检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Ma, Shuming Sun, Xu Li, Wei Li, Sujian Li, Wenjie Ren, Xuancheng MOE Key Lab of Computational Linguistics School of EECS Peking University Deep Learning Lab Beijing Institute of Big Data Research Peking University Department of Computing Hong Kong Polytechnic University

Most recent approaches use the sequence-to-sequence model for paraphrase generation. The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words. Therefore, the generated sentences are often grammatically correct but semantically improper. In this work, we introduce a novel model based on the encoder-decoder framework, called Word Embedding Attention Network (WEAN). Our proposedmodel generates the words by querying distributed word representations (i.e. neural word embeddings), hoping to capturing the meaning of the according words. Following previous work, we evaluate our model on two paraphrase-oriented tasks, namely text simplification and short text abstractive summarization. Experimental results show that our model outperforms the sequence-to-sequence baseline by the BLEU score of 6.3 and 5.5 on two English text simplification datasets, and the ROUGE-2 F1 score of 5.7 on a Chinese summarization dataset. Moreover, our model achieves state-of-the-art performances on these three benchmark datasets1. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Oscillatory evolution of collective behavior in evolutionary games played with reinforcement learning

arXiv

引用

arXiv 2019年

作者： Zhang, Si-Ping Zhang, Ji-Qiang Chen, Li Liu, Xu-Dong Key Laboratory of Biomedical Information Engineering Ministry of Education Key Laboratory of Neuro-informatics & Rehabilitation Engineering Ministry of Civil Affairs Institute of Health and Rehabilitation Science School of Life Science and Technology Xi'an Jiaotong University Xi'an710049 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Physics and Information Technology Shaanxi Normal University Xi'an710062 China

Large-scale cooperation underpins the evolution of ecosystems and the human society, and the collective behaviors by self-organization of multi-agent systems are the key for understanding. As artificial intelligence (AI) prevails in almost all branches of science, it would be of great interest to see what new insights of collective behavior could be obtained from a multi-agent AI system. Here, we introduce a typical reinforcement learning (RL) algorithm - Q learning into evolutionary game dynamics, where agents pursue optimal action on the basis of the introspectiveness rather than the birth-death or imitation processes in the traditional evolutionary game (EG). We investigate the cooperation prevalence numerically for a general 2 × 2 game setting. We find that the cooperation prevalence in the multi-agent AI is amazingly of equal level as in the traditional EG in most cases. However, in the snowdrift games with RL we also reveal that explosive cooperation appears in the form of periodic oscillation, and we study the impact of the payoff structure on its emergence. Finally, we show that the periodic oscillation can also be observed in some other EGs with the RL algorithm, such as the rock-paper-scissors game. Our results offer a reference point to understand emergence of cooperation and oscillatory behaviors in nature and society from AI's perspective. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Foundation models and intelligent decision-making: Progress, challenges, and perspectives

引用

The Innovation 2025年第6期6卷

作者： Jincai Huang Yongjun Xu Qi Wang Qi (Cheems) Wang Xingxing Liang Fei Wang Zhao Zhang Wei Wei Boxuan Zhang Libo Huang Jingru Chang Liantao Ma Ting Ma Yuxuan Liang Jie Zhang Jian Guo Xuhui Jiang Xinxin Fan Zhulin An Tingting Li Aiguo Fei Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China National Engineering Research Center for Software Engineering Peking University Beijing 100871 China College of Systems Engineering National University of Defense Technology Changsha 410073 China Department of Oral Implantology Peking University School and Hospital of Stomatology Beijing 100081 China Laboratory for Big Data and Decision National University of Defense Technology Changsha 410073 China School of Automation Beijing Institute of Technology Beijing 100081 China Huazhong University of Science and Technology Wuhan 430074 China University of Chinese Academy of Sciences Beijing 100049 China State Key Laboratory of AI Safety Beijing 100190 China Department of Automation Tsinghua University Beijing 100084 China School of Information Science and Engineering Dalian Polytechnic University Dalian 116034 China The Hong Kong University of Science and Technology (Guangzhou) Guangzhou 511453 China College of Information and Electrical Engineering China Agricultural University Beijing 100083 China State Key Laboratory of Efficient Utilization of Agricultural Water Resources Beijing 100083 China IDEA Research International Digital Economy Academy Shenzhen 518057 China School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing 100876 China

