检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Iman, Mohammadreza Miller, John A. Rasheed, Khaled Branch, Robert M. Arabnia, Hamid R. Department of Computer Science Franklin College of Arts and Sciences University of Georgia AthensGA United States Institute for Artificial Intelligence Franklin College of Arts and Sciences University of Georgia AthensGA United States Learning Design and Technology Mary Frances Early College of Education University of Georgia AthensGA United States

Deep transfer learning (DTL) techniques try to tackle the limitations of deep learning, the dependency on extensive training data and the training costs, by reusing obtained knowledge from source data for target data. However, the current DTL techniques suffer from either catastrophic forgetting dilemma (losing the previously obtained knowledge) or overly biased pre-trained models (harder to adapt to target data) in finetuning pre-trained models or freezing a part of the pre-trained model, respectively. Progressive learning, a sub-category of DTL, reduces the effect of the overly biased model in the case of freezing earlier layers by adding a new layer to the end of a frozen pre-trained model. Even though it has been successful in many cases, it cannot yet handle distant source and target data. We propose a new continual/progressive learning approach for deep transfer learning to tackle these limitations. To avoid both catastrophic forgetting dilemma and overly biased-model problem, we expand the pre-trained model by expanding pre-trained layers (adding new nodes to each layer) in the model instead of only adding new layers. Hence the method is named EXPANSE. Our experimental results confirm that we can tackle distant source and target data using this technique. At the same time, the final model is still valid on the source data, achieving a promising deep continual learning approach. Moreover, we offer a new way of training deep learning models inspired by the human education system. We termed this two-step training: learning basics first, then adding complexities and uncertainties. The evaluation implies that the two-step training extracts more meaningful features and a finer basin on the error surface since it can achieve better accuracy in comparison to regular training. EXPANSE (model expansion and two-step training) is a systematic continual learning approach applicable to different problems and DL models. Copyright © 2022, The Authors. All rights reserved.

关键词： Freezing

来源：评论

学校读者我要写书评

暂无评论

AI-based sensor layout for predicting thermal deformations of CFRP machine tools

引用

CIRP Annals 2025年

作者： Finkeldey, Felix Kato, Makoto Wiederkehr, Petra Kakinuma, Yasuhiro Virtual Machining Department of Computer Science TU Dortmund University Dortmund Germany Lamarr Institute for Machine Learning and Artificial Intelligence Dortmund Germany Department of System Design Engineering Faculty of Science & Technology Keio University Yokohama Kohoku-ku Japan

Using data-based approaches, accurate predictions of thermal deformations, which can significantly affect the quality of manufactured components, can be enabled. However, a sufficient amount of data with maximised information content is necessary for efficient training. In this paper, an approach for optimising sensor configurations for predicting thermal deformations is presented. From initially 300 temperature sensors, the number of required sensors was significantly reduced while maintaining predictive accuracy. Furthermore, a pattern for sensor placement was identified, providing the potential for an efficient sensor layout that enables cost-effective data acquisition and improved monitoring of machining and wear progression of machine tool components. © 2025 The Authors

关键词： Metal working tools

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Virtual Reality for Child Pedestrian Safety Training: A Case Study in China

Exploring the Potential of Virtual Reality for Child Pedestr...

引用

International Symposium on Educational technology (ISET)

作者： Qinna Feng Gege Li Tingting Yang Heng Luo School of Educational Information Technology Central China Normal University Wuhan China Department of Learning Design and Technology University of Georgia Georgia USA

ISBN: (数字)9781728171890

ISBN: (纸本)9781728171906

This study explores the potential of using virtual reality in conducting child pedestrian safety training by designing and implementing a VR-based training intervention in three elementary schools in China, located in urban, rural, and fringe area respectively. The results suggested enhanced authenticity and interactivity as two technical affordances of VR, which enabled risky behavior diagnosis and personalized remedial instruction. The increased pedestrian performance among children during and after the VR intervention supported its efficacy as an innovative training program. Additionally, the empirical results indicated a limited impact of school location and family SES on children's pedestrian performance, highlighting the need for a universal pedestrian safety training curriculum for elementary schools nationwide.

