Neural Networks on the Intel Xeon ...
收藏 引用
28th IEEE International Parallel & Distributed Processing Symposium Workshops (IPDPSW)
作者: Jin, Lei Wang, Zhaokang Gu, Rong Yuan, Chunfeng Huang, Yihua Nanjing Univ Dept Comp Sci & Technol Natl Key Lab Novel Software Technol Nanjing 210023 Jiangsu Peoples R China
As a new area of machine learning research, the deep learning algorithm has attracted a lot of attention from the research community. It may bring human beings to a higher cognitive level of data. Its unsupervised pre... 详细信息
来源: 评论
A Novel Deep Model for Image Recognition  5
A Novel Deep Model for Image Recognition
收藏 引用
5th IEEE International Conference on Software Engineering and Service Science (ICSESS)
作者: Zhu, Ming Wu, Yan Tongji Univ Coll Elect & Informat Engn Shanghai 200092 Peoples R China
In this paper we propose a hybrid deep network for image recognition. First we use the sparse autoencoder(SAE) which is a method to extract high-level feature representations of data in an unsupervised way, without an... 详细信息
来源: 评论
A Novel Deep Model for Image Recognition
A Novel Deep Model for Image Recognition
收藏 引用
2014 IEEE 5th International Conference on Software Engineering and Service Science
作者: Ming Zhu Yan Wu College of Electronics & Information Engineering University of Tongji
In this paper we propose a hybrid deep network for image *** we use the sparse autoencoder(SAE) which is a method to extract high-level feature representations of data in an unsupervised way,without any manual feature... 详细信息
来源: 评论
基于三维人脸建模的多视角人脸识别方法研究
基于三维人脸建模的多视角人脸识别方法研究
收藏 引用
作者: 邢健飞 杭州电子科技大学
学位级别:硕士
作为典型的模式识别任务,人脸识别有着巨大的实际应用价值与市场前景。理想环境下的人脸识别已经取得不俗成绩,然而,当所处环境变化(如姿态变换、夸张表情、阴阳脸、分辨率较低)时,识别难度增加,效果也急剧变差。与此同时,现有... 详细信息
来源: 评论
SAR Automatic Target Recognition Based on a Visual Cortical System
SAR Automatic Target Recognition Based on a Visual Cortical ...
收藏 引用
6th International Congress on Image and Signal Processing (CISP)
作者: Ni, Jia Cheng Xu, Yue Lei Air Force Engn Univ Inst Aeronaut & Astronaut Engn Xian Peoples R China
Human Vision system is the most complex and accurate system. In order to extract better features about Synthetic Aperture Radar (SAR) targets, a SAR automatic target recognition (ATR) algorithm based on human visual c... 详细信息
来源: 评论
Receptive Field Resolution Analysis in Convolutional Feature Extraction
Receptive Field Resolution Analysis in Convolutional Feature...
收藏 引用
13th International Symposium on Communications and Information Technologies (ISCIT) - Communication and Information Technology for New Life Style Beyond the Cloud
作者: Phaisangittisagul, Ekachai Chongprachawat, Rapeepol Kasetsart Univ Fac Engn Dept Elect Engn Bangkok 10900 Thailand Kasetsart Univ Grad Sch Bangkok 10900 Thailand
Instead of introducing new learning algorithm for solving complex classification tasks, many research groups in machine learning have focused on creating a good feature representation. In addition, labeled data is oft... 详细信息
来源: 评论