检索结果-南通市图书馆

An Empirical Study on Google Research Football Multi-agent Scenarios

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第3期21卷 549-570页

作者： Yan Song He Jiang Zheng Tian Haifeng zhang Yingping zhang Jiangcheng Zhu Zonghong Dai weinan zhang Jun Wang Institute of Automation Chinese Academy of SciencesBeijing100190China Digital Brain Lab Shanghai200001China ShanghaiTech University Shanghai200001China Huawei Cloud Guiyang550003China Shanghai Jiao Tong University Shanghai200001China University College London LondonWC1E 6PTUK

Few multi-agent reinforcement learning (MARL) researches on Google research football (GRF) focus on the 11-vs-11 multi-agent full-game scenario and to the best of our knowledge, no open benchmark on this scenario has been released to the public. In this work, we fill the gap by providing a population-based MARL training pipeline and hyperparameter settings on multi-agent football scenario that outperforms the bot with difficulty 1.0 from scratch within 2 million steps. Our experiments serve as a reference for the expected performance of independent proximal policy optimization (IPPO), a state-of-the-art multi-agent reinforcement learning algorithm where each agent tries to maximize its own policy independently across various training configurations. Meanwhile, we release our training framework Light-MALib which extends the MALib codebase by distributed and asynchronous implementation with additional analytical tools for football games. Finally, we provide guidance for building strong football AI with population-based training and release diverse pretrained policies for benchmarking. The goal is to provide the community with a head start for whoever experiment their works on GRF and a simple-to-use population-based training framework for further improving their agents through self-play. The implementation is available at https://***/Shanghai-Digital-Brain-Laboratory/DB-Football.

关键词： Multi-agent reinforcement learning(RL) distributed RL system population-based training reward shaping game theory

Neural recovery machine for Chinese dropped pronoun

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2019年第5期13卷 1023-1033页

作者： weinan zhang Ting LIU Qingyu YIN Yu zhang Research Center for Social Computing and Information Retrieval School of Computer Science and Technology Harbin Institute of TechnologyHarbin 150001China

Dropped pronouns (DPs) are ubiquitous in pro-drop languages like Chinese, Japanese etc. Previous work mainly focused on painstakingly exploring the empirical features for DPs recovery. In this paper, we propose a neural recovery machine (NRM) to model and recover DPs in Chinese to avoid the non-trivial feature engineering process. The experimental results show that the proposed NRM significantly outperforms the state-of-the-art approaches on two heterogeneous datasets. Further experimental results of Chinese zero pronoun (ZP) resolution show that the performance of ZP resolution can also be improved by recovering the ZPs to DPs.

关键词： neural network Chinese dropped pronoun re-covery Chinese zero pronoun resolution

Probabilistic robust regression with adaptive weights-a case study on face recognition

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2020年第5期14卷 123-134页

作者： Jin Li Quan Chen Jingwen Leng weinan zhang Minyi Guo Department of Computer Science Shanghai Jiao Tong UniversityShanghai200240China

Robust regression plays an important role in many machine learning problems.A primal approach relies on the use of Huber loss and an iteratively reweightedℓ2 ***,because the Huber loss is not smooth and its corresponding distribution cannot be represented as a Gaussian scale mixture,such an approach is extremely difficult to handle using a probabilistic *** address those limitations,this paper proposes two novel losses and the corresponding probability *** is called Soft Huber,which is well suited for modeling non-Gaussian *** is Nonconvex Huber,which can help produce much sparser results when imposed as a prior on regression *** can represent anyℓq loss(1/2≤q<2)with tuning parameters,which makes the regression model more *** also show that both distributions have an elegant form,which is a Gaussian scale mixture with a generalized inverse Gaussian mixing *** enables us to devise an expectation maximization(EM)algorithm for solving the regression *** can obtain an adaptive weight through EM,which is very useful to remove noise data or irrelevant features in regression *** apply our model to the face recognition problem and show that it not only reduces the impact of noise pixels but also removes more irrelevant face *** experiments demonstrate the promising results on two datasets.

关键词： robust regression nonconvex loss face recognition

A syntactic path-based hybrid neural network for negation scope detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2020年第1期14卷 84-94页

作者： Lydia LAZIB Bing QIN Yanyan ZHAO weinan zhang Ting LIU Research Center for Social Computing and Information Retrieval Harbin Institute of TechnologyHarbin 150001China

The automatic detection of negation is a crucial task in a wide-range of natural language processing(NLP)applications,including medical data mining,relation extraction,question answering,and sentiment *** this paper,we present a syntactic path-based hybrid neural network architecture,a novel approach to identify the scope of negation in a *** hybrid architecture has the particularity to capture salient information to determine whether a token is in the scope or not,without relying on any human *** approach combines a bidirectional long shortterm memory(Bi-LSTM)network and a convolutional neural network(CNN).The CNN model captures relevant syntactic features between the token and the cue within the shortest syntactic path in both constituency and dependency parse *** Bi-LSTM learns the context representation along the sentence in both forward and backward *** evaluate our model on the Bioscope corpus,and get 90.82%F-score(78.31%PCS)on the abstract sub-corpus,outperforming features-dependent approaches.