关键词： Training Safety Green products Virtual environments Interviews

来源：评论

学校读者我要写书评

暂无评论

Physics-informed Bayesian optimization of variational quantum circuits 23

Physics-informed Bayesian optimization of variational quantu...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Kim A. Nicoli Christopher J. Anders Lena Funcke Tobias Hartung Karl Jansen Stefan Kühn Klaus-Robert Müller Paolo Stornati Pan Kessel Shinichi Nakajima Transdisciplinary Research Area (TRA) Matter University of Bonn Germany and Helmholtz Institute for Radiation and Nuclear Physics (HISKP) and Berlin Institute for the Foundations of Learning and Data (BIFOLD) Berlin Institute for the Foundations of Learning and Data (BIFOLD) and Technische Universität Berlin Germany Transdisciplinary Research Area (TRA) Matter University of Bonn Germany and Helmholtz Institute for Radiation and Nuclear Physics (HISKP) Northeastern University London UK and Khoury College of Computer Sciences Northeastern University CQTA Deutsches Elektronen-Synchrotron (DESY) Zeuthen Germany Berlin Institute for the Foundations of Learning and Data (BIFOLD) and Technische Universität Berlin Germany and Department of Artificial Intelligence Korea University Korea and Max Planck Institut für Informatik Saarbrücken Germany Institute of Photonic Sciences The Barcelona Institute of Science and Technology (ICFO) Prescient Design gRED Roche Switzerland Berlin Institute for the Foundations of Learning and Data (BIFOLD) and Technische Universität Berlin Germany and RIKEN Center for AIP Japan

In this paper, we propose a novel and powerful method to harness Bayesian optimization for Variational Quantum Eigensolvers (VQEs)—a hybrid quantum-classical protocol used to approximate the ground state of a quantum Hamiltonian. Specifically, we derive a VQE-kernel which incorporates important prior information about quantum circuits: the kernel feature map of the VQE-kernel exactly matches the known functional form of the VQE's objective function and thereby significantly reduces the posterior uncertainty. Moreover, we propose a novel acquisition function for Bayesian optimization called Expected Maximum Improvement over Confident Regions (EMICoRe) which can actively exploit the inductive bias of the VQE-kernel by treating regions with low predictive uncertainty as indirectly "observed". As a result, observations at as few as three points in the search domain are sufficient to determine the complete objective function along an entire one-dimensional subspace of the optimization landscape. Our numerical experiments demonstrate that our approach improves over state-of-the-art baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating STEAM into picture book creation to the action research of practicing university social responsibility

引用

AIP Conference Proceedings 2023年第1期2685卷

作者： Wenchih Chou Ying-Hsin Liang Feng-Hwang Lin Department of Industrial Design Chaoyang University of Technology Wufeng District Taichung 413310 Taiwan Department of MAA Nan Kai University of Technology Caotun Town Nantou County 542021 Taiwan Wufeng Senior Citizens Learning Center Wufeng District Taichung 413004 Taiwan

This research is based on the spirit of university social responsibility, and uses the professional knowledge and skills of teachers and students to solve local problems. In the process, the resources of the "Nankai Three-Creation learning Center" are used to form strategic alliances with the teachers and students of community elementary schools, middle schools, and high schools. The mechanism of co-cultivation and co-learning is used to implement the SDGs "education" indicators to promote the community's "media literacy" and "lifelong/senior learning" cultivation goals. Co-learning partners started with community dialogues and due to the 12-year new national education syllabus emphasizes literacy-oriented and hands-on cultivation goals, researchers use STEAM into the solicitation activities of picture book creation to cultivate students’ ability to perceive the living environment of the community and perceive the community. In addition to the process of solving community problems or needs, the school's teaching energy is improved, and the community environment and ecology issues are deeply cultivated to enhance the motivation for sustainable development of the campus. In the research, the teaching strategies of integrating STEAM into the picture book creation process are summarized as follows: use scientific (S) literacy to carry out the language expression of story narration and the ability of ecological observation and exploration; use technology (T) literacy to expressed the selection skill of coloring tools, paints and materials in picture books; use engineering (E) literacy to realize the process of hands-on work; use artistic (A) literacy to show the ability of image creation and drawing aesthetics; use mathematics (M) literacy to plan and design the visual scale of images. The research process reveals the outline of the story, scene configuration and script content through the interaction and dialogue between the community residents and generations. Through

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ēngines of Ēternity: An Artistic Inquiry into Space Settlement Ideology Using Rotifer Experiments on Board the ISS 73

Ēngines of Ēternity: An Artistic Inquiry into Space Settle...

