检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Bai, Haoming Wu, Linjiao Chengdu University of Technology College of Earth Science Sichuan Chengdu China University of Shanghai for Science and Technology College of Communication and Art Design Shanghai Shanghai China

ISBN: (纸本)9798350317022

Deep learning is a branch of machine learning, which has been used to solve many problems in the fields of computer vision, speech recognition, natural language processing and so on. Deep neural networks are trained by inputting large amounts of data into them, and then they learn how to recognize patterns from these data. This process is called supervised training because the network learns from tagged examples (such as images) or other inputs (such as audio files or text documents). The social media based performed by two models such as Deep network structure feature learning and Feature learning of social media based on deep network. The suggested approach achieved the better transmission of social media by M10, DBLP and Cora of values about 0.70, 0.75 and 0.80 respectively. The problem with deep learning is that it is difficult to train these networks on new tasks without accessing a large amount of tag data for each task. In addition, there are many challenges in teaching the knowledge learned in the learning process. © 2023 IEEE.

关键词： deep learning learning algorithm social media features

来源：评论

学校读者我要写书评

暂无评论

learning algorithm OF LARGE BP NEURAL NETWORK

LEARNING ALGORITHM OF LARGE BP NEURAL NETWORK

引用

计算机，通信，控制与电力工程国际会议

作者： Chen Ming Li Minghui Computer Institute Dalian University of Technology

Training neural network is a NP complete problem[1][3].A learning algorithm is proposed in this *** analysis and simulation results show that this kind of algorithm, which is used to train large BP neural network,can ... 详细信息

ISBN: (纸本)0780312333

关键词： Large BP neural network learning algorithm NP complete problem.

来源：评论

学校读者我要写书评

暂无评论

A novel learning algorithm for Buchi automata based on family of DFAs and classification trees

引用

INFORMATION AND COMPUTATION 2021年 281卷 104678-104678页

作者： Li, Yong Chen, Yu-Fang Zhang, Lijun Liu, Depeng Chinese Acad Sci State Key Lab Comp Sci Inst Software Room 213Bldg 5Zhongguancun South Four St 4 Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Acad Sinica Inst Informat Sci Taipei 11529 Taiwan Inst Intelligent Software Beijing 511400 Peoples R China

In this paper, we propose a novel algorithm to learn a Buchi automaton from a teacher who knows an omega-regular language. The learned Buchi automaton can be a nondeterministic Buchi automaton or a limit deterministic Buchi automaton. The learning algorithm is based on learning a formalism called family of DFAs (FDFAs) recently proposed by Angluin and Fisman. The main catch is that we use a classification tree structure instead of the standard observation table structure. The worst case storage space required by our algorithm is quadratically better than that required by the table-based algorithm proposed by Angluin and Fisman. We implement the proposed learning algorithms in the learning library ROLL (Regular Omega Language learning), which also consists of other complete omega-regular learning algorithms available in the literature. Experimental results show that our tree-based learning algorithms have the best performance among others regarding the number of solved learning tasks. (C) 2020 Elsevier Inc. All rights reserved.

关键词： Buchi automata learning algorithm Automata learning Observation table Family of DFAs Classification tree L*

来源：评论

学校读者我要写书评

暂无评论

Energy efficient resource allocation method for 5G access network based on reinforcement learning algorithm

引用

SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS 2023年 56卷

作者： Zhao, Shasha Fuyang Normal Univ Coll Informat Engn Fuyang 236041 Peoples R China

Edge computing and IIoT (Industrial Internet of Things) are two representative application scenarios in 5G (5th Generation) mobile communication technology network. Therefore, this paper studies the resource allocation methods for these two typical scenarios, and proposes an energy-efficient resource allocation method by using DRL algorithm, which enhances the network performance and reduces the network operation cost. Firstly, ac-cording to the characteristics of edge computing, taking the connection relationship between base stations, users and the transmission power allocated by base stations to users as decision variables, minimizing the overall energy efficiency as the goal, and taking the needs of mobile users as constraints, a resource allocation model for user quality of service (QoS) guarantee is designed. Secondly, simulation experiments are used to verify that the proposed method has faster training speed and convergence speed, ensures the quality-of-service requirements of mobile users, and realizes intelligent and energy-saving resource allocation. The approximate amounts of steps to convergence under four cases are 500, 350, 250, and 220, respectively, and the values of awards are 21.76, 21.09, 20.38, and 20.25, respectively. Thirdly, aiming at the IIoT environment scenario, this paper proposes a resource allocation method for 5G wide connection low delay services based on asynchronous dominant action evaluation algorithm (A3C). Firstly, according to the characteristics of IIoT environment, taking the connection relationship between base stations and users and the transmission power allocated by base stations to users as decision variables and maximizing energy efficiency while satisfying needs of each user as optimization goal, a resource allocation model for 5G wide connection low delay services is designed. On this basis, an energy -efficient resource allocation method according to A3C is proposed. The hierarchical aggregation clustering al-gorithm

