检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Stephenson, Matthew Renz, Jochen Ge, Xiaoyu Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands Research School of Computer Science Australian National University Canberra Australia

The physics-based simulation game Angry Birds has been heavily researched by the AI community over the past five years, and has been the subject of a popular AI competition that is currently held annually as part of a leading AI conference. Developing intelligent agents that can play this game effectively has been an incredibly complex and challenging problem for traditional AI techniques to solve, even though the game is simple enough that any human player could learn and master it within a short time. In this paper we analyse how hard the problem really is, presenting several proofs for the computational complexity of Angry Birds. By using a combination of several gadgets within this game’s environment, we are able to demonstrate that the decision problem of solving general levels for different versions of Angry Birds is either NP-hard, PSPACE-hard, PSPACE-complete or EXPTIME-hard. Proof of NP-hardness is by reduction from 3-SAT, whilst proof of PSPACE-hardness is by reduction from True Quantified Boolean Formula (TQBF). Proof of EXPTIME-hardness is by reduction from G2, a known EXPTIME-complete problem similar to that used for many previous games such as Chess, Go and Checkers. To the best of our knowledge, this is the first time that a single-player game has been proven EXPTIME-hard. This is achieved by using stochastic game engine dynamics to effectively model the real world, or in our case the physics simulator, as the opponent against which we are playing. These proofs can also be extended to other physics-based games with similar mechanics. Copyright © 2018, The Authors. All rights reserved.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Towards a topic discovery and tracking system with application to news items 2nd

Towards a topic discovery and tracking system with applicati...

引用

2nd International Workshop on Future and Emerging Trends in Language Technology, FETLT 2016

作者： Brüggermann, Daniel Hermey, Yannik Orth, Carsten Schneider, Darius Selzer, Stefan Spanakis, Gerasimos Department of Data Science and Knowledge Engineering Maastricht University Maastricht6200 MD Netherlands

ISBN: (纸本)9783319693644

Rapid proliferation of the World Wide Web led to an enormous increase in the availability of textual corpora. In this paper, the problem of topic detection and tracking is considered with application to news items. The proposed approach explores two algorithms (Non-Negative Matrix Factorization and a dynamic version of Latent Dirichlet Allocation (DLDA)) over discrete time steps and makes it possible to identify topics within storylines as they appear and track them through time. Moreover, emphasis is given to the visualization and interaction with the results through the implementation of a graphical tool (regardless the approach). Experimental analysis on Reuters RCV1 corpus and the Reuters 2015 archive reveals that explored approaches can be effectively used as tools for identifying topic appearances and their evolutions while at the same time allowing for an efficient visualization. © 2017, Springer International Publishing AG.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Accumulated gradient normalization 9

Accumulated gradient normalization

引用

9th Asian Conference on Machine Learning, ACML 2017

作者： Hermans, Joeri R. Spanakis, Gerasimos Möckel, Rico Department of Electrical Engineering and Computer Science Liège University Belgium Department of Data Science and Knowledge Engineering Maastricht University Netherlands

This work addresses the instability in asynchronous data parallel optimization. It does so by introducing a novel distributed optimizer which is able to efficiently optimize a centralized model under communication constraints. The optimizer achieves this by pushing a normalized sequence of first-order gradients to a parameter server. This implies that the magnitude of a worker delta is smaller compared to an accumulated gradient, and provides a better direction towards a minimum compared to first-order gradients, which in turn also forces possible implicit momentum fluctuations to be more aligned since we make the assumption that all workers contribute towards a single minima. As a result, our approach mitigates the parameter staleness problem more effectively since staleness in asynchrony induces (implicit) momentum, and achieves a better convergence rate compared to other optimizers such as asynchronous easgd and dynsgd, which we show empirically. © 2017 J.R. Hermans, G. Spanakis & R. Möckel.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

