检索结果-内蒙古大学图书馆

20th International Conference on Image Analysis and Processing (ICIAP)

作者： Plebe, Alice Da Lio, Mauro Univ Trento Dept Informat Engn & Comp Sci Trento Italy Univ Trento Dept Ind Engn Trento Italy

ISBN: (纸本)9783030306427;9783030306410

In the last decades, the research in autonomous vehicles has greatly improved thanks to the success of artificial neural models. Yet, self-driving cars are far from reaching human performances. It is our opinion that would be wise to reflect on why the human brain is so effective in learning tasks as complex as the one of driving, and to try to take inspiration for designing new artificial driving agents. For this aim, we consider two relevant and related neurocognitive theories: the Convergence-divergence Zones (CDZs) mechanism of mental simulation, and the predicting brain theory. Then, we propose an implementation of a semi-supervised variational autoencoder for visual perception, with an architecture that best approximates those two neurocognitive theories.

关键词： Mental imagery Deep learning Autonomous driving variational autoencoder Free energy

来源：评论

学校读者我要写书评

暂无评论

Website Recommendation with Side Information Aided variational autoencoder 39

Website Recommendation with Side Information Aided Variation...

引用

39th IEEE International Performance Computing and Communications Conference (IPCCC)

作者： Wang, Pinhao Li, Wenzhong Yu, Zepeng Lu, Baoguo Lu, Sanglu Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China Nanjing Univ Sino German Inst Social Comp Nanjing Peoples R China Nanjing Res Inst Elect & Engn Nanjing Peoples R China

ISBN: (纸本)9781728198293

Recommender systems had been proposed to help people to find the interested items, such as recommending products to a buyer;identifying movies or music that a user will find interest, etc. However, the existing recommendation approaches mainly focus on capturing user-item interaction patterns for prediction, and ignore the user's side information such as visit frequency and duration. In this paper, we study the side information aided website recommendation problem that using the browsing history of a set of users and their side information to predict the websites that will be of interest to a certain user. We propose a novel recommendation approach called SI-VAE that incorporates side information with the variational autoencoders (VAEs) model for top-k recommendation. The proposed method takes both user-website interaction information and side information as input, and adopts an encoder/decoder model to generate user's interested websites from partial observations. The model of SI-VAE is implemented as a neural network, and trained with a multinomial likelihood objective function to form the ranking of user-website interaction probabilities. We conduct extensive experiments on two real-world datasets, which show that the proposed model outperforms the baselines in a number of performance metrics in website recommendation.

关键词： variational autoencoder website recommendation side information collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Representation learning of resting state fMRI with variational autoencoder

引用

NEUROIMAGE 2021年 241卷 118423-118423页

作者： Kim, Jung-Hoon Zhang, Yizhen Han, Kuan Wen, Zheyu Choi, Minkyu Liu, Zhongming Univ Michigan Dept Biomed Engn Ann Arbor MI 48109 USA Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA Purdue Univ Weldon Sch Biomed Engn W Lafayette IN 47907 USA

Resting state functional magnetic resonance imaging (rsfMRI) data exhibits complex but structured patterns. However, the underlying origins are unclear and entangled in rsfMRI data. Here we establish a variational auto encoder, as a generative model trainable with unsupervised learning, to disentangle the unknown sources of rsfMRI activity. After being trained with large data from the Human Connectome Project, the model has learned to represent and generate patterns of cortical activity and connectivity using latent variables. The latent representation and its trajectory represent the spatiotemporal characteristics of rsfMRI activity. The latent variables reflect the principal gradients of the latent trajectory and drive activity changes in cortical networks. Representational geometry captured as covariance or correlation between latent variables, rather than cortical connectivity, can be used as a more reliable feature to accurately identify subjects from a large group, even if only a short period of data is available in each subject. Our results demonstrate that VAE is a valuable addition to existing tools, particularly suited for unsupervised representation learning of resting state fMRI activity.

关键词： variational autoencoder Deep generative model Unsupervised learning Latent gradients

来源：评论

学校读者我要写书评

暂无评论

variational autoencoder for Non-Negative Matrix Factorization with Exogenous Inputs Applied to Financial Data Modelling 11

Variational Autoencoder for Non-Negative Matrix Factorizatio...

引用

11th International Symposium on Image and Signal Processing and Analysis (ISPA)

作者： Montesdeoca, Luis Squires, Steven Niranjan, Mahesan Univ Southampton Elect & Comp Sci Southampton England

ISBN: (纸本)9781728131405

Multi-variate time series that arise in financial data, for example, are likely to be driven by underlying lower dimensional latent variables. Extracting such latent spaces can be useful in representing the data efficiently and as a means of explaining aspects of the system from which they are generated. Here, we study an extension to the variational autoencoder model specifically cast in a probabilistic setting to deal with positive valued data to extract a non-negative matrix factorization model (NMF) in a probabilistic setting (PAE-NMF). To model financial data, where information about some underlying macroeconomic system may be observed, we extend the PAE-NMF model to include exogenous variables (PAE-XNMF). We present the learning algorithm for this model and illustrate its operation on financial data of constituents of the FTSE100 index and a set of relevant macroeconomic variables. We show an example of the latent space detecting a sharp transition around the Brexit event that is not readily apparent on any of the individual time series.

