检索结果-内蒙古大学图书馆

20th IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Zhang, Lu Yu, Xiaowei Lyu, Yanjun Liu, Tianming Zhu, Dajiang Univ Texas Arlington Comp Sci & Engn Arlington TX 76019 USA Univ Georgia Comp Sci Athens GA USA

ISBN: (纸本)9781665473583

Mild cognitive impairment (MCI) is a high-risk dementia condition which progresses to probable Alzheimer's disease (AD) at approximately 10% to 15% per year. Characterization of group-level differences between two sub-types of MCI - stable MCI (sMCI) and progressive MCI (pMCI) is the key step to understand the mechanisms of MCI progression and enable possible delay of transition from MCI to AD. Functional connectivity (FC) is considered as a promising way to study MCI progression since which may show alterations even in preclinical stages and provide substrates for AD progression. However, the representative FC patterns during AD development for different clinical groups, especially for sMCI and pMCI, have been understudied. In this work, we integrated autoencoder and multi-class classification into a single deep model and successfully learned a set of clinical group related feature vectors. Specifically, we trained two non-linear mappings which realized the mutual transformations between the original FC space and the feature space. By mapping the learned clinical group related feature vectors to the original FC space, representative FCs were constructed for each group. Moreover, based on these feature vectors, our model achieves a high classification accuracy - 68% for multi-class classification (NC vs SMC vs sMCI vs pMCI vs AD). Code has been released(1).

关键词： MCI progression Representative group related FC deep autoencoder

来源：评论

学校读者我要写书评

暂无评论

deep Heterogeneous autoencoders for Collaborative Filtering 18

Deep Heterogeneous Autoencoders for Collaborative Filtering

引用

18th IEEE International Conference on Data Mining Workshops (ICDMW)

作者： Li, Tianyu Ma, Yukun Xu, Jiu Stenger, Bjorn Liu, Chen Hirate, Yu Rakuten Inst Technol Tokyo Japan Nanyang Technol Univ Singapore Singapore

ISBN: (纸本)9781538691595

This paper leverages heterogeneous auxiliary information to address the data sparsity problem of recommender systems. We propose a model that learns a shared feature space from heterogeneous data, such as item descriptions, product tags and online purchase history, to obtain better predictions. Our model consists of autoencoders, not only for numerical and categorical data, but also for sequential data, which enables capturing user tastes, item characteristics and the recent dynamics of user preference. We learn the autoencoder architecture for each data source independently in order to better model their statistical properties. Our evaluation on two MovieLens datasets and an e-commerce dataset shows that mean average precision and recall improve over state-of-the-art methods.

关键词： deep autoencoder Heterogeneous Data Shared Representation Sequential Data Modeling Collaborative Filtering

来源：评论

学校读者我要写书评

暂无评论

Regularized Nonlinear Discriminant Analysis An Approach to Robust Dimensionality Reduction for Data Visualization 12

Regularized Nonlinear Discriminant Analysis <i>An Approach t...

引用

12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP)

作者： Becker, Martin Lippel, Jens Stuhlsatz, Andre Univ Appl Sci Dusseldorf Fac Mech & Proc Engn Munsterstr 156 D-40476 Dusseldorf Germany Univ Appl Sci Dusseldorf Fac Elect Engn & Informat Technol Dusseldorf Germany Univ Appl Sci Dusseldorf Fac Media Dusseldorf Germany

ISBN: (纸本)9789897582288

We present a novel approach to dimensionality reduction for data visualization that is a combination of two deep neural networks (DNNs) with different objectives. One is a nonlinear generalization of Fisher's linear discriminant analysis (LDA). It seeks to improve the class separability in the desired feature space, which is a natural strategy to obtain well-clustered visualizations. The other DNN is a deep autoencoder. Here, an encoding and a decoding DNN are optimized simultaneously with respect to the decodability of the features obtained by encoding the data. The idea behind the combined DNN is to use the generalized discriminant analysis as an encoding DNN and to equip it with a regularizing decoding DNN. Regarding data visualization, a well-regularized DNN guarantees to learn sufficiently similar data visualizations for different sets of samples that represent the data approximately equally good. Clearly, such a robustness against fluctuations in the data is essential for real-world applications. We therefore designed two extensive experiments that involve simulated fluctuations in the data. Our results show that the combined DNN is considerably more robust than the generalized discriminant analysis alone. Moreover, we present reconstructions that reveal how the visualizable features look like back in the original data space.