A Novel Texture Generation Super Resolution Model

引用

Procedia Computer science 2019年 162卷 924-931页

作者： Biao Li Yong Shi Sujuan Li Bo Wang Zhiquan Qi Jiabin Liu School of Economics and Management University of Chinese Academy of Sciences Beijing 101408 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska at Omaha NE 68182 USA Department of Otology the First Affiliated Hospital of Zhengzhou University No. 1 eastern Jianshe road Zhengzhou Henan 450052 China School of Information Technology and Management University of International Business and Economics Beijing 100029 China Department of Computer Science and Engineering Texas A&M University TX 77843 USA

Recently, super-resolution methods pursue visual pleasant details attract more attention in academic circle. Unlike former accurate driving models, they leverage new losses measured the difference of features extracting from a pre-trained deep learning model. Moreover, the popular GANs structure are introduced to approach better outputs. In general, these new visual feeling promoting losses are constrained by the learning ability of model and effected by the weakness of GANs. In order to address these problems, we propose a novel SR method to generating abundant details. Based on former SR methods and texture generated models, we combine new model constructure and integrated loss function to achieve our goal. The new constructure derives from the very thought that more information from the LR input leads to more accurate results. The new integrated loss try to decrease the weakness of each one by corresponding loss.. Experiments show that our model achieves higher quality generations than former methods.

关键词： Super Resolution Multi Scale Smooth Loss Visual Quality

来源：评论

学校读者我要写书评

暂无评论

Resource-gathering algorithms in the game of starcraft

Resource-gathering algorithms in the game of starcraft

引用

2017 IEEE Conference on Computational Intelligence and Games, CIG 2017

作者： Rooijackers, Martin L.M. Winands, Mark H.M. Games AI Group Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

ISBN: (纸本)9781538632338

StarCraft is a real-time strategy game, which has a large state space, and commonly features two opposing players, capable of acting simultaneously. One of the aspects of the game is resource gathering. Each agent playing StarCraft has to gather minerals from nearby mineral field in order to produce more units. The more resources can be gathered, the larger the army is to attack the opponent and win the game. We present five algorithms that can be used for resource gathering for an intelligent agent playing the game of StarCraft: Brood War. The results reveal that improving the scheduling or the path finding improve the resource gathering considerably. © 2017 IEEE.

关键词： Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

Residual network with delayed max pooling for very large scale plant identification 18

Residual network with delayed max pooling for very large sca...

引用

18th Working Notes of CLEF Conference and Labs of the Evaluation Forum, CLEF 2017

作者： Hang, Siang Thye Aono, Masaki Knowledge Data Engineering and Information Retrieval Laboratory Department of Computer Science and Engineering Toyohashi University of Technology Japan

In our approach, we applied a few modifications to the 50-layered Residual Network. Our preliminary experiments with the Plant-CLEF 2016 dataset showed that the modifications improved classification performance. We have trained three models based on the modified Residual Network configuration with different combinations of trusted and noisy PlantCLEF 2017 datasets. Using confidence scores extracted from the three models, we have submitted four runs and our methods showed competitive classification performance.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

What does twitter tell us about tourists’ mobility behavior? A case study on tourists in the Netherlands and Belgium 21

What does twitter tell us about tourists’ mobility behavior...

引用

21st Pacific Asia Conference on Information Systems: Societal Transformation Through IS/IT, PACIS 2017

作者： Habib, Mena B. Krol, Nynke C. Department of Data Science and Knowledge Engineering Maastricht University Netherlands Statistics Netherlands1 Netherlands

