检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Miao, Brenda Y. Chen, Irene Y. Williams, Christopher Y.K. Davidson, Jaysón Garcia-Agundez, Augusto Sun, Shenghuan Zack, Travis Saria, Suchi Arnaout, Rima Quer, Giorgio Sadaei, Hossein J. Torkamani, Ali Beaulieu-Jones, Brett Yu, Bin Gianfrancesco, Milena Butte, Atul J. Norgeot, Beau Sushil, Madhumita Bakar Computational Health Sciences Institute University of California San Francisco San FranciscoCA United States UCSF-UC Berkeley Joint Program in Computational Precision Health University of California Berkeley University of California San Francisco BerkeleyCA United States Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA United States Berkeley AI Research University of California Berkeley BerkeleyCA United States Department of Medicine Division of Rheumatology University of California San Francisco San FranciscoCA United States Helen Diller Family Comprehensive Cancer Center University of California San Francisco San FranciscoCA United States Center for Data-driven Insights and Innovation University of California Office of the President OaklandCA United States Bayesian Health New YorkNY10282 United States Department of Computer Science Johns Hopkins University Whiting School of Engineering BaltimoreMD United States Department of Health Policy & Management Johns Hopkins University Bloomberg School of Public Health BaltimoreMD United States Department of Medicine Johns Hopkins Medicine BaltimoreMD21205 United States Departments of Medicine Radiology and Pediatrics University of California San Francisco San FranciscoCA United States Scripps Research Translational Institute La Jolla CA United States Department of Integrative Structural and Computational Biology Scripps Research La Jolla CA92037 United States Department of Medicine University of Chicago ChicagoIL United States Department of Statistics University of California Berkeley BerkeleyCA United States Center for Computational Biology University of California Berkeley BerkeleyCA United States Qualified Health PBC Palo AltoCA United States

Recent advances in generative models, including large language models (LLMs), vision language models (VLMs), and diffusion models, have accelerated the field of natural language and image processing in medicine and marked a significant paradigm shift in how biomedical models can be developed and deployed. While these models are highly adaptable to new tasks, scaling and evaluating their usage presents new challenges not addressed in previous frameworks. In particular, the ability of these models to produce useful outputs with little to no specialized training data ("zero-" or "few-shot" approaches), as well as the open-ended nature of their outputs, necessitate the development of new guidelines for robust reporting of clinical generative model research. In response to gaps in standards and best practices for the development of clinical AI tools identified by US Executive Order 141103 and several emerging national networks for clinical AI evaluation, we begin to formalize some of these guidelines by building on the original MI-CLAIM checklist. The new checklist, MI-CLAIM-GEN (Table 1), aims to address differences in training, evaluation, interpretability, and reproducibility of new generative models compared to non-generative ("predictive") AI models. This MI-CLAIM-GEN checklist also seeks to clarify cohort selection reporting with unstructured clinical data and adds additional items on alignment with ethical standards for clinical AI research. © 2024, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Student Usage of Interactive Learning Tools in an Online Linear Circuit Analysis Textbook

Student Usage of Interactive Learning Tools in an Online Lin...

引用

Frontiers in Education (FIE) Conference

作者： Nikitha Sambamurthy Alex Edgcomb Yamuna Rajasekhar Engineering Content zyBooks Los Gatos CA USA Research and Development zyBooks Los Gatos CA USA Also with UC Riverside Computer Science Content zyBooks Los Gatos CA USA

ISBN: (数字)9781728117461

ISBN: (纸本)9781728117478

Linear circuit analysis is a foundational course for electrical engineers. Instructors of linear circuit analysis courses have traditionally relied on print textbooks for student learning materials. With the rise of student use of computers and the internet, materials like lecture slides and online videos have also been used for learning materials. Increasingly, traditional textbooks (including online formats) are experiencing a decline, while interactive textbooks are growing in popularity. This paper describes auto-graded learning tools, called challenged activities, from various topics in an online linear circuit analysis textbook. Instructors often assign challenge activities as homework. Each challenge activity has 3-5 levels of increasingly difficult problems. Each level randomly generates a question from a large set of questions of similar difficulty. Students must correctly answer a question in a level to progress to the next level. This paper describes the student usage of 4 challenge activities in an online circuit analysis textbook. The average time spent per activity was under 10 minutes and the vast majority of students who started a level ended up completing that level, indicating little attrition. In fact, most levels had 0% of students give up and the highest was only 8%, which is remarkably low based compared to more traditional paper-and-pencil activities based on the teaching experience of the authors.