关键词： Non Negative Matrix Factorization variational autoencoder Dimensionality Reduction Deep Learning Kull-back Leibler divergence Financial Data Analysis

来源：评论

学校读者我要写书评

暂无评论

Addressing data imbalance problems in ligand-binding site prediction using a variational autoencoder and a convolutional neural network

引用

BRIEFINGS IN BIOINFORMATICS 2021年第6期22卷 bbab277-bbab277页

作者： Trinh-Trung-Duong Nguyen Duc-Khanh Nguyen Ou, Yu-Yen Yuan Ze Univ Comp Sci Dept Chungli Taiwan Yuan Ze Univ Dept Informat Management Chungli Taiwan Yuan Ze Univ Dept Comp Sci & Engn Grad Program Biomed Informat Chungli Taiwan

Since 2015, a fast growing number of deep learning-based methods have been proposed for protein-ligand binding site prediction and many have achieved promising performance. These methods, however, neglect the imbalanced nature of binding site prediction problems. Traditional data-based approaches for handling data imbalance employ linear interpolation of minority class samples. Such approaches may not be fully exploited by deep neural networks on downstream tasks. We present a novel technique for balancing input classes by developing a deep neural network-based variational autoencoder (VAE) that aims to learn important attributes of the minority classes concerning nonlinear combinations. After learning, the trained VAE was used to generate new minority class samples that were later added to the original data to create a balanced dataset. Finally, a convolutional neural network was used for classification, for which we assumed that the nonlinearity could be fully integrated. As a case study, we applied our method to the identification of FAD- and FMN-binding sites of electron transport proteins. Compared with the best classifiers that use traditional machine learning algorithms, our models obtained a great improvement on sensitivity while maintaining similar or higher levels of accuracy and specificity. We also demonstrate that our method is better than other data imbalance handling techniques, such as SMOTE, ADASYN, and class weight adjustment. Additionally, our models also outperform existing predictors in predicting the same binding types. Our method is general and can be applied to other data types for prediction problems with moderate-to-heavy data imbalances.

关键词： variational autoencoder convolutional neural network protein-ligand binding site prediction data imbalance handlin gelectron transport proteins

来源：评论

学校读者我要写书评

暂无评论

Efficient few-shot medical image segmentation via self-supervised variational autoencoder

引用

Medical Image Analysis 2025年 104卷 103637页

作者： Yanjie Zhou Feng Zhou Fengjun Xi Yong Liu Yun Peng David E. Carlson Liyun Tu School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing 100876 China Department of Radiology Beijing Tiantan Hospital Capital Medical University Beijing 100070 China Department of Radiology MOE Key Laboratory of Major Diseases in Children Beijing Children’s Hospital Capital Medical University National Center for Children’s Health Beijing 100045 China Department of Civil and Environmental Engineering and the Department of Electrical and Computer Engineering Duke University Durham NC 27708 USA

Few-shot medical image segmentation typically uses a joint model for registration and segmentation. The registration model aligns a labeled atlas with unlabeled images to form initial masks, which are then refined by the segmentation model. However, inevitable spatial misalignments during registration can lead to inaccuracies and diminished segmentation quality. To address this, we developed EFS-MedSeg, an end-to-end model using two labeled atlases and few unlabeled images, enhanced by data augmentation and self-supervised learning. Initially, EFS-MedSeg applies a 3D random regional switch strategy to augment atlases, thereby enhancing supervision in segmentation tasks. This not only introduces variability to the training data but also enhances the model’s ability to generalize and prevents overfitting, resulting in natural and smooth label boundaries. Following this, we use a variational autoencoder for a weighted reconstruction task, focusing the model’s attention on areas with lower Dice scores to ensure accurate segmentation that conforms to the atlas image’s shape and structural appearance. Moreover, we introduce a self-contrastive module aimed at improving feature extraction, guided by anatomical structure priors, thus enhancing the model’s convergence and segmentation accuracy. Results on multi-modal medical image datasets show that EFS-MedSeg achieves performance comparable to fully-supervised methods. Moreover, it consistently surpasses the second-best method in Dice score by 1.4%, 9.1%, and 1.1% on the OASIS, BCV, and BCH datasets, respectively, highlighting its robustness and adaptability across diverse datasets. The source code will be made publicly available at: https://***/NoviceFodder/EFS-MedSeg .

