检索结果-南通市图书馆

Large Sequence models for sequential decision-making:a survey

Frontiers of Computer Science 2023年第6期17卷 25-42页

作者： Muning WEN Runji LIN Hanjing WANG Yaodong YANG Ying WEN Luo MAI Jun WANG Haifeng ZHANG Weinan ZHANG School of Electronics Information and Electrical Engineering Shanghai Jiao Tong UniversityShanghai 200241China Digital Brain Lab Shanghai 201306China Institute of Automation Chinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Institute for Artificial Intelligence Peking UniversityBeijing 100091China School of Informatics The University of EdinburghEdinburgh EH89JUUK Department of Computer Science University College LondonLondon WC1E 6BTUK

Transformer architectures have facilitated the development of large-scale and general-purpose Sequence models for prediction tasks in natural language processing and computer vision,e.g.,GPT-3 and Swin Transformer.Although originally designed for prediction problems,it is natural to inquire about their suitability for sequential decision-making and reinforcement learning problems,which are typically beset by long-standing issues involving sample efficiency,credit assignment,and partial observability.In recent years,Sequence models,especially the Transformer,have attracted increasing interest in the RL communities,spawning numerous approaches with notable effectiveness and generalizability.This survey presents a comprehensive overview of recent works aimed at solving sequential decision-making tasks with Sequence models such as the Transformer,by discussing the connection between sequential decision-making and Sequence modeling,and categorizing them based on the way they utilize the Transformer.Moreover,this paper puts forth various potential avenues for future research intending to improve the effectiveness of large Sequence models for sequential decision-making,encompassing theoretical foundations,network architectures,algorithms,and efficient training systems.

关键词： sequential decision-making Sequence modeling the Transformer training system

来源：

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

Sequence-sorted redox-switchable hetero[3]rotaxanes

引用

Organic Chemistry Frontiers 2022年第1期9卷 64-74页

作者： Marius Gaedke Henrik Hupatz Felix Witte Susanne M.Rupf Clara Douglas Hendrik V.Schröder Lukas Fischer Moritz Malischewski Beate Paulus Christoph A.Schalley Institut für Chemie und Biochemie der Freien Universität Berlin Arnimallee 2014195 BerlinGermany Institut für Chemie und Biochemie der Freien Universität Berlin Arnimallee 2214195 BerlinGermany Institut für Chemie und Biochemie der Freien Universität Berlin Fabeckstr.34/3614195 BerlinGermany

From a library of five crown ether macrocycles with different ring sizes and redox-active moieties,such as tetrathiafulvalene(TTF)and naphthalene dimiide(NDI),directional heterocircuit[3]rotaxanes were constructed.Using an axle with two binding sites with different steric accessibility,the concept of integrative self-sorting was applied to program the Sequence of functional units in heteropseudo[3]rotaxanes.Depending on binding strength and ring size of the smaller macrocycles,different heteropseudo[3]rotaxane selectivities and stabilities were determined by 2D NMR spectroscopy and tandem mass spectrometry.A heteropseudo[3]rotaxane with rotaxane-like behaviour was isolated chromatographically,displaying electrochemically“frustrated”properties.A robust synthetic procedure was developed allowing the synthesis of four new hetero[3]rotaxanes incorporating specific Sequences of functional units.Sequence pseudoisomeric rotaxanes which have the naphthalene diimide subunit at two different positions show distinct electrochemical properties.DFT calculations suggest that this differences could arise from a folding of the structure,in which the redox-active moieties stack with a stopper unit.This study presents a blueprint for the construction of hetero[3]rotaxanes with sequential control of the functional units along the track of the axle and paves the way to extend the functionality of mechanically interlocked molecules.

关键词： properties redox Sequence

来源：

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

Cross-domain Sequence labelling using language modelling and parameter generating

引用

CAAI Transactions on Intelligence Technology 2022年第4期7卷 710-720页

作者： Bo Zhou Jianying Chen Qianhua Cai Yun Xue Chi Yang Jing He School of Electronics and Information Engineering South China Normal UniversityFoshanChina Department of Neroscience University of OxfordOxfordOxfordshireBritain

Sequence labelling(SL)tasks are currently widely studied in the field of natural language processing.Most Sequence labelling methods are developed on a large amount of labelled training data via supervised learning,which is time-consuming and expensive.As an alternative,domain adaptation is proposed to train a deep-learning model for Sequence labelling in a target domain by exploiting existing labelled training data in related source domains.To this end,the authors propose a Bi-LSTM model to extract more-related knowledge from multi-source domains and learn specific context from the target domain.Further,the language modelling training is also applied to cross-domain adaptability facilitating.The proposed model is extensively evaluated with the named entity recognition and part-of-speech tagging tasks.The empirical results demonstrate the effectiveness of the cross-domain adaption.Our model outperforms the state-of-the-art methods used in both cross-domain tasks and crowd annotation tasks.

