检索结果-南通市图书馆

Robust cooperative multi-agent reinforcement learning via multi-view message certification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 131-145页

作者： Lei YUAN Tao JIANG Lihe LI Feng CHEN Zongzhang ZHANG Yang YU National Key Laboratory for Novel software Technology Nanjing University Polixir Technologies

Many multi-agent scenarios require message sharing among agents to promote coordination,hastening the robustness of multi-agent communication when policies are deployed in a message perturbation environment. Major relevant studies tackle this issue under specific assumptions, like a limited number of message channels would sustain perturbations, limiting the efficiency in complex scenarios. In this paper,we take a further step in addressing this issue by learning a robust cooperative multi-agent reinforcement learning via multi-view message certification, dubbed CroMAC. Agents trained under CroMAC can obtain guaranteed lower bounds on state-action values to identify and choose the optimal action under a worst-case deviation when the received messages are perturbed. Concretely, we first model multi-agent communication as a multi-view problem, where every message stands for a view of the state. Then we extract a certificated joint message representation by a multi-view variational autoencoder(MVAE) that uses a product-of-experts inference network. For the optimization phase, we do perturbations in the latent space of the state for a certificate guarantee. Then the learned joint message representation is used to approximate the certificated state representation during training. Extensive experiments in several cooperative multi-agent benchmarks validate the effectiveness of the proposed CroMAC.

关键词： multi-agent reinforcement learning robust communication adversarial training multi-view learning message certification

Dynamic adaptive spatio-temporal graph network for COVID-19 forecasting

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第3期9卷 769-786页

作者： Xiaojun Pu Jiaqi Zhu Yunkun Wu Chang Leng Zitong Bo Hongan Wang Institute of software Chinese Academy of Sciences BeijingChina Ecovacs Robotics Co. Ltd.SuzhouJiangsuChina Automotive software Innovation Center ChongqingChina

Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 ***,in previous deep learning models for epidemic forecasting,spatial and temporal variations are captured separately.A unified model is developed to cover all spatio-temporal ***,this measure is insufficient for modelling the complex spatio-temporal relations of infectious disease transmission.A dynamic adaptive spatio-temporal graph network(DASTGN)is proposed based on attention mechanisms to improve prediction *** DASTGN,complex spatio-temporal relations are depicted by adaptively fusing the mixed space-time effects and dynamic space-time dependency *** dual-scale model considers the time-specific,space-specific,and direct effects of the propagation process at the fine-grained ***,the model characterises impacts from various space-time neighbour blocks under time-varying interventions at the coarse-grained *** performance comparisons on the three COVID-19 datasets reveal that DASTGN achieves state-of-the-art results with a maximum improvement of 17.092%in the root mean-square error and 11.563%in the mean absolute *** results indicate that the mechanisms of designing DASTGN can effectively detect some spreading characteristics of *** spatio-temporal weight matrices learned in each proposed module reveal diffusion patterns in various *** conclusion,DASTGN has successfully captured the dynamic spatio-temporal variations of COVID-19,and considering multiple dynamic space-time relationships is essential in epidemic forecasting.

关键词： adaptive COVID-19 forecasting dynamic intervention spatio-temporal graph neural networks

Performance of Text-Independent Automatic Speaker Recognition on a Multicore System

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第2期29卷 447-456页

作者： Rand Kouatly Talha Ali Khan Faculty of Tech and software Engineering University of Europe for Applied SciencesPotsdam 14469Germany

This paper studies a high-speed text-independent Automatic Speaker Recognition(ASR)algorithm based on a multicore system's Gaussian Mixture Model(GMM).The high speech is achieved using parallel implementation of the feature's extraction and aggregation methods during training and testing *** memory parallel programming techniques using both OpenMP and PThreads libraries are developed to accelerate the code and improve the performance of the ASR *** experimental results show speed-up improvements of around 3.2 on a personal laptop with Intel i5-6300HQ(2.3 GHz,four cores without hyper-threading,and 8 GB of RAM).In addition,a remarkable 100%speaker recognition accuracy is achieved.

关键词： Automatic Speaker Recognition(ASR) Gaussian Mixture Model(GMM) shared memory parallel programming PThreads OpenMP

LAMDA-SSL:a comprehensive semi-supervised learning toolkit

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第1期67卷 306-307页

作者： Lin-Han JIA Lan-Zhe GUO Zhi ZHOU Yu-Feng LI National Key Laboratory for Novel software Technology Nanjing University

Machine learning, particularly deep learning, has achieved remarkable success across a wide range of tasks. However,most of these tasks demand a substantial amount of labeled training data, which can be challenging to obtain in many real-world applications due to difficulties, costs, or time constraints associated with labeling. In this context,semi-supervised learning (SSL) has emerged as a promising paradigm to alleviate the dependency on large labeled datasets by harnessing the power of unlabeled data [1–3].

关键词：

Random Subspace Sampling for Classification with Missing Data

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2024年第2期39卷 472-486页

作者：曹云浩吴建鑫 State Key Laboratory for Novel software Technology Nanjing UniversityNanjing 210093China

Many real-world datasets suffer from the unavoidable issue of missing values,and therefore classification with missing data has to be carefully handled since inadequate treatment of missing values will cause large *** this paper,we propose a random subspace sampling method,RSS,by sampling missing items from the corresponding feature histogram distributions in random subspaces,which is effective and efficient at different levels of missing *** most established approaches,RSS does not train on fixed imputed ***,we design a dynamic training strategy where the filled values change dynamically by resampling during ***,thanks to the sampling strategy,we design an ensemble testing strategy where we combine the results of multiple runs of a single model,which is more efficient and resource-saving than previous ensemble ***,we combine these two strategies with the random subspace method,which makes our estimations more robust and *** effectiveness of the proposed RSS method is well validated by experimental studies.

