检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Song, Alexander Kottapalli, Sai Nikhilesh Murty Goyal, Rahul Schölkopf, Bernhard Fischer, Peer Max Planck Institute for Medical Research Heidelberg Germany Institute for Molecular Systems Engineering and Advanced Materials Universität Heidelberg Heidelberg Germany Max Planck Institute for Intelligent Systems Tübingen Germany Department of Computer Science ETH Zürich Zürich Switzerland

Optical approaches have made great strides towards the goal of high-speed, energy-efficient computing necessary for modern deep learning and AI applications. Read-in and read-out of data, however, limit the overall performance of existing approaches. This study introduces a multilayer optoelectronic computing framework that alternates between optical and optoelectronic layers to implement matrix-vector multiplications and rectified linear functions, respectively. Our framework is designed for real-time, parallelized operations, leveraging 2D arrays of LEDs and photodetectors connected via independent analog electronics. We experimentally demonstrate this approach using a system with a three-layer network with two hidden layers and operate it to recognize images from the MNIST database with a recognition accuracy of 92% and classify classes from a nonlinear spiral data with 86% accuracy. By implementing multiple layers of a deep neural network simultaneously, our approach significantly reduces the number of read-ins and read-outs required and paves the way for scalable optical accelerators requiring ultra low energy. Copyright © 2024, The Authors. All rights reserved.

关键词： Multilayers

来源：评论

学校读者我要写书评

暂无评论

Hypergraph-based Self-supervised Multi-channel Network for Drug-target Interaction Prediction

Hypergraph-based Self-supervised Multi-channel Network for D...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiaoting Zeng Yu Liang Peng Yang Weilin Chen Baiying Lei School of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Biomedical Engineering Shenzhen University Shenzhen China Institute of Biological Therapy Shenzhen University Medical School Shenzhen University Shenzhen China School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Drug-target interaction (DTI) prediction is vital for drug discovery and repurposing. Hypergraph is utilized in DTI prediction for modeling higher-order relationships in biomedical networks. Although the strategies of modeling hypergraph-based drug-related interactions with multi-channel and utilizing self-supervised learning task to improve DTI prediction performance have been proven promising, current researches fail to effectively model feature interaction across different channels and fully exploit cross-channel information for self-supervised task. In this study, we propose a hypergraph-based self-supervised multi-channel interaction framework HSMI-DTI for DTI prediction. HSMI-DTI aims to extract hypergraph features effectively and model cross-channel correlations, leveraging hierarchical self-supervised learning to uncover the discover correlations between different channels. We compare HSMI-DTI with advanced baselines, and experiment results show our model outperforms existing methods, thereby optimizing DTI prediction performance.

关键词： Correlation Biological system modeling Self-supervised learning Predictive models Feature extraction Heterogeneous networks Drug discovery Bioinformatics Diffusion tensor imaging

来源：评论

学校读者我要写书评

暂无评论

Microsaccade-inspired Event Camera for Robotics

arXiv

引用

arXiv 2024年

作者： He, Botao Wang, Ze Zhou, Yuan Chen, Jingxi Singh, Chahat Deep Li, Haojia Gao, Yuman Shen, Shaojie Wang, Kaiwei Cao, Yanjun Xu, Chao Aloimonos, Yiannis Gao, Fei Fermüller, Cornelia Department of Computer Science University of Maryland College ParkMD20742 United States College of Control Science and Engineering Zhejiang University Hangzhou China Huzhou Institute of Zhejiang University Huzhou China College of Optical Science and Engineering Zhejiang University Hangzhou China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Institute for Advance Computer Studies University of Maryland College ParkMD20742 United States Institute for Systems Research University of Maryland College ParkMD20742 United States

Neuromorphic vision sensors or event cameras have made the visual perception of extremely low reaction time possible, opening new avenues for high-dynamic robotics applications. These event cameras' output is dependent on both motion and texture. However, the event camera fails to capture object edges that are parallel to the camera motion. This is a problem intrinsic to the sensor and therefore challenging to solve algorithmically. Human vision deals with perceptual fading using the active mechanism of small involuntary eye movements - the most prominent ones called microsaccades. By moving the eyes constantly and slightly during fixation, microsaccades can substantially maintain texture stability and persistence. Inspired by microsaccades, we designed an event-based perception system capable of simultaneously maintaining low reaction time and stable texture. In this design, a rotating wedge prism was mounted in front of the aperture of an event camera to redirect light and trigger events. The geometrical optics of the rotating wedge prism allows for algorithmic compensation of the additional rotational motion, resulting in a stable texture appearance and high informational output independent of external motion. The hardware device and software solution are integrated into a system, which we call Artificial MIcrosaccade-enhanced EVent camera (AMI-EV). Benchmark comparisons validate the superior data quality of AMI-EV recordings in scenarios where both standard cameras and event cameras fail to deliver. Various real-world experiments demonstrate the potential of the system to facilitate robotics perception both for low-level and high-level vision tasks. © 2024, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Large Language Models (LLMs) Inference Offloading and Resource Allocation in Cloud-Edge Networks: An Active Inference Approach

