检索结果-内蒙古大学图书馆

Chinese word segmentation without using lexicon and hand-crafted training data 36

Chinese word segmentation without using lexicon and hand-cra...

36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, COLING-ACL 1998

作者： Maosong, Sun Dayang, Shen Tsou, Benjamin K. State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China Computer Science Institute Shantou University Guangdong China Language Information Sciences Research Centre City University of Hong Kong Hong Kong

Chinese word segmentation is the first step in any Chinese NLP system. This paper presents a new algorithm for segmenting Chinese texts without making use of any lexicon and hand-crafted linguistic resource. The statistical data required by the algorithm, that is, mutual information and the difference of t-score between characters, is derived automatically from raw Chinese corpora. The preliminary experiment shows that the segmentation accuracy of our algorithm is acceptable. We hope the gaining of this approach will be beneficial to improving the performance(especially in ability to cope with unknown words and ability to adapt to various domains) of the existing segmenters, though the algorithm itself can also be utilized as a stand-alone segmenter in some NLP applications. © 1998 Universit~ de Montreal.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

A HMM-based integrated method for speaker-independent speech recognition

A HMM-based integrated method for speaker-independent speech...

引用

International Conference on Signal Processing Proceedings (ICSP)

作者： Yiying Zhang Xiaoyan Zhu State Key Laboratory of Intelligent Technology and Systems Department of Computer Science Tsinghua University Beijing China

In this paper a new integrated method for speaker-independent speech recognition is proposed. This method incorporates three models based on the HMM, i.e., the semi-continuous hidden Markov model, the simple trajectory model and the Markov chain model to recognize an input utterance. The training procedure and recognition strategy as well as related computation problems are described in detail in this paper. Experiments on a Mandarin speech database CIDS showed that the proposed method can significantly decrease the error rate of the speaker independent (SI) system and it is a promising method to improve SI recognition systems employing existing techniques. The idea given in this paper provides a new way for speech recognition.

关键词： Hidden Markov models Speech recognition Neural networks Probability density function Laboratories intelligent systems Computer science Databases Error analysis System performance

来源：评论

学校读者我要写书评

暂无评论

Adaptive stabilization of neural control for robot traj ectory tracking

引用

Tsinghua Science and technology 1998年第3期3卷 1149-1154页

作者： Sun Fuchun Lu Wenjuan Dai Min Department of Computer Science and Technology State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing 100084 Department of Electrical Engineering Tsinghua University Beijing 100084

A neural network (NN)-based adaptive control law is proposed for the tracking control of an n-link robot manipulator with unknown dynamic nonli nearities. Basis ftnction-like nets are employed to approximate the plant nonli nearilties, and the bound on the NN reconstruction error is assurred to be unknown. The proposed NN-based adaptive control approach integrates an NN approach with an adaptive implementation of discrete variable structure control with a simple estimation law to estimate the upper bound on the NN reconstruction error and an additional control input to be updated as a function of the estimate. Lyapunov stability theory is used to prove the uni form ultimate boundedness of the tracking error.

关键词： Artificial neural networks Manipulator dynamics Vectors Measurement Control systems

来源：评论

学校读者我要写书评

暂无评论

state Duration-based Segmental Probability Model

State Duration-based Segmental Probability Model

引用

1998 International Conference on Communication technology

作者： Bin Jia Xiaoyan Zhu Yuping Luo Dongcheng Hu Dept.of Automation Tsinghua University Dept.of Computer Science and Technology Tsinghua University State Key Laboratory of Intelligent Technology and Systems in Tsinghua University

ISBN: (纸本)7800908275

This paper suggests a state Duration-based Segmental Probability Model(SDSPM). It comes from incorporating the concept of state duration into the *** distribution of state duration is represented by the Bounded Gamma Distribution(BGD) considered better than Gamma *** SDSPM is simpler than *** the experiments show average 6%improvement of the rate of recognition accuracy compared with HMM and SPM.

关键词： state duration HMM SPM Gamma distribution nonlinear segment

来源：评论

学校读者我要写书评

暂无评论

A fully dynamical fuzzy neural network

A fully dynamical fuzzy neural network

引用

IEEE International Conference on intelligent Processing systems, ICIPS

作者： Z.D. Deng Z.Q. Sun State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China

A fuzzy neural network with dynamic weights is proposed. The network topological architecture and the supervised learning algorithm are given. This novel network has some distinct features and considerable advantages: (1) each basic dynamic weight of the network is a dynamic subsystem; (2) the input space is partitioned into a number of fuzzy boxes; (3) no a priori knowledge including the order of controlled systems is required; (1) it does not require the structuring of feedforward or inverse models of plants through neural networks; (5) the network is essentially a nonlinear controller with learning abilities; and (6) the initial basic dynamic weights can be widely interpretation. The proposed adaptive and learning control system is applied to the control of the pH neutralization process. The simulation investigations show that the dynamic learning control system has better dynamic quality, stronger robustness, and more adaptation and intelligence compared to the present conventional control techniques using an explicit and quantitative mathematical model.

