检索结果-内蒙古大学图书馆

作者： Barash, Guy Castillo-Effen, Mauricio Chhaya, Niyati Clark, Peter Espinoza, Huáscar Farchi, Eitan Geib, Christopher Gundersen, Odd Erik Heígeartaig, Seán Ó Hernández-Orallo, José Hori, Chiori Huang, Xiaowei Jaidka, Kokil Kapanipathi, Pavan Keren, Sarah Kim, Seokhwan Lanctot, Marc Lange, Danny Martinez, David Mattar, Marwan Mausam Mcauley, Julian Michalowski, Martin Mirsky, Reuth Mottaghi, Roozbeh Osborn, Joseph C. Pérolat, Julien Schmid, Martin Shaban-Nejad, Arash Shehory, Onn Srivastava, Biplav Streilein, William Talamadupula, Kartik Togelius, Julian Yoshino, Koichiro Zhang, Quanshi Zitouni, Imed Western Digital Lockheed Martin United States Adobe Research Allen Institute for Artificial Intelligence United States Commissariat àĺÉnergie Atomique France IBM Research Haifa Israel SIFT LLC Norwegian University of Science and Technology AI Officer at TrønderEnergi Norway University of Cambridge's Centre United Kingdom Universitat Politècnica de València Spain United States Department of Computer Science University of Liverpool United Kingdom Nanyang Tech University Singapore IBM Research AI Harvard University United States Research Scientist at Adobe Research United States Research scientist at DeepMind Alberta Edmonton Canada Unity Technologies University of California San Diego United States MIT Lincoln Laboratory Unity Technologies Computer Science at Indian Institute of Technology Delhi India University of Minnesota School of Nursing United States University of Texas United States Allen Institutem for Artificial Intelligence United States Pomona College United States DeepMind London United Kingdom DeepMind Alberta Edmonton Canada University of Tennessee Health Science Center-Oak Ridge National Laboratory United States Bar Ilan University Israel IBM's ArmonkNY United States IBM Research AI Tandon School of Engineering New York University United States Japan MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Conversation understanding group at Microsoft

Affective Content Analysis and CL-Aff Shared Task: In Pursuit of Happiness The Affective Content Analysis workshop series held at the AAai Conference on Artificial Intelligence is an interdisciplinary platform intended to engage the ai and machinelearning communities about open problems in affective content analysis and understanding, with a special focus on affect in language and text. The theme of this second workshop was modeling affect-in-action, with a shared task (CL-Aff-in pursuit of happiness) to encourage the development of new models and approaches for modeling happy moments. Copyright © 2019, Association for the Advancement of Artificial Intelligence.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Dual co-matching network for multi-choice reading comprehension

arXiv

引用

arXiv 2019年

作者： Zhang, Shuailiang Zhao, Hai Wu, Yuwei Zhang, Zhuosheng Zhou, Xi Zhou, Xiang Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China CloudWalk Technology Shanghai China

Multi-choice reading comprehension is a challenging task to select an answer from a set of candidates when given passage and question. This work proposes dual co-matching network which models the relationship among passage, question and answer bidirectionally. The experimental results on RACE, ROCStories and COIN Shared Task 1 show that our model obtains state-of-the-art results and even the single model outperforms the human performance on RACE dataset. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Fully decentralized multi-agent reinforcement learning with networked agents

arXiv

引用

arXiv 2018年

作者： Zhang, Kaiqing Yang, Zhuoran Liu, Han Zhang, Tong Başar, Tamer Department of Electrical and Computer Engineering & Coordinated Science Laboratory University of Illinois at Urbana-Champaign Department of Operations Research and Financial Engineering Princeton University Department of Electrical Engineering and Computer Science and Statistics Northwestern University Tencent AI Lab

