检索结果-内蒙古大学图书馆

26th IEEE International Conference on Image Processing (ICIP)

作者： Song, Jianqiang Shi, Guangming Xie, Xuemei Gao, Dahua Xidian Univ Sch Artificial Intelligence Xian 710071 Shaanxi Peoples R China

ISBN: (纸本)9781538662496

Zero-shot learning (ZSL), which focuses on transferring the knowledge from the seen classes to unseen ones, has attracted more and more attention in the computer vision community. Exploring the relationships among the spaces of visual representation, semantic description and label information is a key to the success of ZSL. In this paper, we propose a novel approach by using a two-layer stacked autoencoder (StAE) with manifold regularizations to construct the tight relations of different spaces, where the first-layer encoder aims to project a visual feature vector into the semantic space, and the second-layer encoder connects the semantic description of a sample with its label directly. Meanwhile, the decoders seek to reconstruct the visual representation from label information and semantic description successively. Besides, two manifold regularizers are integrated in the stacked autoencoder, which captures the manifold structures residing in the different spaces effectively. Compared with the previous related works, the proposed approach is a more general framework and has stronger transfer ability from seen classes to unseen classes. Extensive experiments on the benchmark datasets clearly demonstrate that our StAE performs significantly better than the state-of-the-arts.

关键词： Zero-shot learning stacked autoencoder manifold regularizers general framework

来源：评论

学校读者我要写书评

暂无评论

Manifold Regularized stacked autoencoder for Feature Learning

Manifold Regularized Stacked Autoencoder for Feature Learnin...

引用

IEEE International Conference on Systems, Man, and Cybernetics (SMC)

作者： Lu, Sicong Liu, Huaping Li, Chunwen Tsinghua Univ Sch Informat Sci & Technol Beijing 100084 Peoples R China

ISBN: (纸本)9781479986965

stacked autoencoders enjoy their popularization with the prosperity of deep learning in recent years. However, relative studies seldom exploit the intrinsic information buried in the interrelations between the samples with respect to deep networks. Regarding this, the manifold regularization is introduced to analyze the neighborhood of each training sample, which leads to a manifold regularized stacked autoencoder hierarchical framework with deep multilayer substructures. A series of experiments are conducted upon MNIST and YaleFaces using locally linear embedding as the manifold regularization module. The results show that neighborhood analysis should be combined with stacked autoencoders to achieve some notable promotions of their performances.

关键词： manifold regularization stacked autoencoder feature learning locally linear embedding

来源：评论

学校读者我要写书评

暂无评论

A Semi-supervised stacked autoencoder Approach for Network Traffic Classification 28

A Semi-supervised Stacked Autoencoder Approach for Network T...

引用

28th IEEE International Conference on Network Protocols (IEEE ICNP)

作者： Aouedi, Ons Piamrat, Kandaraj Bagadthey, Dhruvjyoti Univ Nantes LS2N 2 Chemin Houssiniere Nantes France IIT Madras Dept Elect Engn Chennai 600036 Tamil Nadu India

ISBN: (纸本)9781728169927

Network traffic classification is an important task in modern communications. Several approaches have been proposed to improve the performance of differentiating among applications. However, most of them are based on supervised learning where only labeled data are used. In reality, a lot of datasets are partially labeled due to many reasons and unlabeled portions of the data, which can also provide informative characteristics, are ignored. To handle this issue, we propose a semi-supervised approach based on deep learning. We deployed deep learning because of its unique nature for solving problems, and its ability to take into account both labeled and unlabeled data. Moreover, it can also integrate feature extraction and classification into a single model. To achieve these goals, we propose an approach using stacked sparse autoencoder (SSAE) accompanied by denoising and dropout techniques to improve the robustness of extracted features and prevent the over-fitting problem during the training process. The obtained results demonstrate a better performance than traditional models while keeping the whole procedure automated.

