检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhong, Yong Liu, Hongtao Liu, Xiaodong Bao, Fan Shen, Weiran Li, Chongxuan Gaoling School of AI Renmin University of China Beijing China Beijing Key Lab of Big Data Management and Analysis Methods Beijing China Department of Computer Science Technology Tsinghua University Beijing China

Deep generative models (DGMs) are data-eager because learning a complex model on limited data suffers from a large variance and easily overfits. Inspired by the classical perspective of the bias-variance tradeoff, we propose regularized deep generative model (Reg-DGM), which leverages a nontransferable pre-trained model to reduce the variance of generative modeling with limited data. Formally, Reg-DGM optimizes a weighted sum of a certain divergence and the expectation of an energy function, where the divergence is between the data and the model distributions, and the energy function is defined by the pre-trained model w.r.t. the model distribution. We analyze a simple yet representative Gaussian-fitting case to demonstrate how the weighting hyperparameter trades off the bias and the variance. Theoretically, we characterize the existence and the uniqueness of the global minimum of Reg-DGM in a non-parametric setting and prove its convergence with neural networks trained by gradient-based methods. Empirically, with various pre-trained feature extractors and a data-dependent energy function, Reg-DGM consistently improves the generation performance of strong DGMs with limited data and achieves competitive results to the state-of-the-art methods. Our implementation is available at https://***/ML-GSAI/Reg-ADA-APA. Copyright © 2022, 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

Configuration Testing of an Artificial Pancreas System Using a Digital Twin

SSRN

引用

SSRN 2024年

作者： Somers, Richard J. Walkinshaw, Neil Hierons, Robert M. Elliott, Jackie Iqbal, Ahmed Walkinshaw, Emma Computer Science Department University of Sheffield SheffieldS1 4DP United Kingdom Sheffield Teaching Hospitals NHS Foundation Trust Diabetes and Endocrine Centre Northern General Hospital SheffieldS5 7AU United Kingdom University of Sheffield United Kingdom

The recent spread of wearable medical devices has improved the quality of life of people with medical conditions. Traditionally, users configure these systems using physical trials, putting themselves in potentially dangerous scenarios. Digital twins present an opportunity to perform configuration testing in simulated environments, reducing the potential risk. In this paper, we perform an evaluative case study to assess the capabilities of a digital twin in the configuration testing of an artificial pancreas system (APS) control algorithm. These systems regulate the blood glucose levels in people with type 1 diabetes mellitus (T1DM), which if misconfigured, can cause severe hypoglycaemia or hyperglycaemia, which can be life-threatening. We tested the OpenAPS control algorithm against 156 people's clinical data. We found that our digital twin provided an accurately simulated environment to perform configuration testing and was capable of predicting blood glucose-insulin behaviour. We were able to evaluate different APS configurations, identifying a potentially unsafe configuration without the risks associated with a physical trial. We uncovered how modelling clinical data is not always consistent, which could lead to misinterpretations in configuration testing, and the challenges associated with test reliability when modelling human body dynamic uncertainty. © 2024, The Authors. All rights reserved.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Democratizing engineering education: An online Bachelor of science in Engineering degree

Democratizing engineering education: An online Bachelor of S...

引用

Frontiers in Education (FIE) Conference

作者： Nick A. Stites Janet L. Yowell Rhonda Hoenigman William Kuskin Abigail B. Rose University of Colorado Boulder Integrated Teaching & Learning Program Boulder CO USA Computer Science Department University of Colorado Boulder Boulder CO USA English Department University of Colorado Boulder Boulder CO USA University of Colorado Boulder Engineering Digital Education Boulder CO USA