关键词： High-dimensional Data Dimensionality Reduction Data Visualization Discriminant Analysis GerDA deep autoencoder deep Neural Networks Regularization Machine Learning

来源：评论

学校读者我要写书评

暂无评论

deep Optimisation: Multi-scale Evolution by Inducing and Searching in deep Representations 24th

Deep Optimisation: Multi-scale Evolution by Inducing and Sea...

引用

24th International Conference on the Applications of Evolutionary Computation (EvoApplications) Held as Part of EvoStar Conference

作者： Caldwell, Jamie Knowles, Joshua Thies, Christoph Kubacki, Filip Watson, Richard Univ Southampton Agents Interact & Complex AIC Res Grp Southampton SO17 1BJ Hants England Invenia Labs Cambridge CB2 1AW England

ISBN: (纸本)9783030726980;9783030726997

The ability of evolutionary processes to innovate and scale up over long periods of time, observed in nature, remains a central mystery in evolutionary biology, and a challenge for algorithm designers to emulate and explain in evolutionary computation (EC). The Major Transitions in Evolution is a compelling theory that explains evolvability through a multi-scale process whereby individuality (and hence selection and variation) is continually revised by the formation of associations between formerly independent entities, a process still not fully explored in EC. deep Optimisation (DO) is a new type of model-building optimization algorithm (MBOA) that exploits deep learning methods to enable multi-scale optimization. DO uses an autoencoder model to induce a multi-level representation of solutions, capturing the relationships between the lower-level units that contribute to the quality of a solution. Variation and selection are then performed within the induced representations, causing model-informed changes to multiple solution variables simultaneously. Here, we first show that DO has impressive performance compared with other leading MBOAs (and other rival methods) on multiple knapsack problems, a standard combinatorial optimization problem of general interest. Going deeper, we then carry out a detailed investigation to understand the differences between DO and other MBOAs, identifying key problem characteristics where other MBOAs are afflicted by exponential running times, and DO is not. This study serves to concretize our understanding of the Major Transitions theory, and why that leads to evolvability, and also provides a strong motivation for further investigation of deep learning methods in optimization.

关键词： Model-Building Optimisation Algorithms deep autoencoder Multi-scale search Problem structure

来源：评论

学校读者我要写书评

暂无评论

Audio/Speech Coding Based on the Perceptual Sparse Representation of the Signal with DAE Neural Network Quantizer and Near-End Listening Enhancement 11th

Audio/Speech Coding Based on the Perceptual Sparse Represent...

引用

11th International Conference on Multimedia and Network Information Systems (MISSI)

作者： Herasimovich, Vadzim Petrovsky, Alexey Avramov, Vladislav Petrovsky, Alexander Belarusian State Univ Informat & Radioelect Minsk BELARUS

ISBN: (纸本)9783319986784;9783319986777

The article presents universal sound coding framework. The encoding algorithm works at the junction of the transform and parametric approaches. The input signal goes through the decorrelation transform - wavelet packet decomposition (WPD) that is tuned to perceptual structure of the analyzed signal with the psychoacoustic modelling. The parameterization stage is the matching pursuit (MP) algorithm with the WPD based dictionaries. Selected parameters then quantized and coded for the transmission to the decoder. Quantization algorithm based on the artificial neural networks with a deep autoencoder (DAE) architecture is presented. The decoding part of the coder has the listening enhancement function. Since the decoder input is the parameters that are distributed in the subbands it is only necessary to decompose the noise signal with the corresponding filterbank and estimate the subband gain factor based on this information. The results of the conducted research like objective difference grade and performance demonstration are shown.