关键词： 5G Network Edge Computing Industrial Internet of Things Intensive learning learning algorithm Network Access Energy Saving Resource Allocation

来源：评论

学校读者我要写书评

暂无评论

Neural network's learning algorithm based on interval optimization

引用

Jisuanji Gongcheng/Computer Engineering 2006年第4期32卷 192-193+216页

作者： Xue, Jiwei Li, Yaohui Chen, Dongfang Computer Science and Engineering College Daqing Petroleum Institute Daqing 163318 China Chengdu Institute of Computer Application Chinese Academy of Sciences Chengdu 610041 China

Neural networks are usually trained using local gradient-based procedures. Such methods frequently found sub-optimal solutions being trapped in local minima. In solving some application problems, the input/output data sets used to train a neural network may not be hundred percent precise but within certain range. It is difficult for the traditional neural network to solve such problems. A learning algorithm based on interval optimization is presented in this paper. The above disadvantages of the traditional learning algorithm are settled by using this method.

关键词： Global optimization Interval arithmetic learning algorithm Neural network

来源：评论

学校读者我要写书评

暂无评论

An Identification System Design Using a CMAC with a learning algorithm Based on the Kalman Filter

引用

IFAC Proceedings Volumes 1997年第11期30卷 1333-1338页

作者： Yoichi Hirashima Youji Iiguni Okayama University Japan Osaka University Japan

The Cerebellar Model Arithmetic Computer (CMAC) proposed by Albus is a neural network that imitates the human cerebellum, and it is basically a table lookup technique for representing nonlinear functions. The CMAC can approximate a wide variety of nonlinear functions by learning. However, the CMAC requires a number of learning iterations to achieve the adequate approximation accuracy, because CMAC learning algorithm is based on the Least Mean Square method. In this paper, a CMAC learning algorithm based on the Kalman filter is proposed. Using this algorithm, the number of learning iterations is reduced, and the comparable approximation accuracy is achieved as compared to the system using conventional learning algorithm. Generally, the learning algorithm based on the Kalman filter requires much larger computational quantity than that required by algorithms based on the Least Mean Square method. For CMAC system equations contain a sparse matrix, the computational quantity of the proposed learning algorithm can be reduced. Furthermore, since two CMAC weights being in the far place from each other can be considered to have little correlation, the number of weights that should be updated for an learning iteration can be reduced. This reduces the computational quantity of the learning algorithm. Computer simulation results for the modeling problems are presented.

关键词： CMAC Kalman filter LMS method learning algorithm generalization

来源：评论

学校读者我要写书评

暂无评论

HYSTERESIS CHARACTERIZATION BY A FUZZY learning algorithm

引用

International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems 1994年第3期2卷 351-360页

作者： EDGE C. YEH SHAO HOW LU Department of Power Mechanical Engineering National Tsing Hua University Hsinchu Taiwan China Tel: 886-35-715131 Ext 3742 FAX: 886-35-714826

In this paper, the hysteresis characterization in fuzzy spaces is presented by utilizing a fuzzy learning algorithm to generate fuzzy rules automatically from numerical data. The hysteresis phenomenon is first described to analyze its underlying mechanism. Then a fuzzy learning algorithm is presented to learn the hysteresis phenomenon and is used for predicting a simple hysteresis phenomenon. The results of learning are illustrated by mesh plots and input-output relation plots. Furthermore, the dependency of prediction accuracy on the number of fuzzy sets is studied. The method provides a useful tool to model the hysteresis phenomenon in fuzzy spaces.

关键词： hysteresis fuzzy theory learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A learning algorithm with a Gradient Normalization and a learning Rate Adaptation for the Mini-batch Type learning 56

A Learning Algorithm with a Gradient Normalization and a Lea...