The College of Engineering & Applied science at the University of Colorado Boulder proposes a low-cost, online, accredited Bachelor of science in Engineering (BSE) degree. The BSE will provide a pathway for community college (CC) students, or students with similar transfer credits, to complete a degree in engineering at a cost similar to attending CC. The educationally underserved communities across Colorado are often low-income, racially and ethnically diverse, and rural; the BSE's primary goal is to provide access to an engineering education for these students and, thus, open pathways to high-demand, high-wage careers. The BSE will reach an underserved population of learners who can stay in their local community while simultaneously pursuing an engineering education. A fully online, ABET-accredited engineering degree is surprisingly novel-only nine other online engineering degrees in the nation are accredited-but an R1-level university degree at a near-community-college cost is unprecedented. The BSE will invite the institution's best instructors to innovate in online education-virtual labs, team-based projects, flipped asynchronous discussions, and hybrid-learning activities. Student success support will include wrap-around advising to foster the development of the academic, affective, financial, and career support that students need to succeed in engineering. The BSE will utilize five administrative affordances: 1) success coaches to provide wrap-around support and guidance to students; 2) course facilitators who provide personalized support; 3) stackable credentials; 4) eight-week semesters, allowing students to quickly complete portions of their education; and 5) mentorship programming to foster community and to help students develop their (inter)disciplinary identity. The online BSE creates a new pathway for underserved students to matriculate to a flagship public research university for a degree in engineering. This work-in-progress outlines the proposed str

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Ultrasound Video Enhancement

Automated Ultrasound Video Enhancement

引用

2021 International Conference on Communication and Information Technology, ICICT 2021

作者： Jabbar, Shaima I. Day, Charles R. Aladi, Abathar Q. Chadwick, Edward K. Frurat Al Awsat Technical University Babylon technical Institute Babylon Iraq Keele University Computer Science Department United Kingdom Babylon Health Directory Mirjan Teaching Hospital Babylon Iraq University of Aberdeen School of Engineering United Kingdom

ISBN: (纸本)9781665439145

The video ultrasound imaging is one of the techniques that is in demand at the present time. The reason of using ultrasound video is to provide a clearer impression of the organ's details or any area in the body to a specialist. Therefore, automated improving of ultrasound video increase a chance of getting a correct diagnosis and it is possible to add as an option in the ultrasound machine (improving the ultrasound video during recording). In this paper, we introduced and applied a novel technique, which depends on the principle of fuzzy inference system, through designing an effective fuzzy rule to treat image regions of low contrast based on the analysis of the image properties. Proposed technique was performed on muscklusketal ultrasound video and musculoskeletal panoramic ultrasound image. The proposed technique is Fuzzy Inference Ultrasound Video (FIUV), a superior result was obtained when it applied on panoramic images compared to ultrasound video. The performance of the FIUV technique with approximately 18% greater than recent technique in the case of panoramic ultrasound images and 4% less than recent technique when was applied on ultrasound video. Therefore, the results showed that the response of the panoramic images to this proposed technique was more than the videography. However, as future work it is possible to modify this method and improve its performance on video imaging. © 2021 IEEE.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

Engineering Students’ Attitudes and Perceptions towards Project-Based Learning: A Study from Kerala, Southern India

Engineering Students’ Attitudes and Perceptions towards Pro...

引用

IEEE International Conference on teaching, Assessment and Learning for Engineering (TALE)

作者： Akshay R S Alviya Sunny Saranya V S Aby John N. P. Subheesh S M Anzar Department of Electronics and Communication Engineering Government Engineering College Trivandrum India Department of Computer Science and Engineering Model Engineering College India Accenture Solutions Pvt Ltd Coimbatore India Faculty of Philology RUDN University Moscow Russia Teaching Learning Centre SRM University - AP Andhra Pradesh India Department of Electronics and Communication Engineering TKM College of Engineering Kollam India

