检索结果-内蒙古大学图书馆

IEEE International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives

作者： Bin Xin Tianhao Tang Tianzhen Wang Shanghai Maritime University Shanghai China

With the single-tube and double-tube fault of seven-level converter, this paper presents a new way to learn the faults feature based on the deep neural network of sparse autoencoder. sparse autoencoder is an unsupervised learning method, it can learn the feature information of the fault data according to training. The feature information is used to train the softmax classifier by softmax regression to realize the aim of classification. Comparing with the traditional neural network of BP neural network, the experimental results show that the method to classify the fault of seven level converter based on deep neural network of sparse autoencoder can achieve higher accuracy.

关键词： Fault diagnosis Deep neural network Seven-level converter sparse autoencoder Softmax classifier

来源：评论

学校读者我要写书评

暂无评论

Evaluating Shape Representations for Maya Glyph Classification

引用

ACM JOURNAL ON COMPUTING AND CULTURAL HERITAGE 2016年第3期9卷 14-14页

作者： Can, Gulcan Odobez, Jean-Marc Gatica-Perez, Daniel Idiap Res Inst Martigny Switzerland Ecole Polytech Fed Lausanne Lausanne Switzerland Idiap Res Inst Ctr Parc Rue Marconi 19 CH-1920 Martigny Switzerland

Shape representations are critical for visual analysis of cultural heritage materials. This article studies two types of shape representations in a bag-of-words-based pipeline to recognize Maya glyphs. The first is a knowledge-driven Histogram of Orientation Shape Context (HOOSC) representation, and the second is a data-driven representation obtained by applying an unsupervised sparse autoencoder (SA). In addition to the glyph data, the generalization ability of the descriptors is investigated on a larger-scale sketch dataset. The contributions of this article are four-fold: (1) the evaluation of the performance of a data-driven auto-encoder approach for shape representation;(2) a comparative study of hand-designed HOOSC and data-driven SA;(3) an experimental protocol to assess the effect of the different parameters of both representations;and (4) bridging humanities and computer vision/machine learning for Maya studies, specifically for visual analysis of glyphs. From our experiments, the data-driven representation performs overall in par with the hand-designed representation for similar locality sizes on which the descriptor is computed. We also observe that a larger number of hidden units, the use of average pooling, and a larger training data size in the SA representation all improved the descriptor performance. Additionally, the characteristics of the data and stroke size play an important role in the learned representation.

关键词： HOOSC sparse autoencoder sketch Maya glyph

来源：评论

学校读者我要写书评

暂无评论

Fine-grained representation learning in convolutional autoencoders

引用

JOURNAL OF ELECTRONIC IMAGING 2016年第2期25卷 023018-023018页

作者： Luo, Chang Wang, Jie Air Force Engn Univ Air & Missile Def Coll 1 East Changle Rd Xian 710051 CN Peoples R China

Convolutional autoencoders (CAEs) have been widely used as unsupervised feature extractors for high-resolution images. As a key component in CAEs, pooling is a biologically inspired operation to achieve scale and shift invariances, and the pooled representation directly affects the CAEs' performance. Fine-grained pooling, which uses small and dense pooling regions, encodes fine-grained visual cues and enhances local characteristics. However, it tends to be sensitive to spatial rearrangements. In most previous works, pooled features were obtained by empirically modulating parameters in CAEs. We see the CAE as a whole and propose a fine-grained representation learning law to extract better fine-grained features. This representation learning law suggests two directions for improvement. First, we probabilistically evaluate the discrimination-invariance tradeoff with fine-grained granularity in the pooled feature maps, and suggest the proper filter scale in the convolutional layer and appropriate whitening parameters in preprocessing step. Second, pooling approaches are combined with the sparsity degree in pooling regions, and we propose the preferable pooling approach. Experimental results on two independent benchmark datasets demonstrate that our representation learning law could guide CAEs to extract better fine-grained features and performs better in multiclass classification task. This paper also provides guidance for selecting appropriate parameters to obtain better fine-grained representation in other convolutional neural networks. (C) 2016 SPIE and IS&T