Intelligent decision-making (IDM) is a cornerstone of artificial intelligence (AI) designed to automate or augment decision processes. Modern IDM paradigms integrate advanced frameworks to enable intelligent agents to make effective and adaptive choices and decompose complex tasks into manageable steps, such as AI agents and high-level reinforcement learning. Recent advances in multimodal foundation-based approaches unify diverse input modalities—such as vision, language, and sensory data—into a cohesive decision-making process. Foundation models (FMs) have become pivotal in science and industry, transforming decision-making and research capabilities. Their large-scale, multimodal data-processing abilities foster adaptability and interdisciplinary breakthroughs across fields such as healthcare, life sciences, and education. This survey examines IDM’s evolution, advanced paradigms with FMs and their transformative impact on decision-making across diverse scientific and industrial domains, highlighting the challenges and opportunities in building efficient, adaptive, and ethical decision systems.

关键词： artificial intelligence intelligent decision-making foundation models agent large language model

来源：评论

学校读者我要写书评

暂无评论

Needs analysis for the development of interactive virtual reality-based educational media on combustion engine mechanical technology

引用

IOP Conference Series: Materials Science and Engineering 2020年第1期979卷

作者： Sutiman A Yudantoko A Yudianto M Solikin I W Adiyasa N M Suaib F Sholichin D A Irawati Automotive Engineering Education Department Universitas Negeri Yogyakarta Colombo Street 1 Yogyakarta Indonesia. School of Computing Universiti Teknologi Malaysia 81310 UTM Skudai Johor Malaysia. UTM Big Data Center Ibnu Sina Institute of Scientific and Industrial Research Universiti Teknologi Malaysia 81310 UTM Skudai Johor Malaysia.

Needs analysis is the first and necessary step for the researchers to design a newly developed learning media to find out a set of specific requirements to conduct the research activities. The study aims (1) to investigate the user's learning preference, (2) to select the suitable learning materials and to choose the appropriate type of engines, and (3) to identify the needs for the virtual reality development. A focus group discussion (FGD) comprising some representative users and experts in learning media has been involved in the activities with the use of the FGD guidance sheet as the supplementary tools. Additionally, the literature study has also been conducted to collect the necessary additional data to perform a 3D design of the engine. The data were analyzed qualitatively by examining the comment from the users, the experts, and the outcome of the literature review study. It was then concluded that (1) the users require the learning process, which does not need to alternate the learning objects. (2) The two-stroke single-cylinder engine was decided to choose by considering the complexity of the engine mechanical construction. Finally, (3) the needs for engine assembly drawing and virtual reality development have also been described.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Intelligent Hospital Security and data Privacy Construction

引用

Journal of Physics: Conference Series 2019年第5期1187卷

作者： Qiuzi Huang Shuyu Chen Hui Zhao Junhao Wen Network Distributed Computing Laboratory Big Data and Software Institute Huxi Campus of Chongqing University Chongqing China Huxi Campus of Chongqing University no. 55 Chengnan Road Shapingba District Chongqing China Chongqing University 174 Shazheng Street Shapingba District Chongqing China Service Computing Laboratory Big Data and Software Institute Huxi Campus of Chongqing University Chongqing China

With the rapid development of medical information services, the construction of intelligent hospitals is opening up a new mode of medical treatment in the health care industry. Medical data is gradually becoming more and more important, while it also faces some challenges, among which the most urgent problem to be solved is data security and privacy protection. In the construction of intelligent hospitals, the safety issues among the basic information of patients, the protection of medical information and inter-institutional information sharing have become the focus at this stage. Blockchain technology, with highly security, reliable architecture and algorithm design have operated stably in the financial industry for more than seven years. The related innovative technologies such as distributed ledgers, smart contracts, symmetric encryptions and consensus mechanisms are used widely in many fields. This paper will take the demonstration construction of Chongqing Intelligent Hospital as an example, which tries to combine the blockchain, homomorphic encryption and zero-knowledge proof technology to carry out the research on the security construction and data privacy protection of intelligent hospitals.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and development of learning mathematics game for primary school using handheld augmented reality