关键词： Audio/speech coding Wavelet packet Matching pursuit Psychoacoustics Neural networks deep autoencoder Listening enhancement

来源：评论

学校读者我要写书评

暂无评论

Integrating deep Learning and Reinforcement Learning for Enhanced Financial Risk Forecasting in Supply Chain Management

引用

JOURNAL OF THE KNOWLEDGE ECONOMY 2024年第4期15卷 20091-20110页

作者： Cui, Yuanfei Yao, Fengtong Inner Mongolia Agr Univ Coll Econ & Management Hohhot 010018 Peoples R China

In today's dynamic business landscape, the integration of supply chain management and financial risk forecasting is imperative for sustained success. This research paper introduces a groundbreaking approach that seamlessly merges deep autoencoder (DAE) models with reinforcement learning (RL) techniques to enhance financial risk forecasting within the realm of supply chain management. The primary objective of this research is to optimize financial decision-making processes by extracting key feature representations from financial data and leveraging RL for decision optimization. To achieve this, the paper presents the PSO-SDAE model, a novel and sophisticated approach to financial risk forecasting. By incorporating advanced noise reduction features and optimization algorithms, the PSO-SDAE model significantly enhances the accuracy and reliability of financial risk predictions. Notably, the PSO-SDAE model goes beyond traditional forecasting methods by addressing the need for real-time decision-making in the rapidly evolving landscape of financial risk management. This is achieved through the utilization of a distributed RL algorithm, which expedites the processing of supply chain data while maintaining both efficiency and accuracy. The results of our study showcase the exceptional precision of the PSO-SDAE model in predicting financial risks, underscoring its efficacy for proactive risk management within supply chain operations. Moreover, the augmented processing speed of the model enables real-time analysis and decision-making - a critical capability in today's fast-paced business environment.

关键词： Financial risk forecasting Supply chain management deep autoencoder Reinforcement learning Data mining

来源：评论

学校读者我要写书评

暂无评论

deep Optimisation: Transitioning the Scale of Evolutionary Search by Inducing and Searching in deep Representations

引用

SN Computer Science 2022年第3期3卷 253页

作者： Caldwell, Jamie Knowles, Joshua Thies, Christoph Kubacki, Filip Watson, Richard Agents Interaction and Complexity (AIC) Research Group Southampton University Southampton SO17 1BJ United Kingdom School of Computer Science University of Birmingham Birmingham B15 2TT United Kingdom Invenia Labs Cambridge CB2 1AW United Kingdom

We investigate the optimisation capabilities of an algorithm inspired by the Evolutionary Transitions in Individuality. In these transitions, the natural evolutionary process is repeatedly rescaled through successive levels of biological organisation. Each transition creates new higher-level evolutionary units that combine multiple units from the level below. We call the algorithm deep Optimisation (DO) to recognise both its use of deep learning methods and the multi-level rescaling of biological evolutionary processes. The evolutionary model used in DO is a simple hill-climber, but, as higher-level representations are learned, the hill-climbing process is repeatedly rescaled to operate in successively higher-level representations. The transition process is based on a deep learning neural network (NN), specifically a deep auto-encoder. Our experiments with DO start with a study using the NP-hard problem, multiple knapsack (MKP). Comparing with state-of-the-art model-building optimisation algorithms (MBOAs), we show that DO finds better solutions to MKP instances and does so without using a problem-specific repair operator. A second, much more in-depth investigation uses a class of configurable problems to understand more precisely the distinct problem characteristics that DO can solve that other MBOAs cannot. Specifically, we observe a polynomial vs exponential scaling distinction where DO is the only algorithm to show polynomial scaling for all problems. We also demonstrate that some problem characteristics need a deep network in DO. In sum, our findings suggest that the use of deep learning principles have significant untapped potential in combinatorial optimisation. Moreover, we argue that natural evolution could be implementing something like DO, and the evolutionary transitions in individuality are the observable result. © 2022, The Author(s).