引用

73rd International Astronautical Congress, IAC 2022

作者： Vermeulen, Angelo C.J. Maranan, Diego Steyaert, Pieter Versbraegen, Nassim Peeters, Ann Verschuren, Jeroen Wan, Arise Pereira, Frederico D.A.S. Faber, Nils Mirzada, Fattana Hespeels, Boris Van Doninck, Karine Systems Engineering and Simulation Faculty of Technology Policy and Management Delft University of Technology Jaffalaan 5 Delft2628 BX Netherlands Faculty of Information and Communication Studies University of the Philippines Open University Laguna Los Baños Philippines Department of Training and Education Sciences University of Antwerp Sint-Jacobstraat 2 Antwerp2000 Belgium Department of Astrophysics and Planetary Science Niels Bohr Institute University of Copenhagen Blegdamsvej 17 Copenhagen2100 Denmark Machine Learning Group Université Libre de Bruxelles boulevard du Triomphe Brussels1050 Belgium Interuniversity Institute of Bioinformatics in Brussels Université Libre de Bruxelles Vrije Universiteit Brussel Boulevard du Triomphe Brussels1050 Belgium Department of Design & Technology Erasmus Brussels University of Applied Sciences and Arts Nijverheidskaai 170 Brussels1070 Belgium Center for Social and Cultural Psychology KU Leuven Tiensestraat 102 Leuven3000 Belgium University of Namur Namur Belgium Research Unit of Molecular Biology and Evolution Université Libre de Bruxelles Avenue F.D. Roosevelt 50 Brussels1050 Belgium

Ēngines of Ēternity is a transdisciplinary project that takes the biological phenomena of cloning and DNA repair as metaphorical departure points for an art installation about humanity's enthrallment with cultural immortality. Cultural immortality has long fascinated humankind, with such diverse examples as Ancient Egypt, the Roman Empire, Hindu kingdoms, and Mayan civilization, all assuming perpetuity through monumental works in art and architecture. This aspiration of cultural immortality is also deeply embedded in the imaginary of space exploration. Space settlements are often presented as the culmination of technological and cultural evolution. However, the quest for cultural immortality is often imbued with conflict because of convictions of superiority and impulses of colonialism, and this will be no different in outer space. Ēngines of Ēternity explores these human tendencies through the lens of the smallest animals on Earth, rotifers. On the surface, rotifers seem an unchanging biological culture, perfected through evolution, cloning itself endlessly, and surviving extreme conditions such as complete drying or freezing. However, during drying and rehydration, genetic material gets broken and repaired again, and in the process, diversity is generated. Moreover, DNA from totally different organisms such as fungi, bacteria and plants were discovered inside the rotifer's genome. This horizontal gene transfer is another mechanism through which rotifers seek out diversity. In Ēngines of Ēternity it's precisely this contrast between stasis and flux that is used as a metaphorical device to reflect critically on the aspirations of humankind in space. What concept of culture and identity will we develop in space? Who will have a say in this? And if we end up with a rich diversity of cultures and identities, how will we maintain cohesion? Ēngines of Ēternity is a joint effort between SEADS and the laboratory of Karine Van Doninck (UNamur/ULB). In a series of space biol

关键词： Cloning

来源：评论

学校读者我要写书评

暂无评论

Digital Technologies:Sustainable Innovations for Improving Teaching and learning

引用

开放教育研究 2020年第2期 122-122页

作者： Demetrios Sampson Dirk lfenthaler J.Michael Spector Pedro lsaías Department of Digital Systems University of Piraeus Piraeus Learning Design and Technology University of Mannheim Mannheim Department of Learning Technologies University of North Texas Denton Institute for Teaching&Learning Innovation(ITaLI) The University of Queensland St.Lucia

Introduction The aim of this volume entitled Digital Technologies:Sustainable Innovations for improving Teaching and learning is to contribute in the global discussion on digital technologies as the means to foster sustainable educational innovations for improving the teaching,learning and assessment from K-12 to Higher *** book consists of four parts and showcases how emerging educational technologies and innovative practices have been used to address core global educational challenges;spanning from rethinking and transforming learning environments across educational contexts to effectively cultivating students’competences for the digital smart society of the *** book comprises PartⅠ:Transforming the learning Environment;Part II:Enriching student learning experiences;PartⅢ:Measuring and Assessing Teaching and learning with Educational Data Analytics;PartⅣ:Cultivating student competences for the digital Smart *** targets researchers and research students,educational professional practitioners (including teachers,educators and education leaders) as well as education policy makers,who are interested in keeping up-to-date on the global development in this field.