Large Language Models (LLMs) Inference Offloading and Resour...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Jingcheng Fang Ying He F. Richard Yu Jianqiang Li Victor C. Leung Shenzhen Key Lab of Digital & Intelligent Technologies & Systems College of Computer Science and Software Engineering Shenzhen University China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China

As the research and applications of large language model (LLM) become increasingly sophisticated, it is difficult for resource-limited mobile terminals to run large-model inference tasks efficiently. Traditional deep reinforcement learning (DRL) based approaches have been used to offload LLM inference tasks to servers. However, existing solutions suffer from data inefficiency, insensitivity to latency requirements, and non-adaptability to task load variations. In this paper, we propose an active inference with rewardless guidance algorithm using expected future free energy for offloading decisions and allocating resources for the LLM inference task offloading and resource allocation problem of cloud-edge networks systems. Experimental results show that our proposed method has superior performance over mainstream DRLs, improves in data utilization efficiency, and is more adaptable to changing task load scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Self-Evolving Framework for Multi-Agent Medical Consultation Based on Large Language Models

A Self-Evolving Framework for Multi-Agent Medical Consultati...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kai Chen Ji Qi Jing Huo Pinzhuo Tian Fanyu Meng Xi Yang Yang Gao State Key Laboratory for Novel Software Technology Nanjing University Nanjing China China Mobile (Suzhou) Software Technology Co. Ltd. Suzhou China School of Computer Engineering and Science Shanghai University Shanghai China China Mobile Research Institute Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We propose a multi-agent approach (SeM-Agents) based on large language models for medical consultations. This framework incorporates various doctor roles and auxiliary roles, with agents communicating through natural language. Using a residual structure, the system conducts multi-round medical consultations based on the patient’s treatment background and symptoms. In the final summary and output stage of the consultation, it utilizes two experience databases—the Correct Consultation Experience Database and the Chain of Thought (CoT) Experience Database—which evolve with accumulated experience during consultations. This evolution drives the framework’s self-improvement, significantly enhancing the rationality and accuracy of the consultations. To ensure that the conclusions are safe, reliable, and aligned with human values, the final decisions undergo a safety review before being provided to the patient. This framework achieved accuracy rates of 89.2% and 83.1% on the MedQA and PubMedQA datasets, respectively.

关键词： Accuracy Pollution Databases Reviews Large language models Natural languages Signal processing Safety Reliability Speech processing

来源：评论

学校读者我要写书评

暂无评论

Model-Driven Intelligent Management: Constructing a New Framework for Efficient engineering Safety Monitoring

Model-Driven Intelligent Management: Constructing a New Fram...

引用

computer Technology and Information science (ISCTIS), International Symposium on

作者： Hong Li Fei Wang Shaoxun Deng Research and Development Department Guizhou Bit Software Co. Ltd. Guiyang China Power China Guiyang Engineering Co. Ltd. Institute of Engineering Safety Science Guiyang China School of Computer Science and Technology Guizhou University Guiyang China

ISBN: (数字)9798350354560

ISBN: (纸本)9798350354577

In the context of ensuring operational safety for reservoir dams and other vital infrastructures, engineering safety monitoring systems play an essential role, functioning as a core component in assessing and guaranteeing structural health. Traditional monitoring systems, however, have been constrained by their reliance on data architectures tailored to specific manufacturers' devices, limiting system scalability and maintainability. This paper introduces an innovative strategy aimed at eliminating differences among instruments, achieving an integrated process from data acquisition, processing, analysis to report *** study adopts JSON format to standardize instrument models, incorporating abstract design principles that define not only fundamental parameters and data fields but also specific computational logic to accommodate diverse monitoring needs. particularly for complex instruments like multipoint displacement meters, the system introduces the concept of virtual instrument types, realizing advanced functionality through combinations of basic instrument models. Furthermore, by employing predefined templates for data visualization, graphics, and analysis, the system can flexibly adapt to various monitoring *** approach has been successfully implemented in the engineering safety monitoring projects of China Power Construction Group Guiyang institute, covering over 82 dams, foundation pits, and other structures, processing more than 20 million monitoring records, significantly enhancing monitoring efficiency and data analysis quality. While the current system operates effectively with relational databases, future research aims to explore its potential within a Bson and NoSQL environment, further boosting scalability and flexibility.

关键词： Meters Dams Instruments Computational modeling Scalability Relational databases Reservoirs Safety Logic Monitoring

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Algorithms for Delay Prediction in IoT and Tactile Internet

Machine Learning Algorithms for Delay Prediction in IoT and ...