关键词： Sequence generating consuming

来源：

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

The genome Sequence of star fruit(Averrhoa carambola)

引用

Horticulture Research 2020年第1期7卷 1703-1712页

作者： Shasha Wu Wei Sun Zhichao Xu Junwen Zhai Xiaoping Li Chengru Li Diyang Zhang Xiaoqian Wu Liming Shen Junhao Chen Hui Ren Xiaoyu Dai Zhongwu Dai Yamei Zhao Lei Chen Mengxia Cao Xinyu Xie Xuedie Liu Donghui Peng Jianwen Dong Yu-Yun Hsiao Shi-lin Chen Wen-Chieh Tsai Siren Lan Zhong-Jian Liu Key Laboratory of National Forestry and Grassland Administration for Orchid Conservation and Utilization at College of Landscape Architecture Fujian Agriculture and Forestry UniversityFuzhou 350002China Institute of Chinese Materia Medica Chinese Academy of China Medical SciencesBeijing 100700China Institute of Medicinal Plant Development Chinese Academy of Medical Sciences&Peking Union Medical CollegeBeijing 100193China State Key Laboratory of Subtropical Silviculture Zhejiang A&F UniversityLin’anHangzhou 311300China Horticulture Research Institute Guangxi Academy of Agricultural SciencesNanning 530007China Orchid Research and Development Center National Cheng Kung UniversityTainan 701China Institute of Tropical Plant Sciences and Microbiology National Cheng Kung UniversityTainan City 701China

Oxalidaceae is one of the most important plant families in horticulture,and its key commercially relevant genus,Averrhoa,has diverse growth habits and fruit types.Here,we describe the assembly of a high-quality chromosomescale genome Sequence for Averrhoa carambola(star fruit).Ks distribution analysis showed that A.carambola underwent a whole-genome triplication event,i.e.,the gamma event shared by most eudicots.Comparisons between A.carambola and other angiosperms also permitted the generation of Oxalidaceae gene annotations.We identified unique gene families and analyzed gene family expansion and contraction.This analysis revealed significant changes in MADS-box gene family content,which might be related to the cauliflory of A.carambola.In addition,we identified and analyzed a total of 204 nucleotide-binding site,leucine-rich repeat receptor(NLR)genes and 58 WRKY genes in the genome,which may be related to the defense response.Our results provide insights into the origin,evolution and diversification of star fruit.

关键词： Sequence insight analysis

来源：

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

Mining and validation of novel genotyping-bysequencing(GBS)-based simple Sequence repeats(SSRs)and their application for the estimation of the genetic diversity and population structure of coconuts(Cocos nucifera L.)in Thailand

引用

Horticulture Research 2020年第1期7卷 717-732页

作者： Kanamon Riangwong Samart Wanchana Wanchana Aesomnuk Chatree Saensuk Phakchana Nubankoh Vinitchan Ruanjaichon Tippaya Kraithong Theerayut Toojinda Apichart Vanavichit Siwaret Arikit Department of Biotechnology Faculty of Engineering and Industrial TechnologySilpakorn UniversitySanamchandra Palace CampusNakhon Pathom 73000Thailand National Center for Genetic Engineering and Biotechnology(BIOTEC) National Science and Technology Development Agency(NSTDA)Khlong LuangPathum Thani 12120Thailand Center for Agricultural Biotechnology Kasetsart UniversityKamphaeng Saen CampusNakhon Pathom 73140Thailand Rice Science Center Kasetsart UniversityKamphaeng Saen CampusNakhon Pathom 73140Thailand Chumphon Horticultural Research Center Department of AgricultureBangkok 10900Thailand Department of Agronomy Faculty of Agriculture at Kamphaeng SaenKasetsart UniversityKamphaeng Saen CampusNakhon Pathom 73140Thailand

Coconut(Cocos nucifera L.)is an important economic crop in tropical countries.However,the lack of a complete reference genome and the limitations of usable DNA markers hinder genomic studies and the molecular breeding of coconut.Here,we present the results of simple Sequence repeat(SSR)mining from a high-throughput genotyping-bysequencing(GBS)study of a collection of 38 coconut accessions.A total of 22,748 SSRs with di-,tri-,tetra-,penta-and hexanucleotide repeats of five or more were identified,2451 of which were defined as polymorphic loci based on locus clustering in 38 coconut accessions,and 315 loci were suitable for the development of SSR markers.One hundred loci were selected,and primer pairs for each SSR locus were designed and validated in 40 coconut accessions.The analysis of 74 polymorphic markers identified between 2 and 9 alleles per locus,with an average of 3.01 alleles.The assessment of the genetic diversity and genetic relationships among the 40 coconut varieties based on the analysis of population structure,principal coordinate analysis(PCoA),and phylogenetic tree analysis using the 74 polymorphic SSR markers revealed three main groups of coconuts in Thailand.The identified SSR loci and SSR markers developed in this study will be useful for the study of coconut diversity and molecular breeding.The SSR mining approach used in this study could be applied to other plant species with a complex genome regardless of the availability of reference genome.

