检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Hao, Fusheng Cheng, Jun Wang, Lei Wang, Xinchao Cao, Jianzhong Hu, Xiping Tao, Dapeng Xi'an Institute of Optics and Precision Mechanics CAS China University of Chinese Academy of Sciences Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology CAS Department of Computer Science Stevens Insititute of Technology

Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly enforced. In this paper, we propose a novel approach to train deep CNNs by imposing the intra-class compactness and the inter-class separability, so as to enhance the learned features' discriminant power. To this end, we introduce anchors, which are predefined vectors regarded as the centers for each class and fixed during training. Discriminative features are obtained by constraining the deep CNNs to map training samples to the corresponding anchors as close as possible. We propose two principles to select the anchors, and measure the proximity of two points using the Euclidean and cosine distance metric functions, which results in two novel loss functions. These loss functions require no sample pairs or triplets and can be efficiently optimized by batch stochastic gradient descent. We test the proposed method on three benchmark image classification datasets and demonstrate its promising results. Copyright © 2018, The Authors. All rights reserved.

关键词： Anchors

来源：评论

学校读者我要写书评

暂无评论

Compare and Model Multi-level Stereoscopic 3D Visual Fatigue Based on EEG

Compare and Model Multi-level Stereoscopic 3D Visual Fatigue...

引用

SID Symposium, Seminar, and Exhibition 2017, Display Week 2017

作者： Yue, Kang Wang, Danli Hu, Haichen Yang, Xinpan Chiu, Steve C. State Key Laboratory of Computer Institute of Software Chinese Academy of Sciences Beijing China Beijing Key Lab of Human-Computer Interaction Institute of Software Chinese Academy of Sciences Beijing China College of Science and Engineering Idaho State University Pocatello United States

ISBN: (纸本)9781510848757

In this paper, we designed an experiment to observe changes for different fatigue level in human brain when watching random dot stereogram (RDS) using the method of EEG. The subjects were asked to watch 3D content for 30 minutes and the disparity of RDS changed every 10 seconds. During this watching task, subjects should rate their extent of fatigue during the experiment on the scale of one to five only when they felt worse or better. 30 channels electroencephalogram (EEG) signals were recorded through the experiment. Finally, the relationship between various fatigue levels and disparities which revealed by EEG signals were investigated. Our results show that the power of waveband, namely alpha increased with the fatigue level increasing from one to four during watching RDS, but decreased in level five. We have employed logistic regression to model fatigue level and achieved classification accuracy of 94.18%. Our research has important implications for the continuous monitoring of user's fatigue in the future. © 2017 SID.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Chinese pinyin aided IME, input what you have not keystroked yet

arXiv

引用

arXiv 2018年

作者： Huang, Yafang Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China

Chinese pinyin input method engine (IME) converts pinyin into character so that Chinese characters can be conveniently inputted into computer through common keyboard. IMEs work relying on its core component, pinyinto-character conversion (P2C). Usually Chinese IMEs simply predict a list of character sequences for user choice only according to user pinyin input at each turn. However, Chinese inputting is a multi-Turn online procedure, which can be supposed to be exploited for further user experience promoting. This paper thus for the first time introduces a sequenceto-sequence model with gated-Attention mechanism for the core task in IMEs. The proposed neural P2C model is learned by encoding previous input utterance as extra context to enable our IME capable of predicting character sequence with incomplete pinyin input. Our model is evaluated in different benchmark datasets showing great user experience improvement compared to traditional models, which demonstrates the first engineering practice of building Chinese aided IME. Copyright © 2018, 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

Lingke: A fine-grained multi-turn chatbot for customer service

arXiv

引用

arXiv 2018年

作者： Zhu, Pengfei Zhang, Zhuosheng Li, Jiangtong Huang, Yafang Zhao, Hai School of Computer Science and Software Engineering East China Normal University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China College of Zhiyuan Shanghai Jiao Tong University China

Traditional chatbots usually need a mass of human dialogue data, especially when using supervised machine learning method. Though they can easily deal with single-turn question answering, for multi-turn the performance is usually unsatisfactory. In this paper, we present Lingke, an information retrieval augmented chatbot which is able to answer questions based on given product introduction document and deal with multi-turn conversations. We will introduce a finegrained pipeline processing to distill responses based on unstructured documents, and attentive sequential context-response matching for multi-turn conversations. Copyright © 2018, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Erratum to: 'Inhibition of the renal apical sodium dependent bile acid transporter prevents cholemic nephropathy in mice with obstructive cholestasis' [J Hepatol (2024) 80:268-281]

