检索结果-南通市图书馆

Convolutional Multi-Head Self-Attention on Memory for Aspect Sentiment Classification

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2020年第4期7卷 1038-1044页

作者： Yaojie Zhang Bing Xu Tiejun Zhao the laboratory of machine intelligence and translation Department of Computer ScienceHarbin Institute of TechnologyHarbin 150001China

This paper presents a method for aspect based sentiment classification tasks, named convolutional multi-head self-attention memory network(CMA-Mem Net). This is an improved model based on memory networks, and makes it possible to extract more rich and complex semantic information from sequences and aspects. In order to fix the memory network’s inability to capture context-related information on a word-level,we propose utilizing convolution to capture n-gram grammatical information. We use multi-head self-attention to make up for the problem where the memory network ignores the semantic information of the sequence itself. Meanwhile, unlike most recurrent neural network(RNN) long short term memory(LSTM), gated recurrent unit(GRU) models, we retain the parallelism of the network. We experiment on the open datasets Sem Eval-2014 Task 4 and Sem Eval-2016 Task 6. Compared with some popular baseline methods, our model performs excellently.

关键词： Aspect sentiment classification deep learning memory network sentiment analysis(SA)

维普期刊数据库

Toward understanding the role of genomic repeat elements in neurodegenerative diseases

在线全文

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第3期20卷 646-659页

作者： Zhengyu An Aidi Jiang Jingqi Chen Institute of Science and Technology for Brain-Inspired intelligence Fudan UniversityShanghaiChina MOE Frontiers Center for Brain Science Fudan UniversityShanghaiChina MOE Key laboratory of Computational Neuroscience and Brain-Inspired intelligence Fudan UniversityShanghaiChina Zhangjiang Fudan International Innovation Center ShanghaiChina

Neurodegenerative diseases cause great medical and economic burdens for both patients and society;however, the complex molecular mechanisms thereof are not yet well understood. With the development of high-coverage sequencing technology, researchers have started to notice that genomic repeat regions, previously neglected in search of disease culprits, are active contributors to multiple neurodegenerative diseases. In this review, we describe the association between repeat element variants and multiple degenerative diseases through genome-wide association studies and targeted sequencing. We discuss the identification of disease-relevant repeat element variants, further powered by the advancement of long-read sequencing technologies and their related tools, and summarize recent findings in the molecular mechanisms of repeat element variants in brain degeneration, such as those causing transcriptional silencing or RNA-mediated gain of toxic function. Furthermore, we describe how in silico predictions using innovative computational models, such as deep learning language models, could enhance and accelerate our understanding of the functional impact of repeat element variants. Finally, we discuss future directions to advance current findings for a better understanding of neurodegenerative diseases and the clinical applications of genomic repeat elements.

关键词： Alzheimer's disease ataxia deep learning long-read sequencing neurodegeneration neurodegenerative diseases Parkinson's disease repeat element structural variant

维普期刊数据库

Distributed Observer for Full-Measured Nonlinear Systems Based on Knowledge of FMCF

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2025年第1期 69-85页

作者： Haotian Xu Shuai Liu Yueyang Li Ke Li the School of Control Science and Engineering Shandong University and also with Key Laboratory of Machine Intelligence and System Control Ministry of Education IEEE the School of Electrical Engineering University of Jinan

Driven by practical applications, the achievement of distributed observers for nonlinear systems has emerged as a crucial advancement in recent years. However, existing theoretical advancements face certain limitations: They either fail to address more complex nonlinear phenomena, rely on hard-to-verify assumptions, or encounter difficulties in solving system ***, this paper aims to address these challenges by investigating distributed observers for nonlinear systems through the full-measured canonical form(FMCF), which is inspired by full-measured system(FMS) theory. To begin with, this study addresses the fact that the FMCF can only be obtained through the observable canonical form(OCF) in existing FMS *** paper demonstrates that a class of nonlinear systems can directly obtain FMCF through state space equations, independent of OCF. Also, a general method for solving FMCF in such systems is provided. Furthermore, based on the FMCF, A distributed observer is developed for nonlinear systems under two scenarios: Lipschitz conditions and open-loop bounded *** paper establishes their asymptotic omniscience and demonstrates that the designed distributed observer in this study has fewer design parameters and is more convenient to construct than existing approaches. Finally, the effectiveness of the proposed methods is validated through simulation results on Van der Pol oscillators and microgrid systems.