关键词： breeding structure Sequence

来源：

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

FAAD:an unsupervised fast and accurate anomaly detection method for a multi-dimensional Sequence over data stream

引用

Frontiers of Information Technology & Electronic Engineering 2019年第3期20卷 388-404页

作者： Bin LI Yi-jie WANG Dong-sheng YANG Yong-mou LI Xing-kong MA Science and Technology on Parallel and Distributed Processing Laboratory College of ComputerNational University of Defense Technology Block Chain Research Institute of LianLian Pay

Recently, Sequence anomaly detection has been widely used in many fields. Sequence data in these fields are usually multi-dimensional over the data stream. It is a challenge to design an anomaly detection method for a multi-dimensional Sequence over the data stream to satisfy the requirements of accuracy and high speed. It is because:(1) Redundant dimensions in Sequence data and large state space lead to a poor ability for Sequence modeling;(2) Anomaly detection cannot adapt to the high-speed nature of the data stream, especially when concept drift occurs, and it will reduce the detection rate. On one hand, most existing methods of Sequence anomaly detection focus on the single-dimension Sequence. On the other hand, some studies concerning multi-dimensional Sequence concentrate mainly on the static database rather than the data stream. To improve the performance of anomaly detection for a multi-dimensional Sequence over the data stream, we propose a novel unsupervised fast and accurate anomaly detection(FAAD) method which includes three algorithms. First, a method called "information calculation and minimum spanning tree cluster" is adopted to reduce redundant dimensions. Second, to speed up model construction and ensure the detection rate for the Sequence over the data stream, we propose a method called"random sampling and subSequence partitioning based on the index probabilistic suffix tree." Last, the method called "anomaly buffer based on model dynamic adjustment" dramatically reduces the effects of concept drift in the data stream. FAAD is implemented on the streaming platform Storm to detect multi-dimensional log audit data.Compared with the existing anomaly detection methods, FAAD has a good performance in detection rate and speed without being affected by concept drift.

关键词： Data stream Multi-dimensional Sequence Anomaly detection Concept drift Feature selection

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Compound heterozygous mutation of MUSK causing fetal akinesia deformation Sequence syndrome: A case report

引用

World Journal of Clinical Cases 2019年第21期7卷 3655-3661页

作者： Na Li Chong Qiao Yuan Lv Tian Yang Hao Liu Wen-Qian Yu Cai-Xia Liu Department of Obstetrics and Gynecology Shengjing Hospital of China Medical UniversityShenyang 110004Liaoning ProvinceChina Key Laboratory of Maternal-Fetal Medicine of Liaoning Province Key Laboratory of Obstetrics and Gynecology of Higher Education of Liaoning ProvinceShenyang 110004Liaoning ProvinceChina

BACKGROUND Fetal akinesia deformation Sequence(FADS)is a broad spectrum disorder with absent fetal movements as the unifying feature.The etiology of FADS is heterogeneous and mostly still unknown.A prenatal diagnosis of FADS relies on clinical features obtained by ultrasound and fetal muscle pathology.However,the recent advances of next-generation sequencing(NGS)can effectively provide a definitive molecular diagnosis.CASE SUMMARY A fetus presented after 24 wk and 6 d of gestation with absent fetal movements and multiple abnormal ultrasonographic signs.The mother had had a previous abortion due to a similarly affected fetus a year before.A clinical diagnosis of FADS was made.The parents refused cord blood examination and chose abortion.A molecular diagnosis of fetal muscle using NGS of genes found a compound heterozygous mutation in the MUSK gene:c.220C>T(chr9:113449410 p.R74W)and c.421delC(chr9:113457745 p.P141fs).CONCLUSION To our knowledge,this is the first report in China showing that a mutation in MUSK is associated with FADS.This supports previous finding that a lethal mutation of MUSK will cause FADS.A precise molecular diagnosis for genetic counseling and options for a prenatal diagnosis of FADS are very important,especially for recurrent FADS;this may also provide evidence for both prenatal and preimplantation genetic diagnoses.