引用

Journal of hepatology 2025年第6期82卷 1140-1140页

作者： Ahmed Ghallab Daniela González Ellen Strängberg Ute Hofmann Maiju Myllys Reham Hassan Zaynab Hobloss Lisa Brackhagen Brigitte Begher-Tibbe Julia C Duda Carolin Drenda Franziska Kappenberg Joerg Reinders Adrian Friebel Mihael Vucur Monika Turajski Abdel-Latief Seddek Tahany Abbas Noha Abdelmageed Samy A F Morad Walaa Morad Amira Hamdy Wiebke Albrecht Naim Kittana Mohyeddin Assali Nachiket Vartak Christoph van Thriel Ansam Sous Patrick Nell Maria Villar-Fernandez Cristina Cadenas Erhan Genc Rosemarie Marchan Tom Luedde Peter Åkerblad Jan Mattsson Hanns-Ulrich Marschall Stefan Hoehme Guido Stirnimann Matthias Schwab Peter Boor Kerstin Amann Jessica Schmitz Jan H Bräsen Jörg Rahnenführer Karolina Edlund Saul J Karpen Benedikt Simbrunner Thomas Reiberger Mattias Mandorfer Michael Trauner Paul A Dawson Erik Lindström Jan G Hengstler Department of Toxicology Leibniz Research Centre for Working Environment and Human Factors Technical University Dortmund Ardeystr. 67 44139 Dortmund Germany Department of Forensic Medicine and Toxicology Faculty of Veterinary Medicine South Valley University 83523 Qena Egypt. Electronic address: ghallab@ifado.de. Department of Toxicology Leibniz Research Centre for Working Environment and Human Factors Technical University Dortmund Ardeystr. 67 44139 Dortmund Germany. Albireo Pharma Inc. Boston MA 02109 USA. Dr. Margarete Fischer-Bosch Institute of Clinical Pharmacology and University of Tübingen Auerbachstr. 112 70376 Stuttgart Germany. Department of Forensic Medicine and Toxicology Faculty of Veterinary Medicine South Valley University 83523 Qena Egypt. Department of Statistics TU Dortmund University 44227 Dortmund Germany. Institute of Computer Science & Saxonian Incubator for Clinical Research (SIKT) University of Leipzig Haertelstraße 16-18 04107 Leipzig Germany. Department of Gastroenterology Hepatology and Infectious Diseases University Hospital Duesseldorf Medical Faculty at Heinrich-Heine-University 40225 Dusseldorf Germany. Histology Department Faculty of Medicine South Valley University 83523 Qena Egypt. Department of Pharmacology Faculty of Veterinary Medicine Sohag University 82524 Sohag Egypt. Department of Pharmacology Faculty of Veterinary Medicine South Valley University 83523 Qena Egypt. Department of Biomedical Sciences An-Najah National University P.O. Box 7 Nablus Palestine. Department of Pharmacy An-Najah National University P.O. Box 7 Nablus Palestine. MRI Unit Leibniz Research Centre for Working Environment and Human Factors Department of Psychology and Neurosciences Technical University Dortmund 44139 Dortmund Germany. Department of Molecular and Clinical Medicine/Wallenberg Laboratory Sahlgrenska Academy University of Gothenburg 41345 Gothenburg Sweden. University Clinic for Visceral Surgery and Medicine Inselspital Univers

来源：评论

学校读者我要写书评

暂无评论

Technology for underserved communities;personal fabrication: Expert-curated guides to the best of CS research

引用

Queue 2017年第2期15卷

作者： Bailis, Peter Dillahunt, Tawanna Mueller, Stefanie Baudisch, Patrick Department of Computer Science Stanford University United States University of Michigan's School of Information United States MIT's Electrical Engineering Computer Science Department United States Department of Computer Science Hasso Plattner Institute Potsdam University Germany Department of the Human Computer Interaction Lab. United States

Research for Practice combines the resources of the ACM Digital Library, the largest collection of computer science research in the world, with the expertise of the ACM membership. In every RfP column two experts share a short curated selection of papers on a concentrated, practically oriented topic. Copyright © 2017 held by owner/author. Publication rights licensed to ACM.