关键词：

Characterization of ultraviolet communication in a mixed aerosol environment

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年第2期 77-84页

作者： ZHAO Taifei SUN Yuxin WANG Wuxin ZHANG Haijun PAN Feixiang WU Hao Artificial intelligence Key laboratory of Sichuan Province Sichuan University of Science & Engineering Faculty of Automation and Information Engineering Xi'an University of Technology

Wireless ultraviolet (UV) has strong scattering characteristics and can communicate through non-direct *** UV signals are transmitted in the atmosphere,they are affected by the absorption and scattering effects of atmospheric particles and atmospheric turbulence,resulting in attenuation of UV signal energy and reduced reliability of the communication *** paper focuses on the channel model of UV non-direct-view single scattering communication,and simulates and analyzes the communication characteristics of UV light in atmospheric turbulence and mixed aerosol environment under horizontal,vertical and oblique range communication *** results show that at equal relative humidity,the wireless UV non-directive scattering communication performance for vertical communication scenarios is more affected by the mixed aerosol environment and the communication performance is worse.

关键词：

同方期刊数据库

SensFL:Privacy-Preserving Vertical Federated Learning with Sensitive Regularization

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2025年第1期142卷 385-404页

作者： Chongzhen Zhang Zhichen Liu Xiangrui Xu Fuqiang Hu Jiao Dai Baigen Cai Wei Wang School of Automation and intelligence Beijing Jiaotong UniversityBeijing100044China Shuohuang Railway Development Co. Ltd.National Energy GroupCangzhou062350China Beijing Key laboratory of Security and Privacy in Intelligent Transportation School of Computer Science and TechnologyBeijing Jiaotong UniversityBeijing100044China

In the realm of Intelligent Railway Transportation Systems,effective multi-party collaboration is crucial due to concerns over privacy and data *** Federated Learning(VFL)has emerged as a promising approach to facilitate such collaboration,allowing diverse entities to collectively enhance machine learning models without the need to share sensitive training ***,existing works have highlighted VFL’s susceptibility to privacy inference attacks,where an honest but curious server could potentially reconstruct a client’s raw data from embeddings uploaded by the *** vulnerability poses a significant threat to VFL-based intelligent railway transportation *** this paper,we introduce SensFL,a novel privacy-enhancing method to against privacy inference attacks in ***,SensFL integrates regularization of the sensitivity of embeddings to the original data into the model training process,effectively limiting the information contained in shared *** reducing the sensitivity of embeddings to the original data,SensFL can effectively resist reverse privacy attacks and prevent the reconstruction of the original data from the *** experiments were conducted on four distinct datasets and three different models to demonstrate the efficacy of *** results show that SensFL can effectively mitigate privacy inference attacks while maintaining the accuracy of the primary learning *** results underscore SensFL’s potential to advance privacy protection technologies within VFL-based intelligent railway systems,addressing critical security concerns in collaborative learning environments.

关键词： Vertical federated learning privacy defenses

Convolutional adaptive denoising autoencoders for hierarchical feature extraction

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2018年第6期12卷 1140-1148页

作者： Qianjun ZHANG Lei ZHANG machine intelligence laboratory College of Computer ScienceSichuan UniversityChengdu 610065China

Convolutional neural networks (CNNs) are typical structures for deep learning and are widely used in image recognition and classification. However, the random initialization strategy tends to become stuck at local plateaus or even diverge, which results in rather unstable and ineffective solutions in real applications. To address this limitation, we propose a hybrid deep learning CNN-AdapDAE model, which applies the features learned by the AdapDAE algorithm to initialize CNN filters and then train the improved CNN for classification tasks. In this model, AdapDAE is proposed as a CNN pre-training procedure, which adaptively obtains the noise level based on the principle of annealing, by starting with a high level of noise and lowering it as the training progresses. Thus, the features learned by AdapDAE include a combination of features at different levels of granularity. Extensive experimental results on STL-10, CIFAR-10, andMNIST datasets demonstrate that the proposed algorithm performs favorably compared to CNN (random filters), CNNAE (pre-training filters by autoencoder), and a few other unsupervised feature learning methods.