We consider the problem of fully decentralized multi-agent reinforcement learning (MARL), where the agents are located at the nodes of a time-varying communication network. Specifically, we assume that the reward functions of the agents might correspond to different tasks, and are only known to the corresponding agent. Moreover, each agent makes individual decisions based on both the information observed locally and the messages received from its neighbors over the network. Within this setting, the collective goal of the agents is to maximize the globally averaged return over the network through exchanging information with their neighbors. To this end, we propose two decentralized actor-critic algorithms with function approximation, which are applicable to large-scale MARL problems where both the number of states and the number of agents are massively large. Under the decentralized structure, the actor step is performed individually by each agent with no need to infer the policies of others. For the critic step, we propose a consensus update via communication over the network. Our algorithms are fully incremental and can be implemented in an online fashion. Convergence analyses of the algorithms are provided when the value functions are approximated within the class of linear functions. Extensive simulation results with both linear and nonlinear function approximations are presented to validate the proposed algorithms. Our work appears to be the first study of fully decentralized MARL algorithms for networked agents with function approximation, with provable convergence guarantees. Copyright © 2018, 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

The Brain Tumor Segmentation in Pediatrics (BraTS-PEDs) Challenge: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCai BraTS-PEDs)

arXiv

引用

arXiv 2024年

作者： Kazerooni, Anahita Fathi Khalili, Nastaran Liu, Xinyang Gandhi, Deep Jiang, Zhifan Anwar, Syed Muhammed Albrecht, Jake Adewole, Maruf Anazodo, Udunna Anderson, Hannah Baid, Ujjwal Bergquist, Timothy Borja, Austin J. Calabrese, Evan Chung, Verena Conte, Gian-Marco Dako, Farouk Eddy, James Ezhov, Ivan Familiar, Ariana Farahani, Keyvan Franson, Andrea Gottipati, Anurag Haldar, Shuvanjan Iglesias, Juan Eugenio Janas, Anastasia Johansen, Elaine Jones, Blaise V. Khalili, Neda Kofler, Florian LaBella, Dominic Lai, Hollie Anne Van Leemput, Koen Li, Hongwei Bran Maleki, Nazanin McAllister, Aaron S. Meier, Zeke Menze, Bjoern Moawad, Ahmed W. Nandolia, Khanak K. Pavaine, Julija Piraud, Marie Poussaint, Tina Prabhu, Sanjay P. Reitman, Zachary Rudie, Jeffrey D. Sanchez-Montano, Mariana Shaikh, Ibraheem Salman Sheth, Nakul Tu, Wenxin Wang, Chunhao Ware, Jeffrey B. Wiestler, Benedikt Zapaishchykova, Anna Bornhorst, Miriam Deutsch, Michelle Fouladi, Maryam Lazow, Margot Mikael, Leonie Hummel, Trent Kann, Benjamin de Blank, Peter Hoffman, Lindsey Aboian, Mariam Nabavizadeh, Ali Packer, Roger Bakas, Spyridon Resnick, Adam Rood, Brian Vossough, Arastoo Linguraru, Marius George Children’s Hospital of Philadelphia PhiladelphiaPA United States Department of Neurosurgery University of Pennsylvania PhiladelphiaPA United States University of Pennsylvania PhiladelphiaPA United States Sheikh Zayed Institute for Pediatric Surgical Innovation Children’s National Hospital WashingtonDC United States Sage Bionetworks United States Lab Crestview Radiology Lagos Nigeria McGill University MontrealQC Canada Department of Radiology Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Division of Computational Pathology Department of Pathology and Laboratory Medicine Indiana University School of Medicine IndianapolisIN United States Department of Neurosurgery The University of Southern California CA United States Department of Radiology Duke University Medical Center DurhamNC United States Mayo Clinic MN United States Center for Global Health Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Informatics Technical University Munich Germany TranslaTUM - Central Institute for Translational Cancer Research Technical University of Munich Germany Cancer Imaging Program National Cancer Institute National Institutes of Health BethesdaMD United States C. S. Mott Children’s Hospital University of Michigan MI United States Biomedical Engineering Rutgers University New BrunswickNJ United States Athinoula A Martinos Center for Biomedical Imaging Massachusetts General Hospital BostonMA United States Yale University New HavenCT United States PrecisionFDA U.S. Food and Drug Administration Silver SpringMD United States Cincinnati Children’s Hospital Medical Center OH United States Helmholtz AI Helmholtz Munich Germany Department of Radiation Oncology Duke University Medical Center DurhamNC United States Department of Radiology Children’s Health Orange County CA United States Department of Applied Mathematics and Computer Science Technical University of De

Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCai BraTS-PEDs challenge, focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The CBTN-CONNECT-DIPGR-ASNR-MICCai BraTS-PEDs challenge brings together clinicians and ai/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DCMN+: Dual Co-matching network for multi-choice reading comprehension

arXiv

引用

arXiv 2019年

Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question. Previous approaches usually only calculate question-aware passage representation and ignore passage-aware question representation when modeling the relationship between passage and question, which obviously cannot take the best of information between passage and question. In this work, we propose dual co-matching network (DCMN) which models the relationship among passage, question and answer options bidirectionally. Besides, inspired by how human solve multi-choice questions, we integrate two reading strategies into our model: (i) passage sentence selection that finds the most salient supporting sentences to answer the question, (ii) answer option interaction that encodes the comparison information between answer options. DCMN integrated with the two strategies (DCMN+) obtains state-of-the-art results on five multi-choice reading comprehension datasets which are from different domains: RACE, SemEval-2018 Task 11, ROCStories, COIN, MCTest. Copyright © 2019, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning methods for lung cancer segmentation in whole-slide histopathology images - The ACDC@lungHP challenge 2019

arXiv

引用

arXiv 2020年

作者： Li, Zhang Zhang, Jiehua Tan, Tao Teng, Xichao Sun, Xiaoliang Li, Yang Liu, Lihong Xiao, Yang Lee, Byungjae Li, Yilong Zhang, Qianni Sun, Shujiao Zheng, Yushan Yan, Junyu Li, Ni Hong, Yiyu Ko, Junsu Jung, Hyun Liu, Yanling Chen, Yu-Cheng Wang, Ching-Wei Yurovskiy, Vladimir Maevskikh, Pavel Khanagha, Vahid Jiang, Yi Feng, Xiangjun Liu, Zhihong Li, Daiqiang Schüffler, Peter J. Yu, Qifeng Chen, Hui Tang, Yuling Litjens, Geert College of Aerospace Science and Engineering National University of Defense Technology Changsha410073 China Department of Mathematics and Computer Science Eindhoven University of Technology Netherlands and ScreenPoint Medical Eindhoven Nijmegen5600 MB Netherlands Pingan Technology Shenzhen China Lunit Inc. Seoul Korea Republic of School of Electrical Engineering and Computer Science Queen Mary University of London London United Kingdom Image Processing Center School of Astronautics Beihang University Beijing102206 China Beijing Advanced Innovation Center for Biomedical Engineering Beijing100191 China Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Image Processing Center School of Astronautics Beihang University Beijing102206 China AstLab School of Automatationm Beihang University Beijing China Department of R&D Center Arontier Co. Ltd. Seoul Korea Republic of Frederick National Laboratory United States Center of Computer Vision and Medical Imaging Graduate Institute of Biomedical Engineering Graduate institute of Applied Science and Technology National Taiwan University of Science and Technology AI Explore Taipei Taiwan Research Department Sky-chain Global Yekaterinburg Russia Audio Solutions Team Motorola Solutions Inc. PlantationFL United States Second Xiangya Hospital Central South University Changsha China Hunan Biotechnology Ltd. Changsha China Hunan Cancer Hospital Central South University Changsha China Memorial Sloan Kettering Cancer Center United States First Hospital of Changsha City Changsha China Radboud University Medical Center Nijmegen Netherlands

Accurate segmentation of lung cancer in pathology slides is a critical step in improving patient care. We proposed the ACDC@LungHP (Automatic Cancer Detection and Classification in Whole-slide Lung Histopathology) challenge for evaluating different computer-aided diagnosis (CADs) methods on the automatic diagnosis of lung cancer. The ACDC@LungHP 2019 focused on segmentation (pixel-wise detection) of cancer tissue in whole slide imaging (WSI), using an annotated dataset of 150 training images and 50 test images from 200 patients. This paper reviews this challenge and summarizes the top 10 submitted methods for lung cancer segmentation. All methods were evaluated using the false positive rate, false negative rate, and DICE coefficient (DC). The DC ranged from 0.7354±0.1149 to 0.8372±0.0858. The DC of the best method was close to the inter-observer agreement (0.8398±0.0890). All methods were based on deep learning and categorized into two groups: multi-model method and single model method. In general, multi-model methods were significantly better (p Copyright © 2020, The Authors. All rights reserved.

