检索结果-内蒙古大学图书馆

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Yao, Yanli Yu, Qiang Wang, Longbiao Dang, Jianwu Tianjin Univ Sch Comp Sci & Technol Tianjin Key Lab Cognit Comp & Applicat Tianjin Peoples R China

ISBN: (纸本)9781728124858

Different from traditional artificial neural networks (ANNs), spiking neural networks (SNNs) represent and transfer information in spikes, which are considered more like human brain. SNNs contain time information, which make them more suitable for addressing time-structured speech signals. However, it still remains challenging for spiking neural network (SNN) to implement classification tasks based on speech due to the lack of a proper encoding. In this paper, an integrated spiking neural network is proposed to perform the gender classification task. The whole system consists of three functional parts, including encoding, learning and readout. As convolutional restricted boltzmann machine (CRBM) has shown outstanding capability for unsupervised learning of auditory features, we adopt it in this paper as a feature extractor, followed by a spike-latency encoding layer that converts the feature values into spike times. Then these spikes are processed by the spiking neural networks with the tempotron learning rule. We use the TIMIT database to evaluate the performance of our system. Our results show that the as-proposed system is robust for gender classification across a wide range of noise levels.

关键词： Spiking Neural Network convolutional restricted boltzmann machine gender classification

来源：评论

学校读者我要写书评

暂无评论

FACIAL BEAUTY PREDICTION MODEL BASED ON SELF-TAUGHT LEARNING AND convolutional restricted boltzmann machine 13

FACIAL BEAUTY PREDICTION MODEL BASED ON SELF-TAUGHT LEARNING...

引用

International Conference on machine Learning and Cybernetics

作者： Gan, Junying Li, Lichen Zhai, Yikui Wuyi Univ Sch Informat & Engn Jiangmen 529020 Guangdong Peoples R China

ISBN: (纸本)9781479942152

The research of facial beauty mostly focuses on geometric features, which may easily lose much feature information characterizing facial beauty and rely heavily on the accurate manual localization of landmark facial features. Therefore, a novel method to extract apparent features of face images by convolutional restricted boltzmann machine (CRBM) without relying on artificial features selection is proposed. Massive beautiful and ugly training samples are required by traditional machine learning methods, and it is hard to be satisfied because most face images are actually neutral beauty. A better method of relaxing strict restrictions of training samples is self-taught learning, which automatically improves CRBM to understand the characteristics of data distribution even if the requirements of the class and number of training samples are not satisfied, thus the facial beauty prediction model could be established reasonably. Experimental results show that the proposed facial beauty prediction model can achieve recognition rate of 87.3% on three classes of beautiful, ordinary and unbeautiful face images, and 95% on two classes of beautiful and unbeautiful face images. Meanwhile, the extracted apparent features can effectively characterize feature information of beautiful faces.

关键词： Self-taught learning convolutional restricted boltzmann machine Apparent features Facial beauty prediction model

来源：评论

学校读者我要写书评

暂无评论

Fault identification of hydropower unit based on time-frequency feature map of vibration signals and Convrbm-ResNet

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2025年第1期36卷 016121-016121页

作者： Chen, Tingxi Chen, Jinbao Zou, Yidong Liu, Dong Hu, Wenqing Zheng, Yang Xiao, Zhihuai Wuhan Univ Sch Power & Mech Engn Wuhan 430072 Peoples R China China Yangtze River Elect Power Co Ltd Wuhan 430000 Hubei Peoples R China Xihua Univ Key Lab Fluid & Power Machinery Minist Educ Chengdu 610039 Peoples R China

To address the significant impact of the non-stationarity and nonlinearity of vibration signals on the accuracy of fault identification in hydropower units, a method for condition identification based on time-frequency characteristics of vibration signals and convolutional restricted boltzmann machines-Residual Network (ConvRBM-ResNet ) is proposed. The vibration signals are first decomposed by adopting Complementary Comprehensive Empirical Modal Decomposition to further obtain Intrinsic Mode Functions (IMFs) at various frequencies. Then, by combining correlation analysis, the more sensitive IMF components are extracted. Furthermore, the obtained effective IMF components are converted into time-frequency feature maps, which are consequently adopted as inputs to pre-train the ConvRBM model to simplify feature representation. Finally, using the fault category as the output, a fault identification model for hydropower units is obtained by training ConvRBM-ResNet. The proposed fault identification model is validated with actual operation data of a hydropower station. The results indicate that the proposed fault identification model can accurately identify the operating status of the hydropower unit, achieving an accuracy of 98.88%, which is a 4% improvement over the non-improved method. The time cost is reasonable, and the model demonstrates strong robustness.