关键词： MUSK gene Fetal akinesia deformation Sequence Joint contractures Casereport

来源：

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

Pathogenic Characterization and Full Length Genome Sequence of a Reassortant Infectious Bursal Disease Virus Newly Isolated in Pakistan

引用

Virologica Sinica 2019年第1期34卷 102-105页

作者： Altaf Hussain Tiantian Wu Hui Li Linjin Fan Kai Li Li Gao Yongqiang Wang Yulong Gao Changjun Liu Hongyu Cui Qing Pan Yanping Zhang Asim Aslam Khan Muti-Ur-Rehman Muhammad Munir Salman Latif Butt Xiaomei Wang Xiaole Qi Division of Avian Infectious Diseases State Key Laboratory of Veterinary BiotechnologyHarbin Veterinary Research InstituteThe Chinese Academy of Agricultural Sciences OIE Reference Laboratory for Infectious Bursal Disease Pathology Department University of Veterinary and Animal Sciences Division of Biomedical and Life Sciences Faculty of Health and MedicineLancaster University Department of Pathology College of Veterinary MedicineUniversity of Georgia Jiangsu Co-innovation Centre for Prevention and Control of Important Animal Infectious Disease and Zoonoses

Dear Editor,Infectious bursal disease (IBD) is one of the most important diseases of the poultry. The IBD virus (IBDV), a nonenveloped virus belonging to the Birnaviridae family with a genome consisting of two segments of double-stranded RNA (segments A and B), targets B lymphocytes of bursa of Fabricious leading to immunosuppression. In Pakistan,poultry farming is the second biggest industry and IBD is the second biggest disease threating the poultry sector.However.

关键词： In Pathogenic Characterization and Full Length Genome Sequence of a Reassortant Infectious Bursal Disease Virus Newly Isolated in Pakistan

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Complexity estimation of image Sequence for automatic target track

引用

Journal of Systems Engineering and Electronics 2019年第4期30卷 672-683页

作者： WANG Xiaotian ZHANG Kai YAN Jie School of Astronautics Northwestern Polytechnical University

In the field of automatic target recognition and tracking,traditional image complexity metrics,such as statistical variance and signal-to-noise ratio,all focus on single-frame images.However,there are few researches about the complexity of image Sequence.To solve this problem,a criterion of evaluating image Sequence complexity is proposed.Firstly,to characterize this criterion quantitatively,two metrics for measuring the complexity of image Sequence,namely feature space similarity degree of global background(FSSDGB)and feature space occultation degree of local background(FSODLB)are developed.Here,FSSDGB reflects the ability of global background to introduce false alarms based on feature space,and FSODLB represents the difference between target and local background based on feature space.Secondly,the feature space is optimized by the grey relational method and relevant features are removed so that FSSDGB and FSODLB are more reasonable to establish complexity of single-frame images.Finally,the image Sequence complexity is not a linear sum of the single-frame image complexity.Target tracking errors often occur in high-complexity images and the tracking effect of low-complexity images is very well.The nonlinear transformation based on median(NTM)is proposed to construct complexity of image Sequence.The experimental results show that the proposed metric is more valid than other metrics,such as Sequence correlation(SC)and interframe change degree(IFCD),and it is highly relevant to the actual performance of automatic target tracking algorithms.

关键词： complexity of image Sequence feature space similarity degree of global background(FSSDGB) feature space occultation degree of local background(FSODLB) grey relational method nonlinear transformation based on median(NTM)

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

High Secure Sequence Design in Frequency Hopping Communications

引用

China Communications 2019年第4期16卷 139-150页

作者： Rui Chen Zan Li Jia Shi Lei Guan Jiankang Zhang School of Telecommunications Engineering Xidian University School of Electronics and Computer Science University of Southampton

Frequency-hopping(FH) technique is widely used in high-secure communications by exploiting its capabilities of mitigating interference and confidentiality. However, electronic attacks in wireless systems become more and more rigorous, which poses huge challenges to the use of the number theory based and chaos theory assisted Sequences. The structure of the FH Sequence directly affects the performance of FH communication systems. In this paper, the novel FH Sequence generation scheme is proposed with the aid of the so-called Government Standard(GOST) algorithm, which achieves a promising balance between efficiency and security. Moreover, the security performance of the proposed algorithm is analyzed, which reveals that it is more resistant to impossible differential attacks than the widely-used Data Encryption Standard(DES) algorithm. The numerical results show that the FH Sequences generated by the GOST algorithm significantly outperform the ones generated by the DES algorithm and chaotic theory in terms of the randomness and complexity.

关键词： frequency-hopping Sequence cryptographic algorithm security randomness complexity

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：