ISBN: (数字)9798350376234

ISBN: (纸本)9798350376241

The shift from teacher-centric to student-centric education has been a subject of debate, with traditional instruction often criticized for fostering rote learning and passive engagement. Due to its emphasis on student autonomy and real-world application of knowledge, the growing popularity of Project-Based Learning as a novel alternative to traditional classroom-based teaching pedagogy is attracting educational institutions all around the world. In engineering education, multifaceted skill development is paramount. PjBL offers a dynamic approach to cultivate essential competencies and it significantly improves engineering education. The National Education Policy 2020 (NEP 2020) of India lays a strong emphasis on Project-Based Learning as the cornerstone of educational reform. But, only smaller number of research studies are conducted in the country to explore the attitudes and perceptions of students towards Project-Based Learning in the engineering sector. It lays bare the imminent need for educationalists to focus on this research gap. This paper explores the attitudes and perceptions of engineering students towards Project-Based Learning from Kerala, a state in Southern India. A novel questionnaire entitled Project-Based Learning in Engineering Education in Kerala (PLEEK) is developed by the IEEE Education Society Kerala Chapter to conduct the survey. A total of 136 students from all over Kerala attended the survey. It is observed that the students have a positive perception of Project-Based Learning and its impact on enhancing their education. On the other hand, an abysmally low count of 11% of students believed that their current campus ecosystem supported this teaching pedagogy. They highlighted the need for a drastic transformation in the present academic infrastructure to support Project-Based Learning. The findings of the study underscore the potential of Project-Based Learning in enhancing learning outcomes, fostering critical skills, and preparing studen

关键词： Surveys Training Hands Ecosystems Engineering students

来源：评论

学校读者我要写书评

暂无评论

Redesigning an AI bill of rights with/for young people: Principles for exploring AI ethics with middle and high school students

引用

computers and Education: Artificial Intelligence 2024年 7卷

作者： Burriss, Sarah K. Hutchins, Nicole Conley, Zachary Deweese, Menton M. Doe, Yelena J. Eeds, Angela Villanueva, Ana Ziegler, Hannah Oliver, Kendra Vanderbilt University Department of Computer Science 1025 16th Ave S NashvilleTN 37212 United States initative 817 Cathedral of Learning PittsburghPA15213 United States Vanderbilt University Collaborative for STEM Education and Outreach 6 Magnolia NashvilleTN 37212 United States Vanderbilt University Department of Teaching & Learning 1930 South Avenue NashvilleTN 37212 United States

"AI ethics" has become a popular term for signaling concerns with the development and application of artificial intelligence, and a hot-button issue in both academic and public discourse. The current work tends to center adult-oriented, adult-generated, and issues-based conceptions of ethics. This paper reports on an alternative model for "doing ethics" via co-design with young people, highlighting the need for students to engage in AI ethics work, especially as AI is increasingly used in their education and social lives. In particular, we focus on developing a rights-based approach, using the White House Blueprint for an AI Bill of Rights as a starting point for redesigning core AI ethics principles and their conveyance to be accessible and relevant to young people, in collaboration with young people. In this manuscript, we describe our empirical work in a series of three studies on AI ethics teaching and learning with middle and high school students, which culminated in redesigning pieces of the AI Bill of Rights. We present lessons learned, implications for responsible AI in education from student perspectives, and conclude with our suggested principles for integrating student insight and perspectives into the ethics frameworks that guide AI applications. © 2024 The Author(s)

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware similarity measures - properties and construction method 11

Uncertainty-aware similarity measures - properties and const...

引用

11th Conference of the European Society for Fuzzy Logic and Technology, EUSFLAT 2019

作者： Żywica, Patryk Stachowiak, Anna Department of Imprecise Information Processing Methods Faculty of Mathematics and Computer Science Adam Mickiewicz University in Poznań Umultowska 87 Poznań61-614 Poland

ISBN: (纸本)9789462527706

A concept of uncertainty-aware similarity measure is being defined and discussed. The aim of the paper is to support the opinion that both definition and construction of such measure should take into account the epistemic nature of compared incomplete (uncertain) information. This approach, however, generates new challenges resulted from the computational complexity of the problem. We define a set of properties to be satisfied by uncertainty-aware similarity measure and we propose a new technique of constructing such measures for Interval-Valued Fuzzy Sets. Copyright © 2019, the Authors. Published by Atlantis Press. This is an open access article under the CC BY-NC license (http://***/licenses/by-nc/4.0/).