关键词： time-frequency feature map convolutional restricted boltzmann machine residual network fault diagnosis hydropower unit vibration signal

来源：评论

学校读者我要写书评

暂无评论

Monitoring of Changes in Data Stream Distribution Using convolutional restricted boltzmann machines 20th

Monitoring of Changes in Data Stream Distribution Using Conv...

引用

20th International Conference on Artificial Intelligence and Soft Computing (ICAISC)

作者： Jaworski, Maciej Rutkowski, Leszek Staszewski, Pawel Najgebauer, Patryk Cracow Univ Technol Dept Comp Sci Krakow Poland Czestochowa Tech Univ Dept Computat Intelligence Czestochowa Poland Univ Social Sci Inst Informat Technol Lodz Poland

ISBN: (纸本)9783030879860;9783030879853

In this paper, we propose the convolutional restricted boltzmann machine (CRBM) as a tool for detecting concept drift in time-varying data streams. Recently, it was demonstrated that the restricted boltzmann machine (RBM) can be successfully applied to this task. A properly learned RBM contains information about the data probability distribution. Trained on one part of the stream it can be used to detect possible changes in the incoming data. In this work we replace the fully-connected layer in the standard RBM with the convolutional layer, composing the CRBM. We show that it is more suitable for the drift detection task regarding the image data. Preliminary experimental results demonstrate the usefulness of the CRBM as a tool for drift detection in data streams with such type of data.

关键词： convolutional restricted boltzmann machine Data stream mining Concept drift detection

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Pre-Training of Deep Neural Classifiers 12

Unsupervised Pre-Training of Deep Neural Classifiers

引用

12th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, IDAACS 2023

作者： Kroshchanka, Aliaksandr Golovko, Vladimir Peiwen, Shi Lubanska, Zofia Quintary Ai Paphos8011 Cyprus John Paul Ii University in Biala-Podlaska Biala-Podlaska21-500 Poland Jilin International Studies University Changchun City130117 China

ISBN: (纸本)9798350358056

The paper is devoted to studying the issues of pre-training of deep neural network models. A generalized approach for pre-training deep models is proposed, which allows achieving better performance in final accuracy and can be used when training on small datasets. The effectiveness of the proposed approach is demonstrated on examples of training deep neural classifiers models using the MNIST and CIFAR-10 datasets. The obtained results can be used to train fully connected and convolutional types of layers. © 2023 IEEE.

关键词： convolutional restricted boltzmann machine deep neural network pre-training restricted boltzmann machine

来源：评论

学校读者我要写书评

暂无评论

Image recognition based on improved convolutional deep belief network model

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第2期80卷 2031-2045页

作者： Wang, Hongmei Liu, Pengzhong Northwestern Polytech Univ Sch Astronaut Xian Peoples R China Northwestern Polytech Univ Natl Key Lab Aerosp Flight Dynam Xian Peoples R China

Aiming at the homogeneity of convolution kernels in convolutional Deep Belief Network (CDBN), a cross-entropy-based sparse penalty mechanism suitable for convolutional restricted boltzmann machine (CRBM) model is introduced which makes the hidden layer units of the whole network in a lower activation state. On this basis, a parameter learning algorithm is applied to compensate the gradient by introducing the prior information of the samples, which alternates the supervised learning and unsupervised learning. The experimental results show that the proposed model can weaken the homogeneity of convolution kernels and improve the supervising and predicting ability of the network. The recognition rate on simulated dataset achieves 97.45%, which is increased 5.12% and 1.29% than convolutional Neural Network (CNN) and the traditional CDBN model, respectively. At the same time, test error rate on common dataset MNIST also shows that the proposed model is more effective than some other state-of-the-art deep learning models.

关键词： Image recognition convolutional deep belief network convolutional restricted boltzmann machine Homogeneity Gradient diffusion

来源：评论

学校读者我要写书评

暂无评论

Multifocus Image Fusion Method Based on convolutional Deep Belief Network

引用

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2021年第1期16卷 85-97页

作者： Zhai, Hao Zhuang, Yi Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 211106 Peoples R China

Multifocus image fusion is a technique that can integrate the focus information of different source images into a single composite image. At present, most fusion methods still suffer from problems such as block artifacts, artificial edges, halo effects, ringing effects, and contrast reduction. To address these problems, a novel multifocus image fusion method based on a convolutional deep belief network is proposed in this paper. The convolutional operator can effectively extract the focus information of source images, and the focused features extracted from source images can effectively distinguish focused windows from defocused windows. After multiple rounds of training, the convolutional deep belief network model can establish an effective mapping between source images and a score map, which is essential to generate an accurate focus map. Then, the focus map is further modified using binary segmentation and small region filtering, and the final decision map for fusion is obtained. Finally, according to the weights provided by the final decision map, a final fusion image will be formed by fusing multiple source images. The experimental results show that the proposed method is superior to other existing fusion methods in terms of subjective visual effects and objective quantitative evaluation. (c) 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