Social media has made a big impact on the tourism industry. Tourists are increasingly sharing their personal experiences of a particular touristic site scene using social media. Studying tourists’ movement behavior should support the tourism industry with more statistics and information regarding tourism demand. It would also provide policy makers with another data source on tourists and their movements. In this paper, we propose a set of heuristics to identify tourists on Twitter. We also utilized both textual contents and geolocation information of Tweets posted by tourists visiting The Netherlands and Belgium to provide a near real scenario for the tourists’ travel route made during their stay in The Netherlands and Belgium. Finally, we induce and visualize some useful statistics regarding the tourists’ visiting behavior in The Netherlands and Belgium. © PACIS 2017.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy

arXiv

引用

arXiv 2020年

作者： Ali, Sharib Dmitrieva, Mariia Ghatwary, Noha Bano, Sophia Polat, Gorkem Temizel, Alptekin Krenzer, Adrian Hekalo, Amar Guo, Yun Bo Matuszewski, Bogdan Gridach, Mourad Voiculescu, Irina Yoganand, Vishnusai Chavan, Arnav Raj, Aryan Nguyen, Nhan T. Tran, Dat Q. Huynh, Le Duy Boutry, Nicolas Rezvy, Shahadate Chen, Haijian Choi, Yoon Ho Subramanian, Anand Balasubramanian, Velmurugan Gao, Xiaohong W. Hu, Hongyu Liao, Yusheng Stoyanov, Danail Daul, Christian Realdon, Stefano Cannizzaro, Renato Lamarque, Dominique Tran-Nguyen, Terry Bailey, Adam Braden, Barbara East, James Rittscher, Jens Institute of Biomedical Engineering and Big Data Institute Old Road Campus University of Oxford Oxford United Kingdom Translational Gastroenterology Unit Experimental Medicine Div. John Radcliffe Hospital University of Oxford Oxford United Kingdom Oxford NIHR Biomedical Research Centre Oxford United Kingdom Université de Versailles St-Quentin en Yvelines Hôpital Ambroise Paré France Instituto Onclologico Veneto IOV-IRCCS Padova Italy CRO Centro Riferimento Oncologico IRCCS Aviano Italy Computer Engineering Department Arab Academy for Science and Technology Alexandria Egypt Department of Computer Science University College London London United Kingdom CRAN UMR 7039 University of Lorraine CNRS Nancy France Graduate School of Informatics Middle East Technical University Ankara Turkey Department of Artificial Intelligence and Knowledge Systems University of Würzburg Germany School of Engineering University of Central Lancashire United Kingdom Department of Computer Science University of Oxford United Kingdom Mimyk Medical Simulations Pvt Ltd Indian Institute of Science Bengaluru India Dhanbad India Hanoi Viet Nam Le Kremlin-BicêtreF-94270 France School of Science and Technology Middlesex University London United Kingdom Department of Computer Science School of Informatics Xiamen University China Sungkyunkwan University Seoul Korea Republic of Claritrics India Pvt Ltd Chennai India School of Medical Science and Technology Indian Institute of Technology KharagpurWest Bengal India Shanghai Jiaotong University Shanghai China Ibn Zohr University Computer Science HIT Agadir Morocco

The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identifying subtle precancerous precursors and cancer abnormalities. Artefacts often affect the robustness of deep learning methods applied to the gastrointestinal tract organs as they can be confused with tissue of interest. EndoCV2020 challenges are designed to address research questions in these remits. In this paper, we present a summary of methods developed by the top 17 teams and provide an objective comparison of state-of-the-art methods and methods designed by the participants for two sub-challenges: i) artefact detection and segmentation (EAD2020), and ii) disease detection and segmentation (EDD2020). Multi-center, multi-organ, multi-class, and multi-modal clinical endoscopy datasets were compiled for both EAD2020 and EDD2020 sub-challenges. The out-of-sample generalization ability of detection algorithms was also evaluated. Whilst most teams focused on accuracy improvements, only a few methods hold credibility for clinical usability. The best performing teams provided solutions to tackle class imbalance, and variabilities in size, origin, modality and occurrences by exploring data augmentation, data fusion, and optimal class thresholding techniques. © 2020, CC BY-NC-SA.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Exploration of Interpretability Techniques for Deep COVID-19 Classification using Chest X-ray Images