关键词： Few-shot learning Image reconstruction Medical image segmentation variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Network Embedding via Community Based variational autoencoder

引用

IEEE ACCESS 2019年 7卷 25323-25333页

作者： Shi, Wei Huang, Ling Wang, Chang-Dong Li, Juan-Hui Tang, Yong Fu, Chengzhou Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou 510006 Guangdong Peoples R China Guangdong Prov Key Lab Computat Sci Guangzhou 510275 Guangdong Peoples R China South China Normal Univ Sch Comp Sci Guangzhou 510631 Guangdong Peoples R China

In recent years, network embedding has attracted more and more attention due to its effectiveness and convenience to compress the network structured data. In this paper, we propose a community-based variational autoencoder (ComVAE) model to learn network embedding, which consists of a community detection module and a deep learning module. In the proposed model, both community information and deep learning techniques are utilized to learn low-dimensional vertex representations. First, community information reveals an implicit relationship between vertices from a global view, which can be a supplement to local information and help to improve the embedding quality. To obtain the community information, community detection algorithms are utilized as a module and the modularization design makes the model more flexible. Second, deep learning techniques can not only integrate and preserve the information from both local and global views efficiently but also strengthen the robustness of vertex representations. To demonstrate the performance of our model, extensive experiments are conducted in four downstream tasks, namely, network reconstruction, node classification, link prediction, and visualization. The experimental results show that our model outperforms the state-of-the-art approaches to real-world datasets.

关键词： Network embedding community detection variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Gaussian feature learning based on variational autoencoder for improving nonlinear process monitoring

引用

JOURNAL OF PROCESS CONTROL 2019年 75卷 136-155页

作者： Zhang, Zehan Jiang, Teng Zhan, Chengjun Yang, Yupu Shanghai Jiao Tong Univ Dept Automat Minist Educ Syst Control & Informat Proc Key Lab Shanghai 200240 Peoples R China

Deep learning algorithms, especially the autoencoders, have been applied in nonlinear process monitoring recently. However, the features extracted by the autoencoders can hardly follow the Gaussian distribution, consequently, the control limit of the corresponding monitoring statistic can not be determined by an F or chi(2) distribution. Recent improvements in the unsupervised learning domain of deep learning offer opportunities to avoid the problem. In this paper, a novel nonlinear process monitoring method based on variational autoencoder (VAE) is proposed to tackle the Gaussian assumption problem. Due to the Gaussian distribution limitation added in the hidden layer of the VAE, it can not only automatically learn the key features of the nonlinear system, but also learn features that follow the Gaussian distribution. The Gaussian feature representations obtained from VAE are then provided to construct a new statistic H-2 whose control limit can be easily determined by a chi(2) distribution. A nonlinear numerical study and the TE benchmark process have verified the effectiveness of the proposed method. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Nonlinear process monitoring Deep learning variational autoencoder Gaussian feature learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Task with variational autoencoder for Lung Cancer Prognosis on Clinical Data 2020

Multi-Task with Variational Autoencoder for Lung Cancer Prog...

引用

The 9th International Conference on Smart Media and Applications

作者： Thanh-Hung Vo Guee-Samg Lee Hyung-Jeong Yang Sae-Ryung Kang In-Jae Oh Soo-Hyung Kim Chonnam National University S. Korea Chonnam National University Medical School S. Korea

ISBN: (纸本)9781450389259

Due to the increase of lung cancer in Korea, survival analysis for this kind of cancer gets emerging in recent years. Statistical and traditional machine learning methods usually used by medical doctors for this task. Which the success of deep learning in many tasks of computer vision, natural language processing, some studies starting to use DL for this task. Differ than many fields, data in medicine is difficult to collect and process, then the number of samples usually small and a little bit difficult to apply deep learning approach. In this study, we apply variational autoencoder together with the normal task of survival analysis and analysis the effect of it’s it on the target task. The results show that when combine the VAE with the target task, the network architecture less sensitive with the training size, and then could be trained with small number of sample. The limit of this study is using the internal dataset, then it is difficult to compare to the others.

关键词： variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised dimensional sentiment analysis with variational autoencoder

引用

KNOWLEDGE-BASED SYSTEMS 2019年 165卷 30-39页

作者： Wu, Chuhan Wu, Fangzhao Wu, Sixing Yuan, Zhigang Liu, Junxin Huang, Yongfeng Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Microsoft Res Asia Beijing 100084 Peoples R China

Dimensional sentiment analysis (DSA) aims to compute real-valued sentiment scores of texts in multiple dimensions such as valence and arousal. Existing methods for DSA are usually based on supervised learning. However, it is expensive and time-consuming to annotate sufficient samples for training. In this paper, we propose a semi-supervised approach for DSA based on the variational autoencoder model. Our model consists of three modules: an encoding module to encode sentences into hidden vectors, a sentiment prediction module to predict the sentiment scores of sentences, and a decoding module that takes the outputs of the preceding two modules as input and reconstructs the input sentences. In our approach, the sentiment prediction module is encouraged to accurately predict sentiment scores of both labeled and unlabeled texts to help the decoding module reconstruct such texts more accurately. Thus, our approach can exploit useful information in unlabeled data. Experimental results on three benchmark datasets show that our approach can effectively improve the performance of DSA with considerably less labeled data. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Dimensional sentiment analysis variational autoencoder Semi-supervised learning

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：