关键词： Fuzzy neural networks Fuzzy control Nonlinear dynamical systems Control system synthesis Nonlinear control systems Control systems Supervised learning Partitioning algorithms Fuzzy systems Inverse problems

来源：评论

学校读者我要写书评

暂无评论

A rough set approach for planner evaluation

A rough set approach for planner evaluation

引用

IEEE International Conference on systems, Man and Cybernetics

作者： B.K. Sy Wang Jiaxin Pattern Analysis and Machine Intelligence Group System Design Engineering Department University of Waterloo Waterloo ONT Canada Department of Computer Science CUNY Flushing NY USA The State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China

This paper discusses a rough set approach for evaluating solutions of scheduling problems. Algorithms for solving scheduling problems are planners and the scheduling problems are modelled as constraint satisfaction problems. Conventional approach for the analysis of algorithms often focuses on the time and representational complexities, and assumes an identical cost on all operations. The proposed rough set approach augments conventional approaches for the analysis of algorithms in two ways: 1) it permits the consideration of different costs arising from different operations; and 2) it allows one to define a new utility for a complexity analysis.

关键词： Algorithm design and analysis Processor scheduling Set theory Machine intelligence Computer science Costs Search problems Educational institutions Pattern analysis System analysis and design

来源：评论

学校读者我要写书评

暂无评论

AutoSilicon: Scaling Up RTL Design Generation Capability of Large Language Models

引用

ACM Transactions on Design Automation of Electronic systems 1000年

作者： Cangyuan Li Chujie Chen Yudong Pan Wenjun Xu Yiqi Liu Kaiyan Chang Yujie Wang Mengdi Wang Ying Wang Huawei Li Yinhe Han Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing China University of the Chinese Academy of Sciences Beijing China Hangzhou Institute for Advanced Study University of the Chinese Academy of Sciences Hangzhou China Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing China SKLP Institute of Computing Technology Chinese Academy of Sciences Beijing China State Key Laboratory of Processor Institute of Computing Technology Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China Zhejiang Lab Hangzhou China

Hardware description language (HDL) code designing is a critical component of the chip design process, requiring substantial engineering and time resources. Recent advancements in large language models (LLMs), such as GPT series, have shown promise in automating HDL code generation. However, current LLM-based approaches face significant challenges in meeting real-world hardware design requirements, particularly in handling complex designs and ensuring code correctness. Our evaluations reveal that the functional correctness rate of LLM-generated HDL code significantly decreases as design complexity increases. In this paper, we propose the AutoSilicon framework, which aims to scale up the hardware design capability of LLMs. AutoSilicon incorporates an agent system, which 1) allows for the decomposition of large-scale, complex code design tasks into smaller, simpler tasks; 2) provides a compilation and simulation environment that enables LLMs to compile and test each piece of code it generates; and 3) introduces a series of optimization strategies. Experimental results demonstrate that AutoSilicon can scale hardware designs to projects with code equivalent to over 10,000 tokens. In terms of design quality, it further improves the syntax correctness rate and functional correctness rate compared with approaches that do not employ any extensions. For example, compared to directly generating HDL code using GPT-4-turbo, AutoSilicon enhances the syntax correctness rate by an average of 35.8% and improves functional correctness by an average of 35.6%.

关键词： Verilog Code Generation LLM Agent Verilog

来源：评论

学校读者我要写书评

暂无评论

Topology in Process Calculus 1

引用

1000年

作者： Mingsheng Ying

ISBN: (数字)9781461301233

ISBN: (纸本)9780387950921;9781461265221

Communication and concurrency are essential in understanding complex dynamic systems, and there have been many theories to deal with them such as Petri nets, CSP and ACP. Among them, CCS (process calculus is one of the most important and mathematically developed models of communication and concurrency. Various behavior equivalences between agents, such as (strong and weak) bisimilarity, observation congruence, trace equivalence, testing equivalence and failure equivalence, are central notions in process calculus. In the real applications of process calculus, specification and implementation are described as two agents, correctness of programs is treated as a certain behavior equivalence between specification and implementation, and then the proof of correctness of programs is a task to establish some behavior equivalence between them. The goal of this book is to provide some suitable and useful concepts and tools for the understanding and analysis of approximate correctness of programs in concurrent systems. Throughout this book the focus is on the framework of process calculus, and the main idea is to construct some natural and reasonable topological structures which can reveal suitably a mechanism of approximate computation in process calculus and to work out various relationships among processes which are compatible with these topological structures.