arXiv

引用

arXiv 2020年

作者： Chatterjee, Soumick Saad, Fatima Sarasaen, Chompunuch Ghosh, Suhita Krug, Valerie Khatun, Rupali Mishra, Rahul Desai, Nirja Radeva, Petia Rose, Georg Stober, Sebastian Speck, Oliver Nürnberger, Andreas Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Germany Faculty of Computer Science Otto von Guericke University Magdeburg Germany Genomics Research Centre Human Technopole Italy Institute for Medical Engineering Otto von Guericke University Magdeburg Germany Research Campus STIMULATE Otto von Guericke University Magdeburg Germany Biomedical Magnetic Resonance Otto von Guericke University Magdeburg Germany Artificial Intelligence Lab Otto von Guericke University Magdeburg Germany Department of Mathematics and Computer Science University of Barcelona Barcelona Spain Translational Radiobiology Department of Radiation Oncology Universitätsklinikum Erlangen Erlangen Germany Apollo Hospitals Bilaspur India HCG Cancer Centre Vadodara India Computer Vision Centre Cerdanyola Barcelona Spain Centre for Behavioural Brain Sciences Magdeburg Germany German Centre for Neurodegenerative Diseases Magdeburg Germany

The outbreak of COVID-19 has shocked the entire world with its fairly rapid spread and has challenged different sectors. One of the most effective ways to limit its spread is the early and accurate diagnosing infected patients. Medical imaging, such as X-ray and Computed Tomography (CT), combined with the potential of Artificial Intelligence (AI), plays an essential role in supporting medical personnel in the diagnosis process. Thus, in this article five different deep learning models (ResNet18, ResNet34, InceptionV3, InceptionResNetV2 and DenseNet161) and their ensemble, using majority voting have been used to classify COVID-19, pneumoniæ and healthy subjects using chest X-ray images. Multilabel classification was performed to predict multiple pathologies for each patient, if present. Firstly, the interpretability of each of the networks was thoroughly studied using local interpretability methods - occlusion, saliency, input X gradient, guided backpropagation, integrated gradients, and DeepLIFT, and using a global technique - neuron activation profiles. The mean Micro-F1 score of the models for COVID-19 classifications ranges from 0.66 to 0.875, and is 0.89 for the ensemble of the network models. The qualitative results showed that the ResNets were the most interpretable models. This research demonstrates the importance of using interpretability methods to compare different models before making a decision regarding the best performing model. Copyright © 2020, The Authors. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

s-LWSR: Super lightweight super-resolution network

arXiv

引用

arXiv 2019年

作者： Li, Biao Liu, Jiabin Wang, Bo Qi, Zhiquan Shi, Yong School of Economics and Management University of Chinese Academy of Sciences Beijing101408 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Information Technology and Management University of International Business and Economics Beijing100029 China Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States College of Information Science and Technology University of Nebraska OmahaNE68182 United States

Deep learning (DL) architectures for super-resolution (SR) normally contain tremendous parameters, which has been regarded as the crucial advantage for obtaining satisfying performance. However, with the widespread use of mobile phones for taking and retouching photos, this character greatly hampers the deployment of DL-SR models on the mobile devices. To address this problem, in this paper, we propose a super lightweight SR network: s-LWSR. There are mainly three contributions in our work. Firstly, in order to efficiently abstract features from the low resolution image, we build an information pool to mix multi-level information from the first half part of the pipeline. Accordingly, the information pool feeds the second half part with the combination of hierarchical features from the previous layers. Secondly, we employ a compression module to further decrease the size of parameters. Intensive analysis confirms its capacity of trade-off between model complexity and accuracy. Thirdly, by revealing the specific role of activation in deep models, we remove several activation layers in our SR model to retain more information for performance improvement. Extensive experiments show that our s-LWSR, with limited parameters and operations, can achieve similar performance to other cumbersome DL-SR methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Chemical activation

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：