关键词： Traffic classification Feature extraction Deep learning Machine learning stacked autoencoder stacked Denoising autoencoder Dropout Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

ROBUST FEATURE LEARNING BY stacked autoencoder WITH MAXIMUM CORRENTROPY CRITERION

ROBUST FEATURE LEARNING BY STACKED AUTOENCODER WITH MAXIMUM ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Qi, Yu Wang, Yueming Zheng, Xiaoxiang Wu, Zhaohui Zhejiang Univ Qiushi Acad Adv Studies Hangzhou 310003 Zhejiang Peoples R China

ISBN: (纸本)9781479928934

Unsupervised feature learning with deep networks has been widely studied in the recent years. Despite the progress, most existing models would be fragile to non-Gaussian noises and outliers due to the criterion of mean square error (MSE). In this paper, we propose a robust stacked autoencoder (R-SAE) based on maximum correntropy criterion (MCC) to deal with the data containing non-Gaussian noises and outliers. By replacing MSE with MCC, the anti-noise ability of stacked autoencoder is improved. The proposed method is evaluated using the MNIST benchmark dataset. Experimental results show that, compared with the ordinary stacked autoencoder, the R-SAE improves classification accuracy by 14% and reduces the reconstruction error by 39%, which demonstrates that R-SAE is capable of learning robust features on noisy data.

关键词： Unsupervised feature learning stacked autoencoder correntropy deep learning

来源：评论

学校读者我要写书评

暂无评论

Prediction of the Indian summer monsoon using a stacked autoencoder and ensemble regression model (vol 37, pg 58, 2021)

引用

INTERNATIONAL JOURNAL OF FORECASTING 2021年第3期37卷 1309-1309页

作者： Saha, Moumita Santara, Anirban Mitra, Pabitra Chakraborty, Arun Nanjundiah, Ravi S. [a]Department of Computer Science University of Colorado Boulder USA [b]Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India [c]Centre for Oceans Rivers Atmosphere and Land Sciences Indian Institute of Technology Kharagpur India [d]Centre for Atmospheric and Oceanic Sciences Indian Institute of Science Bangalore India [e]Divecha Centre for Climate Change Indian Institute of Science Bangalore India [f]Indian Institute of Tropical Meteorology Pune India

The study of climatic variables that govern the Indian summer monsoon has been widely explored. In this work, we use a non-linear deep learning-based feature reduction scheme for the discovery of skilful predictors for monsoon rainfall with climatic variables from various regions of the globe. We use a stacked autoencoder network along with two advanced machine learning techniques to forecast the Indian summer monsoon. We show that the predictors such as the sea surface temperature and zonal wind can predict the Indian summer monsoon one month ahead, whereas the sea level pressure can predict ten months before the season. Further, we also show that the predictors derived from a combination of climatic variables can outperform the predictors derived from an individual variable. The stacked autoencoder model with combined predictors of sea surface temperature and sea level pressure can predict the monsoon (June-September) two months ahead with a 2.8% error. The accuracy of the identified predictors is found to be superior to the state-of-the-art predictions of the Indian monsoon.

关键词： stacked autoencoder Automated feature learning Predictor identification Monsoon prediction Ensemble regression model Indian summer monsoon

来源：评论

学校读者我要写书评

暂无评论

Sense-Through-Foliage Target Detection Based on stacked autoencoder and UWB Radar Sensor Networks 10th

Sense-Through-Foliage Target Detection Based on Stacked Auto...

引用

10th International Conference on Communications, Signal Processing, and Systems

作者： Mao, Chengchen Liang, Qilian Univ Texas Arlington Arlington TX 76019 USA

ISBN: (纸本)9789811903908;9789811903892

In this paper, we proposed a stacked autoencoder (SAE)-based approach to ultra wide band (UWB) radar for sense-through-foliage target detection. As one of the widely used deep learning structures, SAE could learn representations of data with multiple levels of abstraction automatically. Processing the poor signal collections, in some positions, the SAE-based target detection approach performed well. While in other positions, a single radar target detection performed under satisfaction, RAKE structure was applied in radar sensor networks with maximum ratio combing and equal combine to integrate radar echoes from different radar cluster-members. The experimental results showed that the RAKE-SAE-based method could qualify the mission of target detection.

关键词： Ultra-WideBand radar Sense-through-foliage Target detection Radar sense network stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep Sparse Representation Classification with stacked autoencoder 15

Deep Sparse Representation Classification with Stacked Autoe...