关键词： natural language processing negation scope detection convolutional neural network recurrent neural network syntactic path

Gated recurrent unit model for a sequence tagging problem

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Technology Letters 2019年第1期25卷 81-87页

作者： Rekia Kadari zhang Yu zhang weinan Liu Ting Research Center for Social Computing and Information Retrieval Harbin Institute of Technology

Combinatory categorial grammer(CCG) supertagging is an important subtask that takes place before full parsing and can benefit many natural language processing(NLP) tasks like question answering and machine translation. CCG supertagging can be regarded as a sequence labeling problem that remains a challenging problem where each word is assigned to a CCG lexical category and the number of the probably associated CCG supertags to each word is large. To address this, recently recurrent neural networks(RNNs), as extremely powerful sequential models, have been proposed for CCG supertagging and achieved good performances. In this paper, a variant of recurrent networks is proposed whose design makes it much easier to train and memorize information for long range dependencies based on gated recurrent units(GRUs), which have been recently introduced on some but not all tasks. Results of the experiments revealed the effectiveness of the proposed method on the CCGBank datasets and show that the model has comparable accuracy with the previously proposed models for CCG supertagging.

关键词： combinatory categorial grammer (CCG) CCG supertagging deep learning gated recurrent unit (GRU)

体外心肺复苏院内启动准备流程的最佳证据总结

在线全文

学校读者我要写书评

暂无评论

中国实用护理杂志 2024年第5期40卷 365-371页

作者：王鹏程王迪季学丽张丽黄夕华张阳春马娜张伟男陈旭锋南京医科大学第一附属医院急诊室南京210029 南京大学附属鼓楼医院血管外科南京210008

目的检索、评价并总结体外心肺复苏院内启动准备流程的相关证据, 以期为临床开展体外心肺复苏提供循证依据。方法采用循证护理研究方法, 根据"6S"证据模型, 自上而下检索美国指南网、苏格兰院际间指南网、英国国家临床医学研究所指南网... 详细信息

目的检索、评价并总结体外心肺复苏院内启动准备流程的相关证据, 以期为临床开展体外心肺复苏提供循证依据。方法采用循证护理研究方法, 根据"6S"证据模型, 自上而下检索美国指南网、苏格兰院际间指南网、英国国家临床医学研究所指南网等网站及UpToDate、The Cochrane Library、PubMed、Embase、中国知网、万方等数据库中与体外心肺复苏院内启动准备相关的指南、临床决策、专家共识、系统评价等文献, 检索日期为建库至2023年5月20日。研究者对检索文献进行筛选、质量评价、证据提取并整合。结果最终纳入11篇文献, 包括2篇指南, 6篇专家共识, 1篇系统评价, 2篇类实验研究, 从医疗条件、团队组建、物品管理、运行机制、启动前救治及启动判断6个方面总结出18条最佳证据。结论本研究总结了体外心肺复苏院内启动准备流程的相关证据, 可为促进体外心肺复苏推广及实施提供参考。后续研究中仍需要着重关注体外心肺复苏的团队建设、人员培训考核以及管理制度优化, 以提高体外心肺复苏的救治效率及准备度。

关键词：心脏停搏体外膜氧合作用体外心肺复苏启动准备证据总结

An Evaluation of Chinese Human-Computer Dialogue Technology

在线全文

学校读者我要写书评

暂无评论

Data Intelligence 2019年第2期1卷 187-200页

作者： Zhengyu Zhao weinan zhang Wanxiang Che Zhigang Chen Yibo zhang Research Center for Social Computing and Information Retrieval Harbin Institute of TechnologyHarbin 150001China AI Research Institute IFLYTEK Co.Ltd.Hefei 230088China Huawei Technologies Co. Ltd.Shenzhen 518129China

The human-computer dialogue has recently attracted extensive attention from both academia and industry as an important branch in the field of artificial intelligence(AI).However,there are few studies on the evaluation of large-scale Chinese human-computer dialogue *** this paper,we introduce the Second Evaluation of Chinese Human-Computer Dialogue Technology,which focuses on the identification of a user’s intents and intelligent processing of intent *** Evaluation consists of user intent classification(Task 1)and online testing of task-oriented dialogues(Task 2),the data sets of which are provided by iFLYTEK *** evaluation tasks and data sets are introduced in detail,and meanwhile,the evaluation results and the existing problems in the evaluation are discussed.

关键词： Chinese human-computer dialogue evaluation Evaluation data User intent classification Task-oriented dialogue

基于AHP的铁路危险货物办理站作业风险评估研究

在线全文

学校读者我要写书评

暂无评论

时代汽车 2024年第10期 11-14页

作者：张伟男邓聪聪黄居杰柳州铁道职业技术学院广西柳州545616

通过对影响铁路危险货物办理站作业安全的各因素分析,构建层次分析结构模型,并应用AHP的基本原理,对铁路危险货物办理站作业中各有关因素权重排序,结果表明在二级准则层中“人的因素”影响占比权重最大,其占比为0.5542,在三级案例层中,... 详细信息

通过对影响铁路危险货物办理站作业安全的各因素分析,构建层次分析结构模型,并应用AHP的基本原理,对铁路危险货物办理站作业中各有关因素权重排序,结果表明在二级准则层中“人的因素”影响占比权重最大,其占比为0.5542,在三级案例层中,“从业人员遵守规章意识”权重占比最大,达到0.3071,并针对研究结果提出相关建议。

关键词：铁路危险货物办理站 AHP 风险评估指标权重

Large sequence models for sequential decision-making:a survey

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

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 *** 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 *** recent years,sequence models,especially the Transformer,have attracted increasing interest in the RL communities,spawning numerous approaches with notable effectiveness and *** 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 ***,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