引用

IOP Conference Series: Materials Science and Engineering 2020年第1期979卷

作者： E Song N M Suaib A J Sihes R Alwee Z Mohd Yunos School of Computing Faculty of Engineering Universiti Teknologi Malaysia 81310 Johor Malaysia UTM Big Data Center Ibnu Sina Institute of Scientific and Industrial Research Universiti Teknologi Malaysia 81310 UTM Skudai Johor Malaysia. School of Education Faculty of Social Sciences and Humanities Universiti Teknologi Malaysia 81310 UTM Skudai Johor Malaysia.

The traditional learning methods have some drawbacks and limitation such as restricted learning space, high cost, and lack of student engagement. In the era of digitalization, traditional education starts to transform into a more dynamic and modern education with the influence of the 21st-century learning method. Moreover, due to the pandemic, schools and universities are moving to digital learning to contain the spread of Coronavirus Disease 2019 (COVID-19). Therefore, the aim of this project is to develop a Mathematics game using handheld Augmented Reality (HAR) for primary school children as an alternative method in learning Mathematics. There are three main phases have been carried out, first is to study the requirements of an educational game. The second phase involves the design and development including the game element, storyline, game characters as well as user interface design. Finally, the third phase is integrating the learning Mathematics game using HAR, followed by evaluation. The evaluation of the learning Mathematics game was carried out for usability and user acceptance. The usability results show that the users are satisfied with the prototype and feedbacks show the game is fun. Overall, this project has successfully produced a learning Mathematics game using HAR for primary school children.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Angular triplet-center loss for multi-view 3D shape retrieval

arXiv

引用

arXiv 2018年

作者： Li, Zhaoqun Xu, Cheng Leng, Biao School of Computer Science and Engineering Beihang University Beijing100191 Research Institute of Beihang University in Shenzhen Shenzhen518057 Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191

How to obtain the desirable representation of a 3D shape, which is discriminative across categories and polymerized within classes, is a significant challenge in 3D shape retrieval. Most existing 3D shape retrieval methods focus on capturing strong discriminative shape representation with softmax loss for the classification task, while the shape feature learning with metric loss is neglected for 3D shape retrieval. In this paper, we address this problem based on the intuition that the cosine distance of shape embeddings should be close enough within the same class and far away across categories. Since most of 3D shape retrieval tasks use cosine distance of shape features for measuring shape similarity, we propose a novel metric loss named angular triplet-center loss, which directly optimizes the cosine distances between the features. It inherits the triplet-center loss property to achieve larger inter-class distance and smaller intra-class distance simultaneously. Unlike previous metric loss utilized in 3D shape retrieval methods, where Euclidean distance is adopted and the margin design is difficult, the proposed method is more convenient to train feature embeddings and more suitable for 3D shape retrieval. Moreover, the angle margin is adopted to replace the cosine margin in order to provide more explicit discriminative constraints on an embedding space. Extensive experimental results on two popular 3D object retrieval benchmarks, ModelNet40 and ShapeNetCore 55, demonstrate the effectiveness of our proposed loss, and our method has achieved state-of-the-art results on various 3D shape datasets. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Adaptive Structure-Constrained Robust Latent Low-Rank Coding for Image Recovery

Adaptive Structure-Constrained Robust Latent Low-Rank Coding...