关键词： multifocus image fusion convolutional deep belief network convolutional restricted boltzmann machine deep learning

来源：评论

学校读者我要写书评

暂无评论

Flexible human motion transition via hybrid deep neural network and quadruple-like structure learning

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL SCIENCE AND ENGINEERING 2021年第2期24卷 136-146页

作者： Peng, Shu-Juan Zhang, Liang-Yu Liu, Xin Huaqiao Univ Coll Comp Sci & Technol Xiamen 361021 Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen 361021 Peoples R China Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen 361021 Peoples R China

Skeletal motion transition is of crucial importance to the animation creation. In this paper, we propose a hybrid deep learning framework that allows for efficient human motion transition. First, we integrate a convolutional restricted boltzmann machine with deep belief network to extract the spatio-temporal features of each motion style, featuring on appropriate detection of transition points. Then, a quadruples-like data structure is exploited for motion graph building, motion splitting and indexing. Accordingly, the similar frames fulfilling the transition segments can be efficiently retrieved. Meanwhile, the transition length is reasonably computed according to the average speed of the motion joints. As a result, different kinds of diverse motions can be well transited with satisfactory performance. The experimental results show that the proposed transition approach brings substantial improvements over the state-of-the-art methods.

关键词： skeletal motion transition hybrid deep learning convolutional restricted boltzmann machine quadruples-like data structure

来源：评论

学校读者我要写书评

暂无评论

Detection of weak transient signals based on unsupervised learning for bearing fault diagnosis

引用

NEUROCOMPUTING 2018年 314卷 445-457页

作者： Chen, Longting Xu, Guanghua Wang, Yi Wang, Jianhua Xi An Jiao Tong Univ Sch Mech Engn Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian 710049 Shaanxi Peoples R China

Transient impulse contains abundant information of bearings status. When fault occurs, it is activated and would recur periodically or quasi-periodically. Its period can indicate where defects lie in. However, transient impulse is easily swallowed by background noise or interferences in part or in whole, especially at early stage of fault. This problem brings hard obstacles into faults detection. Considering that transient impulses are periodical or quasi-periodical and vibration signal has local similarity, the single transient impulse can be seen as one of shift-invariant features. In view of this, this paper derives adaptive and non-linear signal decomposition formulas and further proposes adaptive and unsupervised feature learning method by using convolutional restricted boltzmann machine model. With respecting local waveform structures, this method can automatically capture shift-invariant patterns hidden in original signal and decompose the original signal into several sub-components at the cost of minimizing reconstruction error. Among these sub-components, the fault-related information, i.e., transient impulses signal, could be extracted likely. It provides a promising idea for intelligent signal processing by using unsupervised learning. Afterwards, Maximizing kurtosis is applied to select optimally latent fault component. Two real bearing experiments validate this method is effective and reliable in extraction of weak transient impulses. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Bearing fault detection Signal decomposition Unsupervised deep learning convolutional restricted boltzmann machine Shift-invariant feature learning

来源：评论

学校读者我要写书评

暂无评论

Spiking convolutional Deep Belief Networks 26th

Spiking Convolutional Deep Belief Networks

引用

26th International Conference on Artificial Neural Networks (ICANN)

作者： Kaiser, Jacques Zimmerer, David Tieck, J. Camilo Vasquez Ulbrich, Stefan Roennau, Arne Dillmann, Ruediger FZI Res Ctr Informat Technol D-76131 Karlsruhe Germany

ISBN: (纸本)9783319686127;9783319686110

Understanding visual input as perceived by humans is a challenging task for machines. Today, most successful methods work by learning features from static images. Based on classical artificial neural networks, those methods are not adapted to process event streams as provided by the Dynamic Vision Sensor (DVS). Recently, an unsupervised learning rule to train Spiking restricted boltzmann machines has been presented [9]. Relying on synaptic plasticity, it can learn features directly from event streams. In this paper, we extend this method by adding convolutions, lateral inhibitions and multiple layers. We evaluate our method on a self-recorded DVS dataset as well as the Poker-DVS dataset. Our results show that our convolutional method performs better and needs less parameters. It also achieves comparable results to previous event-based classification methods while learning features in an unsupervised fashion.

关键词： Spiking neural network convolutional restricted boltzmann machine event-based Contrastive Divergence

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：