关键词： deep autoencoder Model-building optimisation algorithms Multi-scale search Problem structure

来源：评论

学校读者我要写书评

暂无评论

deep Streaming Graph Representations 18th

Deep Streaming Graph Representations

引用

18th International Conference on Computational Science (ICCS)

作者： Lei, Minglong Shi, Yong Li, Peijia Niu, Lingfeng Univ Chinese Acad Sci Sch Comp & Control Engn Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Univ Nebraska Coll Informat Sci & Technol Omaha NE 68182 USA

ISBN: (纸本)9783319937137;9783319937120

Learning graph representations generally indicate mapping the vertices of a graph into a low-dimension space, in which the proximity of the original data can be preserved in the latent space. However, traditional methods that based on adjacent matrix suffered from high computational cost when encountering large graphs. In this paper, we propose a deep autoencoder driven streaming methods to learn low-dimensional representations for graphs. The proposed method process the graph as a data stream fulfilled by sampling strategy to avoid straight computation over the large adjacent matrix. Moreover, a graph regularized deep autoencoder is employed in the model to keep different aspects of proximity information. The regularized framework is able to improve the representation power of learned features during the learning process. We evaluate our method in clustering task by the features learned from our model. Experiments show that the proposed method achieves competitive results comparing with methods that directly apply deep models over the complete graphs.

关键词： Streaming methods Representation learning deep autoencoder Graph regularization

来源：评论

学校读者我要写书评

暂无评论

SEPARATION OF METABOLITE AND MACROMOLECULE SIGNALS FOR ¹H-MRSI USING LEARNED NONLINEAR MODELS 17

SEPARATION OF METABOLITE AND MACROMOLECULE SIGNALS FOR <SUP>...

引用

IEEE 17th International Symposium on Biomedical Imaging (ISBI)

作者： Li, Yahang Wang, Zepeng Lam, Fan Univ Illinois Dept Bioengn Champaign IL 61820 USA Univ Illinois Beckman Inst Adv Sci & Technol Champaign IL 61820 USA

ISBN: (纸本)9781538693308

This paper presents a novel method to reconstruct and separate metabolite and macromolecule (MM) signals in H-1 magnetic resonance spectroscopic imaging (MRSI) data using learned nonlinear models. Specifically, deep autoencoder (DAE) networks were constructed and trained to learn the nonlinear low-dimensional manifolds, where the metabolite and MM signals reside individually. A regularized reconstruction formulation is proposed to integrate the learned models with signal encoding model to reconstruct and separate the metabolite and MM components. An efficient algorithm was developed to solve the associated optimization problem. The performance of the proposed method has been evaluated using simulation and experimental H-1-MRSI data. Efficient low-dimensional signal representation of the learned models and improved metabolite/MM separation over the standard parametric fitting based approach have been demonstrated.

关键词： proton magnetic resonance spectroscopic imaging deep learning deep autoencoder regularization ADMM

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Representation for Multi-view Clustering: From Intra-sample to Intra-view to Inter-view 22

Hierarchical Representation for Multi-view Clustering: From ...

引用

31st ACM International Conference on Information and Knowledge Management (CIKM)

作者： Yang, Jing-Hua Chen, Chuan Dai, Hong-Ning Ding, Meng Fu, Le-Le Zheng, Zibin Macau Univ Sci & Technol Macau Peoples R China Sun Yat Sen Univ Guangzhou Peoples R China Hong Kong Baptist Univ Hong Kong Peoples R China Southwest Jiaotong Univ Chengdu Peoples R China

ISBN: (纸本)9781450392365

Multi-view clustering (MVC) aims at exploiting the consistent features within different views to divide samples into different clusters. Existing subspace-based MVC algorithms usually assume linear subspace structures and two-stage similarity matrix construction strategies, thereby posing challenges in imprecise low-dimensional subspace representation and inadequacy of exploring consistency. This paper presents a novel hierarchical representation for MVC method via the integration of intra-sample, intra-view, and interview representation learning models. In particular, we first adopt the deep autoencoder to adaptively map the original high-dimensional data into the latent low-dimensional representation of each sample. Second, we use the self-expression of the latent representation to explore the global similarity between samples of each view and obtain the subspace representation coefficients. Third, we construct the third-order tensor by arranging multiple subspace representation matrices and impose the tensor low-rank constraint to sufficiently explore the consistency among views. Being incorporated into a unified framework, these three models boost each other to achieve a satisfactory clustering result. Moreover, an alternating direction method of multipliers algorithm is developed to solve the challenging optimization problem. Extensive experiments on both simulated and real-world multi-view datasets show the superiority of the proposed method over eight state-of-the-art baselines.

关键词： Multi-view clustering hierarchical representation tensor low-rank constraint deep autoencoder alternating direction method of multipliers

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：