关键词： Digital libraries

来源：评论

学校读者我要写书评

暂无评论

Affordable on-line dialogue policy learning

Affordable on-line dialogue policy learning

引用

2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017

作者： Chang, Cheng Yang, Runzhe Chen, Lu Zhou, Xiang Yu, Kai Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781945626838

The key to building an evolvable dialogue system in real-world scenarios is to ensure an affordable on-line dialogue policy learning, which requires the on-line learning process to be safe, efficient and economical. But in reality, due to the scarcity of real interaction data, the dialogue system usually grows slowly. Besides, the poor initial dialogue policy easily leads to bad user experience and incurs a failure of attracting users to contribute training data, so that the learning process is unsustainable. To accurately depict this, two quantitative metrics are proposed to assess safety and efficiency issues. For solving the unsustainable learning problem, we proposed a complete companion teaching framework incorporating the guidance from the human teacher. Since the human teaching is expensive, we compared various teaching schemes answering the question how and when to teach, to economically utilize teaching budget, so that make the online learning process affordable. © 2017 Association for Computational Linguistics.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

On-line dialogue policy learning with companion teaching 15

On-line dialogue policy learning with companion teaching

引用

15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017

作者： Chen, Lu Runzhe, Yang Cheng, Chang Ye, Zihao Zhou, Xiang Yu, Kai Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781510838604

On-line dialogue policy learning is the key for building evolvable conversational agent in real world scenarios. Poor initial policy can easily lead to bad user experience and consequently fail to attract sufficient real users for policy training. We propose a novel framework, companion teaching, to include a human teacher in the on-line dialogue policy training loop to address the cold start problem. Here, dialogue policy is trained using not only user's reward but also teacher's example action as well as estimated immediate reward at turn level. Simulation experiments showed that, with a small number of human teaching dialogues, the proposed approach can effectively improve user experience at the beginning and smoothly lead to good performance with more user interaction data. © 2017 Association for Computational Linguistics.

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

Agent-aware dropout DQN for safe and efficient on-line dialogue policy learning

Agent-aware dropout DQN for safe and efficient on-line dialo...

引用

2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017

作者： Chen, Lu Zhou, Xiang Chang, Cheng Yang, Runzhe Yu, Kai Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781945626838

Hand-crafted rules and reinforcement learning (RL) are two popular choices to obtain dialogue policy. The rule-based policy is often reliable within predefined scope but not self-adaptable, whereas RL is evolvable with data but often suffers from a bad initial performance. We employ a companion learning framework to integrate the two approaches for on-line dialogue policy learning, in which a predefined rule-based policy acts as a teacher and guides a data-driven RL system by giving example actions as well as additional rewards. A novel agent-aware dropout Deep Q-Network (AAD-DQN) is proposed to address the problem of when to consult the teacher and how to learn from the teacher’s experiences. AAD-DQN, as a data-driven student policy, provides (1) two separate experience memories for student and teacher, (2) an uncertainty estimated by dropout to control the timing of consultation and learning. Simulation experiments showed that the proposed approach can significantly improve both safety and efficiency of on-line policy optimization compared to other companion learning approaches as well as supervised pre-training using static dialogue corpus. © 2017 Association for Computational Linguistics.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Modeling Multi-turn conversation with deep utterance aggregation

arXiv

引用

arXiv 2018年

作者： Zhang, Zhuosheng Li, Jiangtong Zhu, Pengfei Zhao, Hai Liu, Gongshen Department of Computer Science and Engineering Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 College of Zhiyuan Shanghai Jiao Tong University School of Cyber Security Shanghai Jiao Tong University School of Computer Science and Software Engineering East China Normal University

Multi-turn conversation understanding is a major challenge for building intelligent dialogue systems. This work focuses on retrieval-based response matching for multi-turn conversation whose related work simply concatenates the conversation utterances, ignoring the interactions among previous utterances for context modeling. In this paper, we formulate previous utterances into context using a proposed deep utterance aggregation model to form a fine-grained context representation. In detail, a self-matching attention is first introduced to route the vital information in each utterance. Then the model matches a response with each refined utterance and the final matching score is obtained after attentive turns aggregation. Experimental results show our model outperforms the state-of-the-art methods on three multi-turn conversation benchmarks, including a newly introduced e-commerce dialogue corpus. Copyright © 2018, The Authors. All rights reserved.

关键词： Speech processing

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：