关键词： missing data random subspace neural network ensemble learning

A Comprehensive Survey on Deep Learning Multi-Modal Fusion:Methods,Technologies and Applications

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第7期80卷 1-35页

作者： Tianzhe Jiao Chaopeng Guo Xiaoyue Feng Yuming Chen Jie Song software College Northeastern UniversityShenyang110819China

Multi-modal fusion technology gradually become a fundamental task in many fields,such as autonomous driving,smart healthcare,sentiment analysis,and human-computer *** is rapidly becoming the dominant research due to its powerful perception and judgment *** complex scenes,multi-modal fusion technology utilizes the complementary characteristics of multiple data streams to fuse different data types and achieve more accurate ***,achieving outstanding performance is challenging because of equipment performance limitations,missing information,and data *** paper comprehensively reviews existing methods based onmulti-modal fusion techniques and completes a detailed and in-depth *** to the data fusion stage,multi-modal fusion has four primary methods:early fusion,deep fusion,late fusion,and hybrid *** paper surveys the three majormulti-modal fusion technologies that can significantly enhance the effect of data fusion and further explore the applications of multi-modal fusion technology in various ***,it discusses the challenges and explores potential research ***-modal tasks still need intensive study because of data heterogeneity and *** complementary information and eliminating redundant information between modalities is critical in multi-modal *** data fusion methods may introduce extra noise and lead to worse *** paper provides a comprehensive and detailed summary in response to these challenges.

关键词： Multi-modal fusion representation translation alignment deep learning comparative analysis

Foundation models meet visualizations: Challenges andopportunities

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2024年第3期10卷 399-424页

作者： Weikai Yang Mengchen Liu Zheng Wang Shixia Liu School of software Tsinghua UniversityBeijing 100084China Microsoft Redmond 98052USA

Recent studies have indicated that foundation models, such as BERT and GPT, excel atadapting to various downstream tasks. This adaptability has made them a dominant force in buildingartiﬁcial intelligence (AI) systems. Moreover, a newresearch paradigm has emerged as visualizationtechniques are incorporated into these models. Thisstudy divides these intersections into two researchareas: visualization for foundation model (VIS4FM)and foundation model for visualization (FM4VIS).In terms of VIS4FM, we explore the primary roleof visualizations in understanding, reﬁning, and evaluating these intricate foundation models. VIS4FMaddresses the pressing need for transparency, explainability, fairness, and robustness. Conversely, in termsof FM4VIS, we highlight how foundation models canbe used to advance the visualization ﬁeld itself. Theintersection of foundation models with visualizations ispromising but also introduces a set of challenges. Byhighlighting these challenges and promising opportunities, this study aims to provide a starting point forthe continued exploration of this research avenue.

关键词： visualization artiﬁcial intelligence(AI) machine learning foundation models visualization for foundation model(VIS4FM) foundation model for visualization(FM4VIS)

Improving actionable warning identification via the refined warning-inducing context representation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第5期67卷 321-322页

作者： Xiuting GE Chunrong FANG Xuanye LI Quanjun ZHANG Jia LIU Zhihong ZHAO Zhenyu CHEN State Key Laboratory for Novel software Technology Nanjing University

Static analysis tools(SATs) have shown potential ability in software quality assurance [1]. However, SATs report an overwhelming number of warnings, where most warnings are unactionable ones(i.e., warnings that are not acted on or fixed by developers). It is not a trivial task for developers to find actionable warnings(i.e., warnings that are acted on and fixed by developers) in all reported warnings. Hence,the excessive unactionable warnings seriously impede the usability of SATs [2].

关键词：

Machine-Learning Based Packet Switching Method for Providing Stable High-Quality Video Streaming in Multi-Stream Transmission

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第3期78卷 4153-4176页

作者： Yumin Jo Jongho Paik Major in software Fusion Department of ComputerSeoulWomen’s UniversitySeoul01797South Korea Department of software Convergence Seoul Women’s UniversitySeoul01797South Korea

Broadcasting gateway equipment generally uses a method of simply switching to a spare input stream when a failure occurs in a main input ***,when the transmission environment is unstable,problems such as reduction in the lifespan of equipment due to frequent switching and interruption,delay,and stoppage of services may ***,applying a machine learning(ML)method,which is possible to automatically judge and classify network-related service anomaly,and switch multi-input signals without dropping or changing signals by predicting or quickly determining the time of error occurrence for smooth stream switching when there are problems such as transmission errors,is *** this paper,we propose an intelligent packet switching method based on the ML method of classification,which is one of the supervised learning methods,that presents the risk level of abnormal multi-stream occurring in broadcasting gateway equipment based on ***,we subdivide the risk levels obtained from classification techniques into probabilities and then derive vectorized representative values for each attribute value of the collected input data and continuously update *** obtained reference vector value is used for switching judgment through the cosine similarity value between input data obtained when a dangerous situation *** the broadcasting gateway equipment to which the proposed method is applied,it is possible to perform more stable and smarter switching than before by solving problems of reliability and broadcasting accidents of the equipment and can maintain stable video streaming as well.

关键词： Broadcasting and communication convergence multi-stream packet switching advanced television systems committee standard 3.0(ATSC 3.0) data pre-processing machine learning cosine similarity