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval

arXiv

引用

arXiv 2022年

作者： Zhan, Jingtao Ai, Qingyao Liu, Yiqun Mao, Jiaxin Xie, Xiaohui Zhang, Min Ma, Shaoping Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China

Recent advance in Dense Retrieval (DR) techniques has significantly improved the effectiveness of first-stage retrieval. Trained with large-scale supervised data, DR models can encode queries and documents into a low-dimensional dense space and conduct effective semantic matching. However, previous studies have shown that the effectiveness of DR models would drop by a large margin when the trained DR models are adopted in a target domain that is different from the domain of the labeled data. One of the possible reasons is that the DR model has never seen the target corpus and thus might be incapable of mitigating the difference between the training and target domains. In practice, unfortunately, training a DR model for each target domain to avoid domain shift is often a difficult task as it requires additional time, storage, and domain-specific data labeling, which are not always available. To address this problem, in this paper, we propose a novel DR framework named Disentangled Dense Retrieval (DDR) to support effective and flexible domain adaptation for DR models. DDR consists of a Relevance Estimation Module (REM) for modeling domain-invariant matching patterns and several Domain Adaption Modules (DAMs) for modeling domain-specific features of multiple target corpora. By making the REM and DAMs disentangled, DDR enables a flexible training paradigm in which REM is trained with supervision once and DAMs are trained with unsupervised data. Comprehensive experiments in different domains and languages show that DDR significantly improves ranking performance compared to strong DR baselines and substantially outperforms traditional retrieval methods in most scenarios. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Elementary symmetric partitions

arXiv

引用

arXiv 2024年

作者： Ballantine, Cristina Beck, George Merca, Mircea Sagan, Bruce E. Department of Mathematics and Computer Science College of the Holy Cross WorcesterMA01610 United States Department of Mathematics and Statistics Dalhousie University HalifaxNSB3H 4R2 Canada Department of Mathematical Methods and Models Fundamental Sciences Applied in Engineering Research Center National University of Science and Technology Politehnica Bucharest BucharestRO-060042 Romania Academy of Romanian Scientists BucharestRO-050044 Romania Department of Mathematics Michigan State University East LansingMI48824 United States

Let ek(x1,..., x) be an elementary symmetric polynomial and let λ = (λ1,..., λ) be an integer partition. Define prek(λ) to be the partition whose parts are the summands in the evaluation ek(λ1,..., λ). The study of such partitions was initiated by Ballantine, Beck, and Merca who showed (among other things) that pre2 is injective as a map on binary partitions of n. In the present work we derive a host of identities involving the sequences which count the number of parts of a given value in the image of pre2. These include generating functions, explicit expressions, and formulas for forward differences. We generalize some of these to d-ary partitions and explore connections with color partitions. Our techniques include the use of generating functions and bijections on rooted partitions. We end with a list of conjectures and a direction for future *** Codes 05A17, 05E05 (Primary) 05A15, 05A19 (Secondary) © 2024, CC BY.

关键词： Integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Authors' Response

引用

Journal of the Academy of Nutrition and Dietetics 2024年第2期124卷 166-167页

作者： Vasiliki Bountziouka Christopher P Nelson Veryan Codd Nilesh J Samani Computer Simulations Genomics and Data Analysis Laboratory Department of Food Science and Nutrition University of the Aegean Lemnos Geece Population Policy and Practice Research and Teaching Department GOS Institute of Child Health University College London London United Kingdom Department of Cardiovascular Sciences University of Leicester Leicester United Kingdom NIHR Leicester Biomedical Research Centre Glenfield Hospital Leicester United Kingdom. Department of Cardiovascular Sciences University of Leicester Leicester United Kingdom

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：