引用

56th Annual Conference of the Society-of-Instrument-and-Control-Engineers-of-Japan (SICE)

作者： Ito, Daiki Okamoto, Takashi Koakutsu, Seiichi Chiba Univ Fac Engn Chiba Japan Chiba Univ Grad Sch Engn Chiba Japan

ISBN: (纸本)9784907764579

The development of a high-performance optimization algorithm to solve the learning problem of the neural networks is strongly demanded with the advance of the deep learning. The learning algorithms with gradient normalization mechanisms have been investigated, and their effectiveness has been shown. In the learning algorithms, the adaptation of the learning rate is very important issue. The learning algorithms of the neural networks are classified into the batch learning and the mini-batch learning. In the learning with vast training data, the mini-batch type learning is often used due to the limitation of memory size and the computational cost. The mini-batch type learning algorithms with gradient normalization mechanisms have been investigated. However, the adaptation of the learning rate in the mini-batch type learning algorithm with the gradient normalization has not been investigated well. This study proposes to introduce a new learning rate adaptation mechanism based on sign variation of gradient to a mini-batch type learning algorithm with the gradient normalization. The effectiveness of the proposed algorithm is verified through applications to a learning problem of the multi-layered neural networks and a learning problem of the convolutional neural networks.

关键词： Neural networks Convolutional neural networks Stochastic gradient descent method learning algorithm

来源：评论

学校读者我要写书评

暂无评论

HELOP: Multi-target tracking based on heuristic empirical learning algorithm and occlusion processing✩,✩✩

引用

DISPLAYS 2023年第1期79卷

作者： Jia, Yunhua Zhang, Yukuan Zhou, Chengjiang Yang, Yang Yunnan Normal Univ Sch Informat Technol Kunming Peoples R China Lab Pattern Recognit & Artificial Intelligence Kunming 650500 Peoples R China Yunnan Normal Univ Sch Phys & Elect Informat Kunming 650500 Peoples R China

Multi-target tracking is one of the important fields in computer vision, which aims to solve the problem of matching and correlating targets between adjacent frames. In this paper, we propose a fine-grained track recoverable (FGTR) matching strategy and a heuristic empirical learning (HEL) algorithm. The FGTR matching strategy divides the detected targets into two different sets according to the distance between them, and adopts different matching strategies respectively, in order to reduce false matching, we evaluated the trust degree of the target's appearance feature information and location feature information, adjusted the proportion of the two reasonably, and improved the accuracy of target matching. In order to solve the problem of trajectory drift caused by the cumulative increase of Kalman filter error during the occlusion process, the HEL algorithm predicts the position information of the target in the next few frames based on the effective information of other previous target trajectories and the motion characteristics of related targets. Make the predicted trajectory closer to the real trajectory. Our proposed method is tested on MOT16 and MOT17, and the experimental results verify the effectiveness of each module, which can effectively solve the occlusion problem and make the tracking more accurate and stable.

关键词： Multi-target tracking Occlusion optimization Matching strategy learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Cost-Effective Outage Management in Smart Grid under Single, Multiple, and Critical Fault Conditions through Teaching-learning algorithm†

引用

ENERGIES 2020年第23期13卷 6205页

作者： Thiruvenkadam, S. Ra, In-Ho Kim, Hyung-Jin PA Coll Engn & Technol Dept Elect & Elect Engn Pollachi 642003 Tamil Nadu India Kunsan Natl Univ Sch Comp Informat & Commun Engn Gunsan 54150 South Korea Chonbuk Natl Univ Dept IT Appl Syst Engn Jeonju 54896 South Korea

A distribution system becomes the most essential part of a power system as it links the utility and utility customers. Under abnormal conditions of the system, a definitive goal of the utility is to provide continuous power supply to the customers. This demands a fast restoration process and provision of optimal solutions without violating the power system operational constraints. The main objective of the proposed work is to reduce the service restoration cost (SRC) along with the elimination of the out-of-service loads. In addition, this work concentrates on the minimal usage and finding of optimal locations for additional equipment, such as capacitor placement (CP) and distributed generators (DGs). This paper proposes a two-stage strategy, namely, the service restoration phase and optimization phase. The first phase ensures the restoration of the system from the fault condition, and the second phase identifies the optimal solution with reconfiguration, CP, and DG placement. The optimization phase uses the teaching-learning algorithm (TLA) for optimal restructuring and optimal capacitor and DG placement. The robustness of the algorithm is validated by addressing the test cases under different fault conditions, such as single, multiple, and critical. The effectiveness of the proposed strategy is exhibited with the implementation to IEEE 33-bus radial distribution system (RDS) and 83-bus Taiwan Power Distribution Company (TPDC) System.

关键词： distribution system faults service restoration optimization teaching– learning algorithm capacitor placement DGs

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：