引用

15th International Conference on Computational Intelligence and Security (CIS)

作者： Xu, Bingxin Zhou, Xiuling Beijing Union Univ Beijing Key Lab Informat Serv Engn Beijing Peoples R China Beijing City Univ Dept Technol & Ind Dev Beijing Peoples R China

ISBN: (纸本)9781728160924

Sparse representation classification (SRC) is a new framework for classification and has been successfully applied to face recognition. However, in some cases it is not well to represent the test sample accurately, which tends to undermine the classification accuracy. In order to alleviate this issue, a deep sparse representation based classification (DSRC) method with a deep dictionary which learned by stacked autoencoder is proposed. Specifically, the proposed method trains a stacked autoencoders by pseudoinverse learning and used the hidden outputs to construct a deep dictionary. Given the deep dictionary, a hierarchical sparse representation based classification method is presented to determine the label for each test sample by a weighted residuals strategy. The experimental results show that the proposed method can achieve a comprehensively better performance compared with the state-of-the-art classification methods.

关键词： deep sparse representation stacked autoencoder pseudoinverse learning dictionary Learning

来源：评论

学校读者我要写书评

暂无评论

Predictor Discovery for Early-Late Indian Summer Monsoon Using stacked autoencoder

Predictor Discovery for Early-Late Indian Summer Monsoon Usi...

引用

16th Annual International Conference on Computational Science (ICCS)

作者： Saha, Moumita Mitra, Pabitra Nanjundiah, Ravi S. Indian Inst Technol Kharagpur Dept Comp Sci & Engn Kharagpur W Bengal India Indian Inst Sci Div Ctr Climate Change Ctr Atmospher & Ocean Sci Bangalore Karnataka India

Indian summer monsoon has distinct behaviors in its early and late phase. The influencing climatic factors are also different. In this work we aim to predict the national rainfall in these phases. The predictors used by the forecast models are discovered using a stacked autoencoder deep neural network. A fitted regression tree is used as the forecast model. A superior accuracy to state of art method is achieved. We also observe that the late monsoon can be predicted with higher accuracy than early monsoon rainfall.

关键词： Feature learning Monsoon predictors stacked autoencoder Early and Late Indian summer monsoon

来源：评论

学校读者我要写书评

暂无评论

Plant classification based on stacked autoencoder 2

Plant classification based on Stacked Autoencoder

引用

2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC 2017)

作者： Meng-Meng Yang Arifur Nayeem Ling-Ling Shen School of Computer Science and Technology Nanjing Normal University Saidpur Government Technical School And College School of Overseas Education Nanjing University Of Post And Telecommunications School of Business of Nanjing Normal University

ISBN: (纸本)9781509064151;9781509064144

With the development of rapid technology, the similarity between plants is increasing, which will enhance the classified workload of botanists. Therefore, it is urge to find a quick automatic classification method. In recent years, the performance of autoencoder has become more and more prominent. Consequently, in this paper, we employ stacked autoencoder to classify three plants, including 630 images in total. The result of this experience shows that the accuracy of classification is 93.3%.

关键词： stacked autoencoder plant classification deep learning

来源：评论

学校读者我要写书评

暂无评论

EXPERIMENTAL STUDY ON stacked autoencoder ON INSUFFICIENT TRAINING SAMPLES

EXPERIMENTAL STUDY ON STACKED AUTOENCODER ON INSUFFICIENT TR...

引用

International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)

作者： Xue, Jin Chan, Patrick P. K. Hu, Xian South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China

ISBN: (纸本)9781538604120

Many studies have shown that deep learning outperforms traditional machine learning methods in many applications. To prevent overfitting, a huge number of training samples is usually required in training process of deep learning. However, collecting such a large dataset is time-consumed and costly. Recently, several methods have been proposed to effectively learn the models with a limited number of training samples. In this paper, we experimentally evaluate the data augmentation and the transfer learning methods on the MNIST dataset with stacked autoencoders. The experiment results suggest that the transfer learning method can improve the performance of the SAE when training samples are insufficient.

关键词： Deep learning Small dataset stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：