关键词： convolutional neural networks annealing denoising autoencoder adaptive noise level pre-training

A feature-wise attention module based on the difference with surrounding features for convolutional neural networks

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第6期17卷 77-86页

作者： Shuo TAN Lei ZHANG Xin SHU Zizhou WANG machine intelligence laboratory College of Computer ScienceSichuan UniversityChengdu 610065China

Attention mechanism has become a widely researched method to improve the performance of convolutional neural networks(CNNs).Most of the researches focus on designing channel-wise and spatial-wise attention modules but neglect the importance of unique information on each feature,which is critical for deciding both“what”and“where”to *** this paper,a feature-wise attention module is proposed,which can give each feature of the input feature map an attention ***,the module is based on the well-known surround suppression in the discipline of neuroscience,and it consists of two sub-modules,Minus-Square-Add(MSA)operation and a group of learnable non-linear mapping *** MSA imitates the surround suppression and defines an energy function which can be applied to each feature to measure its *** group of non-linear functions refines the energy calculated by the MSA to more reasonable *** these two sub-modules,feature-wise attention can be well ***,due to the simple structure and few parameters of the two sub-modules,the proposed module can easily be almost integrated into any *** verify the performance and effectiveness of the proposed module,several experiments were conducted on the Cifar10,Cifar100,Cinic10,and Tiny-ImageNet datasets,*** experimental results demonstrate that the proposed module is flexible and effective for CNNs to improve their performance.

关键词： feature-wise attention surround suppression image classification convolutional neural networks

维普期刊数据库

Generating Basic Unit Movements with Conditional Generative Adversarial Networks

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2019年第6期28卷 1099-1107页

作者： LUO Dingsheng NIE Mengxi WU Xihong Key laboratory of machine Perception (Ministry of Education) Speech and Hearing Research CenterDepartment of Machine Intelligence School of EECS Peking University

Arm motion control is fundamental for robot accomplishing complicated manipulation *** movements can be organized by configuring a series of motion units. Our work aims at equipping the robot with the ability to carry out Basic unit movements(BUMs), which are used to constitute various motion sequences so that the robot can drive its hand to a desired position. With the definition of BUMs, we explore a learning approach for the robot to develop such an ability by leveraging deep learning technique. In order to generate the BUM regarding to the current arm state,an internal inverse model is developed. We propose to use Conditional generative adversarial networks(CGANs) to establish the inverse model to generate the BUMs. The experimental results on a humanoid robot PKU-HR6.0Ⅱ illustrate that CGANs could successfully generate multiple solutions given a BUM, and these BUMs can be used to constitute further reaching movement effectively.

关键词： Arm motion control Basic unit movements Deep learning CGANs Inverse model Humanoids

Integrated Chinese Segmentation, Parsing and Named Entity Recognition

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2018年第4期27卷 756-760页

作者： LI Dongchen ZHANG Xiantao WU Xihong Key laboratory of machine Perception and intelligence Speech and Hearing Research Center Peking University

Segmentation, named entity recognition and parsing are standalone techniques in natural language processing community, and their annotations are inconsistent. However, the joint output is needed in some practical use, and they rely on the result of each other to make more concise output. A unified model is learned to resolve these three tasks simultaneously. At the training stage, the joint annotation of the three tasks are employed to learn a unified model. At the decoding stage, the three tasks are carried out on a given text to provide a consistent *** results demonstrate the higher performance for each task and verify the benefits of the unified framework.

关键词： Parsing Joint representation Named entity recognition