关键词： Software Engineering/Programming and Operating systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement Learning based Edge Content Caching for Connected Autonomous Vehicles in IoV

引用

ACM Transactions on Autonomous and Adaptive systems 1000年

作者： Xiaolong Xu Linjie Gu Muhammad Bilal Maqbool Khan Yiping Wen Guoqiang Liu Yuan Yuan School of Software Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services Nanjing University of Information Science and Technology China Changwang School of Honors Nanjing University of Information Science and Technology China Department of Computer and Electronics Systems Engineering Hankuk University of Foreign Studies Korea Department of IT and Computer Science Pak-Austria Fachhochschule-Institute of Applied Sciences and Technology Pakistan School of Computer Science and Engineering Hunan University of Science and Technology China School of Software Nanjing University of Information Science and Technology China School of Computer Science and Engineering Beihang University State Key Laboratory of Software Development Environment Zhongguancun Laboratory China

Connected Autonomous Vehicle (CAV) Driving, as a data-driven intelligent driving technology within the Internet of Vehicles (IoV), presents significant challenges to the efficiency and security of real-time data management. The combination of Web3.0 and edge content caching holds promise in providing low-latency data access for CAVs’ real-time applications. Web3.0 enables the reliable pre-migration of frequently requested content from content providers to edge nodes. However, identifying optimal edge node peers for joint content caching and replacement remains challenging due to the dynamic nature of traffic flow in IoV. Addressing these challenges, this article introduces GAMA-Cache, an innovative edge content caching methodology leveraging Graph Attention Networks (GAT) and Multi-Agent Reinforcement Learning (MARL). GAMA-Cache conceptualizes the cooperative edge content caching issue as a constrained Markov decision process. It employs a MARL technique predicated on cooperation effectiveness to discern optimal caching decisions, with GAT augmenting information extracted from adjacent nodes. A distinct collaborator selection mechanism is also developed to streamline communication between agents, filtering out those with minimal correlations in the vector input to the policy network. Experimental results demonstrate that, in terms of service latency and delivery failure, the GAMA-Cache outperforms other state-of-the-art MARL solutions for edge content caching in IoV.

关键词： Content Caching Reinforcement Learning Connected Autonomous Driving

来源：评论

学校读者我要写书评

暂无评论

intelligent Strategies for Pathway Mining 1

引用

丛书名： Lecture Notes in Computer Science

1000年

作者： Qingfeng Chen Baoshan Chen Chengqi Zhang

ISBN: (数字)9783319041728

ISBN: (纸本)9783319041711

This book is organized into thirteen chapters that range over the relevant approaches and tools in data integration, modeling, analysis and knowledge discovery for signaling pathways. Having in mind that the book is also addressed for students, the contributors present the main results and techniques in an easily accessed and understood way together with many references and instances. Chapter 1 presents an introduction to signaling pathway, including motivations, background knowledge and relevant data mining techniques for pathway data analysis. Chapter 2 presents a variety of data sources and data analysis with respect to signaling pathway, including data integration and relevant data mining applications. Chapter 3 presents a framework to measure the inconsistency between heterogenous biological databases. A GO-based (genome ontology) strategy is proposed to associate different data sources. Chapter 4 presents identification of positive regulation of kinase pathways in terms of association rule mining. The results derived from this project could be used when predicting essential relationships and enable a comprehensive understanding of kinase pathway interaction. Chapter 5 presents graphical model-based methods to identify regulatory network of protein kinases. A framework using negative association rule mining is introduced in Chapter 6 to discover featured inhibitory regulation patterns and the relationships between involved regulation factors. It is necessary to not only detect the objects that exhibit a positive regulatory role in a kinase pathway but also to discover those objects that inhibit the regulation. Chapter 7 presents methods to model ncRNA secondary structure data in terms of stems, loops and marked labels, and illustrates how to find matched structure patterns for a given query. Chapter 8 shows an interval-based distance metric for computing the distance between conserved RNA secondary structures. Chapter 9 presents a framework to explore structura

关键词： Artificial Intelligence Database Management Algorithm Analysis and Problem Complexity Information systems Applications (incl. Internet) Information Storage and Retrieval Computation by Abstract Devices

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：