关键词： Digital Technologies:Sustainable Innovations for Improving Teaching and learning

来源：评论

学校读者我要写书评

暂无评论

Machine learning of Thermodynamic Observables in the Presence of Mode Collapse 38

Machine Learning of Thermodynamic Observables in the Presenc...

引用

38th International Symposium on Lattice Field Theory, LATTICE 2021

作者： Nicoli, Kim A. Anders, Christopher J. Funcke, Lena Hartung, Tobias Jansen, Karl Kessel, Pan Nakajima, Shinichi Stornati, Paolo Technische Universität Berlin Machine Learning Group Marchstrasse 23 Berlin10587 Germany Technische Universität Berlin Berlin Germany Center for Theoretical Physics Co-Design Center for Quantum Advantage NSF AI Institute for Artificial Intelligence and Fundamental Interactions Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA02139 United States Perimeter Institute for Theoretical Physics 31 Caroline Street North WaterlooONN2L 2Y5 Canada Computation-Based Science and Technology Research Center The Cyprus Institute 20 Kavafi Street Nicosia2121 Cyprus Department of Mathematical Sciences University of Bath Bath United Kingdom Deutsches Elektronen-Synchrotron DESY Platanenallee 6 Zeuthen15738 Germany RIKEN Center for AIP 1-4-1 Nihonbashi Chuo-ku Tokyo Japan ICFO The Barcelona Institute of Science and Technology Av. Carl Friedrich Gauss 3 Castelldefels Barcelona08860 Spain

Estimating the free energy, as well as other thermodynamic observables, is a key task in lattice field theories. Recently, it has been pointed out that deep generative models can be used in this context [1]. Crucially, these models allow for the direct estimation of the free energy at a given point in parameter space. This is in contrast to existing methods based on Markov chains which generically require integration through parameter space. In this contribution, we will review this novel machine-learning-based estimation method. We will in detail discuss the issue of mode collapse and outline mitigation techniques which are particularly suited for applications at finite temperature. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0)

关键词： Free energy

来源：评论

学校读者我要写书评

暂无评论

Planning of Truck Platooning for Road-Network Capacitated Vehicle Routing Problem

arXiv

引用

arXiv 2024年

作者： Hao, Yilang Chen, Zhibin Sun, Xiaotong Tong, Lu Shanghai Key Laboratory of Urban Design and Urban Science NYU Shanghai 567 West Yangsi Road Pudong New District Shanghai200126 China Shanghai Frontiers Science Center of Artificial Intelligence and Deep Learning NYU Shanghai 567 West Yangsi Road Pudong New District Shanghai200126 China Department of Civil and Urban Engineering New York University 6 MetroTech Center BrooklynNY11201 United States Guangzhou China Department of Civil and Environmental Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong The School of Traffic and Transportation Beijing Jiaotong University No.3 Shangyuan Cun Haidian District Beijing China

Truck platooning, a linking technology of trucks on the highway, has gained enormous attention in recent years due to its benefits in energy and operation cost savings. However, most existing studies on truck platooning limit their focus on particular scenarios that each truck can serve only one customer demand and is thus with a specified origin-destination pair, so only routing and time schedules are taken into account. Nevertheless, in real-world logistics, each truck may need to serve multiple customers located at different places, and the operator managing a fleet of trucks thus has to determine not only the routing and time schedules of each truck but also the set of customers allocated to each truck and their sequence to visit. This is well known as a capacitated vehicle routing problem with time windows (CVRPTW), and considering the application of truck platooning in such a problem entails new modeling frameworks and tailored solution algorithms. In light of this, this study makes the first attempt to optimize the truck platooning plan for a road-network CVRPTW in a way to minimize the total operation cost, including vehicles' fixed dispatch cost and energy cost, while fulfilling all delivery demands within their time window constraints. Specifically, the operation plan will dictate the number of trucks to be dispatched, the set of customers, and the routing and time schedules for each truck. In addition, the modeling framework is constructed based on a road network instead of a traditional customer node graph to better resemble and facilitate the platooning operation. A 3-stage algorithm embedded with a "route-then-schedule" scheme, dynamic programming, and modified insertion heuristic, is developed to solve the proposed model in a timely manner. Numerical experiments are conducted to validate the proposed modeling framework, demonstrate the performance of the proposed solution algorithm, and quantify the benefit brought by the truck platooning technology.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Dissolving the Dichotomies Between Online and Campus-Based Teaching: a Collective Response to The Manifesto for Teaching Online (Bayne et al. 2020)