关键词： Biological organs

来源：评论

学校读者我要写书评

暂无评论

Open named entity modeling from embedding distribution

arXiv

引用

arXiv 2019年

作者： Luo, Ying Zhao, Hai Zhang, Zhuosheng Tang, Bingjie The Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Minhang District Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University 800 Dongchuan Road Minhang District Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University 800 Dongchuan Road Minhang District Shanghai China The Department of Computer Science University of Southern California United States

In this paper, we report our discovery on named entity distribution in a general word embedding space, which helps an open definition on multilingual named entity definition rather than previous closed and constraint definition on named entities through a named entity dictionary, which is usually derived from human labor and replies on schedule update. Our initial visualization of monolingual word embeddings indicates named entities tend to gather together despite of named entity types and language difference, which enable us to model all named entities using a specific geometric structure inside embedding space, namely, the named entity hypersphere. For monolingual cases, the proposed named entity model gives an open description of diverse named entity types and different languages. For cross-lingual cases, mapping the proposed named entity model provides a novel way to build a named entity dataset for resource-poor languages. At last, the proposed named entity model may be shown as a handy clue to enhance state-of-the-art named entity recognition systems generally. Copyright © 2019, 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

Computing Image Intersection and Union Regions for Drosophila Neurons Based on Multi-core CPUs 16th

Computing Image Intersection and Union Regions for Drosophil...

引用

16th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2019

作者： Guo, Ming-Yan Cheng, Hui-Jun Lin, Chun-Yuan Lin, Yen-Jen Chiang, Ann-Shyn Department of Computer Science and Information Engineering Chang Gung University Taoyuan33302 Taiwan AI Innovation Research Center Chang Gung University Taoyuan33302 Taiwan Division of Rheumatology Allergy and Immunology Chang Gung Memorial Hospital Taoyuan33302 Taiwan National Center for High-Performance Computing Hsinchu30076 Taiwan Brain Research Center National Tsing Hua University Hsinchu30013 Taiwan Institute of Biotechnology and Department of Life Science National Tsing Hua University Hsinchu30013 Taiwan Kavli Institute for Brain and Mind University of California at San Diego La Jolla San DiegoCA United States Department of Biomedical Science and Environmental Biology Kaohsiung Medical University Kaohsiung80708 Taiwan Genomics Research Center Academia Sinica NankangTaipei11529 Taiwan

ISBN: (纸本)9783030301422

With more and more Drosophila Driver and Neuron images, it is an important work to find the similarity relationships among them as the functional inference. There is a general problem that how to find a Drosophila Driver image, which can cover a set of Drosophila Neuron images. In order to solve this problem, the intersection/union region for a set of Drosophila Neuron images should be computed at first, then a comparison work is used to calculate the similarities between the region and Drosophila Driver image(s). In this paper, three encoding schemes, namely Integer, Boolean, Decimal, are proposed to encode each Drosophila Driver and Neuron image as a one-dimensional structure, respectively. Then, the intersection/union region from these images can be computed by using the various operations, such as Boolean operators and lookup-table search method. Finally, the comparison work is done as the union region computation, and the similarity score can be calculated by the definition of Tanimoto coefficient. The above methods for the region computation are also implemented in the multi-core CPUs environment with the OpenMP. From the experimental results, in the encoding phase, the performance by Boolean scheme is the best than that by others;in the region computation phase, the performance by Decimal is the best when the number of images is large. The speedup ratio can achieve 13 based on 16 CPUs. © 2019, Springer Nature Switzerland AG.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Machine learning–based detection model of early Alzheimer's disease using wearable device and gait assessment