关键词： Pooling fine-grained representation convolutional neural networks sparse autoencoder discrimination-invariance tradeoff unsupervised learning deep learning

来源：评论

学校读者我要写书评

暂无评论

A sparse FEATURE REPRESENTATION FOR GENETIC DATA ANALYSIS 14

A SPARSE FEATURE REPRESENTATION FOR GENETIC DATA ANALYSIS

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Liu, Hua-Hao Huang, Pei-Jie Lin, Pi-Yuan Lin, Wen-Hu Qi, Pei-Heng Song, Chong-Hua South China Agr Univ Coll Math & Informat Guangzhou 510642 Guangdong Peoples R China

ISBN: (纸本)9781467372206

Feature representation is one of the key research issues in machine learning. In some applications with high dimensionality of data, e.g. genomic microarray data, obtaining a good feature representation with effective dimensionality reduction still remains a challenge. In this paper, instead of selecting a subset of original features by feature selection, we use sparse autoencoder to find a reconstructed feature representation for genetic data analysis. The performance of our proposed method is empirically evaluated using one of the genomic microarray dataset provided in ASU Feature Selection Repository. The results show that the proposed method yield better classification accuracy than some representative feature selection methods.

关键词： Feature representation sparse autoencoder Machine learning Genetic data analysis

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Rule Reduction using sparse Auto-Encoders

Fuzzy Rule Reduction using Sparse Auto-Encoders

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Sevakula, Rahul K. Verma, Nishchal K. Indian Inst Technol Kanpur Dept Elect Engn Kanpur Uttar Pradesh India

ISBN: (纸本)9781467374286

Fuzzy Rule based regression, classification and control have found great use in modern applications due to its simplicity, flexibility and capability. A key issue in all such methods is the computation time. Computational complexity of training and testing is linearly dependent on the size of fuzzy rule base and the respective fuzzy rule space is exponentially dependent on data dimensionality. sparse Auto-Encoders (SAs) have become popular in giving compact feature representations for image, audio and speech data and have helped in giving state of the art pattern recognition performances in most of the domains. These feature representation are learnt in an unsupervised fashion and are found to give higher order building blocks with which the data is seemingly made of. This paper proposes a method where SAs are used for getting compact feature representation of input data and if needed with reduced dimensionality. The regular fuzzy rule based models are then learnt from data in the new feature space. The method was tested for Regression and Classification problems, giving impressive results in both. The method with Regression problem gave comparable performance with almost half the number of rules and with Classification problem it gave improvement in classification accuracy by 2.67% while reducing the size of fuzzy rule base by 11.25 times and 7.5 times by number.

关键词： sparse autoencoder fuzzy rule reduction deep learning deep belief networks dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

The effect of whitening transformation on pooling operations in convolutional autoencoders

引用

EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING 2015年第1期2015卷 1页

作者： Li, Zuhe Fan, Yangyu Liu, Weihua Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Peoples R China Zhengzhou Univ Light Ind Sch Comp & Commun Engn Zhengzhou 450002 Peoples R China

Convolutional autoencoders (CAEs) are unsupervised feature extractors for high-resolution images. In the pre-processing step, whitening transformation has widely been adopted to remove redundancy by making adjacent pixels less correlated. Pooling is a biologically inspired operation to reduce the resolution of feature maps and achieve spatial invariance in convolutional neural networks. Conventionally, pooling methods are mainly determined empirically in most previous work. Therefore, our main purpose is to study the relationship between whitening processing and pooling operations in convolutional autoencoders for image classification. We propose an adaptive pooling approach based on the concepts of information entropy to test the effect of whitening on pooling in different conditions. Experimental results on benchmark datasets indicate that the performance of pooling strategies is associated with the distribution of feature activations, which can be affected by whitening processing. This provides guidance for the selection of pooling methods in convolutional autoencoders and other convolutional neural networks.