引用

Postdigital Science and Education 2022年第2期4卷 271-329页

作者： MacKenzie, Alison Bacalja, Alexander Annamali, Devisakti Panaretou, Argyro Girme, Prajakta Cutajar, Maria Abegglen, Sandra Evens, Marshall Neuhaus, Fabian Wilson, Kylie Psarikidou, Katerina Koole, Marguerite Hrastinski, Stefan Sturm, Sean Adachi, Chie Schnaider, Karoline Bozkurt, Aras Rapanta, Chrysi Themelis, Chryssa Thestrup, Klaus Gislev, Tom Örtegren, Alex Costello, Eamon Dishon, Gideon Hoechsmann, Michael Bucio, Jackeline Vadillo, Guadalupe Sánchez-Mendiola, Melchor Goetz, Greta Gusso, Helder Lima Arantes, Janine Aldous Kishore, Pallavi Lodahl, Mikkel Suoranta, Juha Markauskaite, Lina Mörtsell, Sara O’Reilly, Tanya Reed, Jack Bhatt, Ibrar Brown, Cheryl MacCallum, Kathryn Ackermann, Cecile Alexander, Carolyn Payne, Ameena Leah Bennett, Rebecca Stone, Cathy Collier, Amy Lohnes Watulak, Sarah Jandrić, Petar Peters, Michael Gourlay, Lesley School of Social Sciences Education and Social Work Queen’s University Belfast Belfast BT7 1HL United Kingdom Melbourne Graduate School of Education University of Melbourne Melbourne Australia Department of Accounting and Finance Lancaster University Lancaster United Kingdom National Higher Education Research Institute (IPPTN) Universiti Sains Malaysia Penang Malaysia Dublin City University Dublin Ireland Department of Arts Open Communities & Adult Education University of Malta Msida Malta Division of Digital Learning KTH Royal Institute of Technology Stockholm Sweden School of Architecture Planning and Landscape University of Calgary Calgary Canada Science Policy Research Unit University of Sussex Brighton United Kingdom Educational Technology & Design Department of Curriculum Studies University of Saskatchewan Saskatoon Canada Faculty of Education and Social Work University of Auckland Auckland New Zealand Digital Learning Deakin University Melbourne Australia Department of Education Umeå University Umeå Sweden Open Education Faculty Distance Education Department Anadolu University Eskişehir Turkey Faculty of Social Sciences and Humanities Universidade Nova de Lisboa Lisbon Portugal Department of Education and Lifelong Learning Norwegian University of Science and Technology Trondheim Norway Danish School of Education Aarhus University Aarhus Denmark Centre for Educational Development Aarhus University Aarhus Denmark Department of Applied Educational Science Umeå University Umeå Sweden Dept of Education Ben Gurion University Beersheba Israel Lakehead University Orillia Heritage Place 1 Colborne Street West Orillia Orillia L3V 7X5 ON Canada Online High School & MOOC Open University Educational Innovation and Distance Education Office Universidad Nacional Autónoma de México Mexico City Mexico Open University Educational Innovation and Distance Education Office Coordinator Universidad Nacional Autónoma de México Mexico City Mexico Engl

This article is a collective response to the 2020 iteration of The Manifesto for Teaching Online. Originally published in 2011 as 20 simple but provocative statements, the aim was, and continues to be, to critically challenge the normalization of education as techno-corporate enterprise and the failure to properly account for digital methods in teaching in Higher Education. The 2020 Manifesto continues in the same critically provocative fashion, and, as the response collected here demonstrates, its publication could not be timelier. Though the Manifesto was written before the Covid-19 pandemic, many of the responses gathered here inevitably reflect on the experiences of moving to digital, distant, online teaching under unprecedented conditions. As these contributions reveal, the challenges were many and varied, ranging from the positive, breakthrough opportunities that digital learning offered to many students, including the disabled, to the problematic, such as poor digital networks and access, and simple digital poverty. Regardless of the nature of each response, taken together, what they show is that The Manifesto for Teaching Online offers welcome insights into and practical advice on how to teach online, and creatively confront the supremacy of face-to-face teaching. © 2021, The Author(s).

关键词： Campus learning Collective response Covid-19 Digital learning Distant learning Manifesto for teaching online Postdigital

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：