引用

Alzheimer's & Dementia 2021年第S5期17卷

作者： YoungHoon Jeon Thi Kieu Khanh Ho Jaeyong Kang Byeong C. Kim Kun Ho Lee Jong-In Song Jeonghwan Gwak School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Gwangju South Korea Department of Software Korea National University of Transportation Chungju South Korea Department of Neurology Chonnam National University Medical School Gwangju South Korea Department of Biomedical Science Chosun University Gwangju South Korea Aging Neuroscience Research Group Korea Brain Research Institute Daegu South Korea Gwangju Alzheimer’s Disease and Related Dementia Cohort Research Center Chosun University Gwangju South Korea Department of IT & Energy Convergence (BK21 FOUR) Korea National University of Transportation Chungju South Korea Department of AI Robotics Engineering Korea National University of Transportation Chungju South Korea Department of Biomedical Engineering Korea National University of Transportation Chungju South Korea

Background A method for diagnosing early stages of Alzheimer's disease (AD) is developed by analyzing human gait and training a machine learning classifier using signals obtained from inertial measurement unit. This patient-friendly and cost-effective method enables periodic monitoring, contributing to savings in treatment costs and effort. Method 145 subjects (77 healthy controls, 68 Mild Cognitive Impairment) were employed to perform seven types of gait paradigms, including normal and complex walking. The gait of the employed subjects was measured by 7 shimmer devices, which consist of a three-dimensional accelerometer and gyroscope. The acquired signal data is converted into 35 features including gait cycle. The extracted features are used to train an ensemble classifier based on machine learning with an oversampling method. In order to find the optimal combination in the ensemble model, an elimination technique was used to compare performance by removing single classifiers one by one. For performance comparison, the dataset is divided into training set/test set by leave-one-patient-out cross-validation, and several metrics such as accuracy and F1 score are used. Result The classifier for MCI detection classified severity to an accuracy of about 0.7 for 145 subjects. The combination of oversampling techniques and different single classifiers contributes to improved performance. In the seven walking experimental paradigms, the accuracy of the classification of normal walking without subtasks is about 0.67. O the other hand, the classification of walking with associative word-speaking or counting numbers shows significant results with accuracy of 0.7413 and 0.7338, respectively. Conclusion Our proposed method predicts severity through efficient walking with less space-time constraints. Subtasks that stress the brain in walking contribute to the performance improvement of the ensemble model with oversampling. These results demonstrate that our proposed method with g

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta-Learning Techniques to Analyze the Raman Data for Optical Diagnosis of Oral Cancer Detection

Meta-Learning Techniques to Analyze the Raman Data for Optic...

引用

IEEE International Symposium on Parallel and Distributed Processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Mukta Sharma Lokesh Sharma Ming-Jer Jeng Liann-Be Chang Shiang-Fu Huang Shih-Lin Wu Department of Electronic Engineering Chang Gung University Taoyuan Taiwan AI Innovation Research Center Chang Gung University Taoyuan Department of Otolaryngology-Head and Neck Surgery Chang Gung Memorial Hospital Linkou Taiwan Department of Public Health Chang Gung University Taoyuan Taiwan Department of Cardiology Chang Gung Memorial Hospital Taoyuan Department of Electrical Engineering Ming Chi University of technology New Taipei City Taiwan Department of Computer Science and Information Engineering Chang Gung University Taoyuan Taiwan

ISBN: (纸本)9781728152103

Recently, Machine Learning methods have shown great improvement while analyzing the biomedical data. Raman Spectroscopy (RS), a non-invasive technique, and widely used in screening to diagnose the oral cancer. In order to spot cancer in a smarter and faster way, we have employed Meta-Learning (ml) techniques to learn such as Bagging and Boosting on RS data. Further, we employed normal and tumor tissue class classification by Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA) and Adaptive Boosting (AdaBoost) classifiers. The present study aims at examining the RS data with total 110 samples, including 57 tumor and 53 normal ones. To evaluate the performance, we have used the training samples to optimize, and testing samples to generalize the model parameters. The results show that the AdaBoost classifier with Bagging techniques showed the significant changes in accuracy.

关键词： biomedical optical imaging cancer image classification learning (artificial intelligence) medical image processing tumours Biomedical optical imaging Medical image processing Image classification Tumours Mouth Neoplasms Malignant Oral Cavity Tumor cancer test OPTICAL DIAGNOSTICS Boost bagging PURSE

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：