引用

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Lei Wang Sheng Li Yang Wang Zheng Zhang Zhengjun Zha Meng Wang School of Computer Science and Technology Soochow University Suzhou China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei China Department of Computer Science University of Georgia Athens GA Bio-Computing Research Center Harbin Institute of Technology (Shenzhen) Shenzhen China School of Information Science and Technology University of Science and Technology of China Hefei China

In this paper, we propose a robust representation learning model called Adaptive Structure-constrained Low-Rank Coding (AS-LRC) for the latent representation of data. To recover the underlying subspaces more accurately, AS-LRC seamlessly integrates an adaptive weighting based block-diagonal structure-constrained low-rank representation and the group sparse salient feature extraction into a unified framework. Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part. To enforce the block-diagonal structures adaptive to different real datasets for the low-rank recovery, AS-LRC clearly computes an auto-weighting matrix based on the locality-adaptive features and multiplies by the low-rank coefficients for direct minimization at the same time. This encourages the codes to be block-diagonal and can avoid the tricky issue of choosing optimal neighborhood size or kernel width for the weight assignment, suffered in most local geometrical structures-preserving low-rank coding methods. In addition, our AS-LRC selects the L2, 1-norm on the projection for extracting group sparse features rather than learning low-rank features by Nuclear-norm regularization, which can make learnt features robust to noise and outliers in samples, and can also make the feature coding process efficient. Extensive visualizations and numerical results demonstrate the effectiveness of our AS-LRC for image representation and recovery.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Face Recognition Method Based on CNN

引用

Journal of Physics: Conference Series 2019年第1期1395卷

作者： Zhiming Xie Junjie Li Hui Shi Department of Information Engineering Shanwei Polytechnic Shanwei 516600 Guangdong China The Research Institute of Cloud Computing and Data Center Project Design Shanwei Innovation Industrial Design & Research Institute Shanwei 516600 Guangdong China The Professional Committee Cloud Computing and Big Data in Higher Vocational College Higher Education Institute in Guangdong Province Shanwei 516600 Guangdong China

The traditional face recognition technology is more complicated for the extraction of facial image features and the selection of classifiers, and the recognition rate is not high. With the continuous maturity of the convolutional neural network from handwritten digit recognition to face recognition, A face recognition algorithm that tests CNN using the Python+Keras framework. The method mainly involves two aspects. One is to observe the influence on the network by changing the number of neurons in the hidden layer; the other is to observe the influence on the network by changing the number of feature maps of the convolutional layer 1 and the convolutional layer 2. The best CNN model is 36-76-1024 through multiple sets of experimental tests. The model can automatically extract facial image features and classify them. Using adam optimizer and softmax classifier for face recognition can make training faster convergence and more. Effectively improve accuracy and use the Dropout method to avoid overfitting. The experimental results show that the recognition rate of the CNN model on the olivettifaces face database is 97.5%. When the optimal CNN model is used, the average recognition rate is close to 100%, which verifies the validity and accuracy of the algorithm and model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Small Evolution Antenna Design Method Based on Dynamic Hill Climbing Algorithm and Orthogonal Experiment

引用

Journal of Physics: Conference Series 2019年第1期1395卷

作者： Hui Shi Junjie Li Zhiming Xie Department of Information Engineering Shanwei Polytechnic Shanwei 516600 Guangdong China The Research Institute of Cloud Computing and Data Center Project Design Shanwei Innovation Industrial Design & Research Institute Shanwei 516600 Guangdong China The Professional Committee Cloud Computing and Big Data in Higher Vocational College Higher Education Institute in Guangdong Province Shanwei 516600 Guangdong China

Small-scale evolution antennas have the advantages of high gain, wide bandwidth and small size, and have broad application prospects in the aerospace field. Aiming at the complex high-dimensional and dynamic problems of aerial antenna modeling, a dynamic hill-climbing algorithm based on orthogonal design is designed and implemented to simulate and optimize the single-span antenna in high-frequency operation mode. In the optimization problem, this paper defines a new individual comparison mechanism, which can reflect the number of violations of constraints and the degree of violation of each constraint, making the comparison of individuals more reasonable. The antenna simulation results demonstrate the effectiveness and feasibility of using dynamic evolutionary algorithms for antenna design.

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：