关键词： Convolutional neural network sparse autoencoder Image classification Computer vision Unsupervised learning Deep learning

来源：评论

学校读者我要写书评

暂无评论

Convolutional autoencoder-based Color Image Classification using Chroma Subsampling in YCbCr Space 8

Convolutional Autoencoder-based Color Image Classification u...

引用

Proceedings 2015 8 International Congress on Image and Signal Processing (CISP)

作者： Li, Zuhe Fan, Yangyu Wang, Fengqin Northwestern Polytech Univ Sch Elect & Informat Xian Peoples R China Zhengzhou Univ Light Ind Sch Comp & Commun Engn Zhengzhou Peoples R China

ISBN: (纸本)9781467390989

We propose a convolutional autoencoder neural network for image classification in YCbCr color space to reduce computational complexity. We first learned local image features from image patches in YCbCr space with a sparse autoencoder and then convolved them with large images to obtain global features. Chrominance components were subsampled before convolution as it is permitted to reduce bandwidth for chrominance components in YCbCr space. We then adopted an algorithm to resize the convolved features in chrominance components by shifting the elements after convolution. Global features were finally fed into a softmax classifier to test the classification accuracy. Experimental results reveal that the convolutional neural network in YCbCr space is able to obtain a reduction of at least 21.6% in time consumption compared to the RGB representation with a slight loss in accuracy.

关键词： Image classification Computer vision Unsupervised feature learning Convolutional neural network sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

Abnormal Event Detection using Recurrent Neural Network

Abnormal Event Detection using Recurrent Neural Network

引用

2nd International Conference on Computer Science and Applications (CSA)

作者： Zhou, Xu-gang Zhang, Li-qing Shanghai Jiao Tong Univ Dept Comp Sci Shanghai Peoples R China

ISBN: (纸本)9781479999613

In this paper, we introduce a simple but novel model to detect abnormal event in surveillance video using sparse autoencoder and recurrent neuron network. In this model, we first train a sparse autoencoder to extract features and use a sequence of temporal continuous features to train a recurrent neuron network to predict the subsequent features. We classify the frame as normal and abnormal based on the prediction error of recurrent neuron network. Experimental result on a crowd activity dataset verifies the effectiveness of our model and the implication of recurrent neural networks in abnormal detection is also discussed.

关键词： abnormal event detection sparse autoencoder recurrent neuron network

来源：评论

学校读者我要写书评

暂无评论

A Vehicle Type Recognition Method based on sparse Auto Encoder

A Vehicle Type Recognition Method based on Sparse Auto Encod...

引用

2015 International Conference on Computer Information Systems and Industrial Applications(CISIA2015)

作者： H.L.Rong Y.X.Xia Wu Han University of Technology

ISBN: (纸本)9781510805750

In recent years,feature learning methods based on unsupervised learning get more and more *** now,Unsupervised feature learning has been applied to solve many problems such as detection,recognition and *** this paper,we propose a deep feature learning method based on sparse autoencoder to recognize vehicle types and to improve the classification accuracy *** we used sparse autoencoder to generate the convolutional kernel and used the convolutional kernel to generate convolutional *** pooling was *** repeated the network several times to construct a deep feature learning *** improve performance,we also combined the feature learned in different layer to form a new feature vector and applied PCA to reduce the *** we used softmax to recognize the vehicle *** the local receive field,we can reduce the *** experiment shows that our method can improve the performance a little.

关键词： vehicle type recognition sparse autoencoder multilevel features fusing

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Rule Reduction using sparse Auto-Encoders

Fuzzy Rule Reduction using Sparse Auto-Encoders

引用

IEEE International Conference on Fuzzy Systems

作者： Rahul K. Sevakula Nishchal K. Verma Department of Electrical Engineering Indian Institute of Technology Kanpur

ISBN: (纸本)9781467374293

关键词： sparse autoencoder Fuzzy rule reduction Deep learning Deep belief networks Dimensionality reduction

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：