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： Janani B Kapil Aggarwal K. Malarvizhi S. Zulaikha Beevi M. Malathy D. Suganthi Department of Computer Science and Business Systems Dr. NGP Institute of Technology Coimbatore Tamil Nadu Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Computer Science and Business Systems JCT College of Engineering and Technology Coimbatore Department of Computer Science and Engineering JCT College of Engineering and Technology Pichanur Coimbatore Department of CSE Vel Tech High Tech Dr. Rangarajan Dr.Sakunthala Engineering College Avadi Chennai Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Thandalam Chennai Tamilnadu India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

Within the domain of fifth-generation (5G) networks, which represent the next generation of cellular systems, the combination of state-of-the-art artificial intelligence (AI) with revolutionary concepts like globally networked products and touch-based internet is envisaged. The incorporation of artificial intelligence technology into 5G networks presents an opportunity to provide innovative services with significant and long-lasting effects. In particular, network traffic prediction—a critical component of guaranteeing the security, dependability, and quality availability in data networks—is greatly aided by machine learning (ML) technologies, which are skilled at identifying nonlinear patterns in the environment. This research uses a forward-looking k-step-ahead prediction approach to estimate delays in the Internet of Things (IoT) and tactile internet using a nonlinear autoregressive model with external data (NARX)-enabled recurrent neural network (RNN). The machine learning training process uses four different training functions: Levenberg–Marquardt backpropagation (Trainlm), conjugate slope backpropagation with Fletcher-Reeves updates (Traincgf), robust backpropagation (Trainrp), and Bayesian regularization backpropagation (Trainbr). Mean squared error, root average square error, and mean absolute percentage of error (MAPE) functions are used to analyze the accuracy of projected delays, providing a thorough evaluation of the forecast performance.

关键词： Backpropagation Tactile Internet Training Accuracy Recurrent neural networks 5G mobile communication Heuristic algorithms Predictive models Prediction algorithms Delays

来源：评论

学校读者我要写书评

暂无评论

End-to-end Semantic Segmentation Network for Low-Light Scenes

End-to-end Semantic Segmentation Network for Low-Light Scene...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Hongmin Mu Gang Zhang MengChu Zhou Zhengcai Cao College of Information Science and Technology Beijing University of Chemical Technology Beijing China Department of Macao Institute of Systems Engineering Macau University of Science and Technology Macao China Helen and John C. Hartmann Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In the fields of robotic perception and computer vision, achieving accurate semantic segmentation of low-light or nighttime scenes is challenging. This is primarily due to the limited visibility of objects and the reduced texture and color contrasts among them. To address the issue of limited visibility, we propose a hierarchical gated convolution unit, which simultaneously expands the receptive field and restores edge texture. To address the issue of reduced texture among objects, we propose a dual closed-loop bipartite matching algorithm to establish a total loss function consisting of the unsupervised illumination enhancement loss and supervised intersection-over-union loss, thus enabling the joint minimization of both losses via the Hungarian algorithm. We thus achieve end-to-end training for a semantic segmentation network especially suitable for handling low-light scenes. Experimental results demonstrate that the proposed network surpasses existing methods on the Cityscapes dataset and notably outperforms state-of-the-art methods on both Dark Zurich and Nighttime Driving datasets.

关键词： Training computer vision Accuracy Convolution Semantic segmentation Lighting Logic gates

来源：评论

学校读者我要写书评

暂无评论

AFALog: A General Augmentation Framework for Log-based Anomaly Detection with Active Learning

AFALog: A General Augmentation Framework for Log-based Anoma...

引用

International Symposium on software Reliability engineering (ISSRE)

作者： Chiming Duan Tong Jia Huaqian Cai Ying Li Gang Huang School of Software and Microelectronics Peking University Beijing China Institute for Artificial Intelligence Peking University Beijing China School of Computer Science Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China

Log-based anomaly detection is becoming more and more important for maintaining the availability of modern microservice systems. Existing supervised/semi-supervised log anomaly detection models require a large amount of human-labeled logs for training which are hard to collect in real-world systems. Unsupervised models often perform poorly without explicit anomaly labels. To improve the performance of unsupervised models, in this paper, we first make an empirical study of existing unsupervised models to tackle the reason why they often produce unsatisfied results. We find that anomaly detection results produced by existing unsupervised models are significantly affected by two key problems including Not-Cover (NC) problem and Suspicious-Noise (SN) problem. To solve these problems, we propose a novel augmentation framework called AFALog. AFALog leverages the idea of active learning to incorporate human knowledge so as to augment data quality. It can support almost all existing unsupervised models and improve their performance. Our experiments on two open datasets and one dataset collected from a real-world microservice system demonstrate that DALog improves the F1-score by an average of 6.61%, with only 5.9% labeled training data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum Reinforcement Learning with Quantum World Model

Quantum Reinforcement Learning with Quantum World Model

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Peigen Zeng Ying He F. Richard Yu Victor C.M. Leung Shenzhen Key Lab of Digital & Intelligent Technologies & Systems College of Computer Science and Software Engineering Shenzhen University China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China

Quantum reinforcement learning (QRL) can outperform classical reinforcement learning (RL) by utilizing quantum parallel theory and quantum phenomena such as superposition and entanglement. Although some excellent work has been done on QRL, most existing works either fail to show the exponential advantage of quantum computation over classical computation in terms of performance or are too demanding on quantum devices. In this paper, we provide a novel perspective on combining quantum computing and RL with faster convergence speed and relatively relaxed demands on quantum devices. Specifically, we propose a method to construct a world model with quantum circuit that allows it to interact in a quantum way. In addition, we use Grover's algorithm to efficiently extract high-value information from the quantum world model. Extensive simulation results show that the proposed method can have superior performance compared to classical RL algorithms.

关键词：

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：