关键词： Linear circuits Resistors Tools Mathematical model Circuit analysis Measurement Capacitors

来源：评论

学校读者我要写书评

暂无评论

Transfer of adversarial robustness between perturbation types

arXiv

引用

arXiv 2019年

作者： Kang, Daniel Sun, Yi Brown, Tom Hendrycks, Dan Steinhardt, Jacob OpenAI San FranciscoCA United States Department of Computer Science Stanford University Palo AltoCA United States Department of Mathematics Columbia University New YorkNY United States Department of Electrical Engineering and Computer Science UC Berkeley BerkeleyCA United States

We study the transfer of adversarial robustness of deep neural networks between different perturbation types. While most work on adversarial examples has focused on L∞ and L2-bounded perturbations, these do not capture all types of perturbations available to an adversary. The present work evaluates 32 attacks of 5 different types against models adversarially trained on a 100-class subset of ImageNet. Our empirical results suggest that evaluating on a wide range of perturbation sizes is necessary to understand whether adversarial robustness transfers between perturbation types. We further demonstrate that robustness against one perturbation type may not always imply and may sometimes hurt robustness against other perturbation types. In light of these results, we recommend evaluation of adversarial defenses take place on a diverse range of perturbation types and sizes. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2020年

作者： He, Tanjin Sun, Wenhao Huo, Haoyan Kononova, Olga Rong, Ziqin Tshitoyan, Vahe Botari, Tiago Ceder, Gerbrand Department of Materials Science and Engineering UC Berkeley BerkeleyCA94720 United States Materials Sciences Division Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Google LLC 1600 Amphitheatre Parkway Mountain ViewCA94043 United States Institute of Mathematics and Computer Sciences University of São Paulo São Carlos SP13566-590 Brazil

Collecting and analyzing the vast amount of information available in the solid-state chemistry literature may accelerate our understanding of materials synthesis. However, one major problem is the difficulty of identifying which materials from a synthesis paragraph are precursors or are target materials. In this study, we developed a two-step Chemical Named Entity Recognition (CNER) model to identify precursors and targets, based on information from the context around material entities. Using the extracted data, we conducted a meta-analysis to study the similarities and differences between precursors in the context of solid-state synthesis. To quantify precursor similarity, we built a substitution model to calculate the viability of substituting one precursor with another while retaining the target. From a hierarchical clustering of the precursors, we demonstrate that "chemical similarity" of precursors can be extracted from text data. Quantifying the similarity of precursors helps provide a foundation for suggesting candidate reactants in a predictive synthesis model. Copyright © 2020, The Authors. All rights reserved.

关键词： Chemical analysis

来源：评论

学校读者我要写书评

暂无评论

BiasedWalk: Biased Sampling for Representation Learning on Graphs

BiasedWalk: Biased Sampling for Representation Learning on G...

引用

2018 IEEE International Conference on Big Data, Big Data 2018

作者： Nguyen, Duong Malliaros, Fragkiskos D. Department of Computer Science and Engineering UC San Diego San DiegoCA United States Center for Visual Computing CentraleSupélec Inria Saclay Gif-Sur-Yvette France

ISBN: (纸本)9781538650356

Network embedding algorithms are able to learn latent feature representations of nodes, transforming networks into lower dimensional vector representations. Typical key applications, which have effectively been addressed using network embeddings, include link prediction, multilabel classification and community detection. In this paper, we propose Biased-Walk, a scalable, unsupervised feature learning algorithm that is based on biased random walks to sample context information about each node in the network. Our random-walk based sampling can behave as Breath-First-Search (BFS) and Depth-First-Search (DFS) samplings with the goal to capture homophily and role equivalence between the nodes in the network. We have performed a detailed experimental evaluation comparing the performance of the proposed algorithm against various baseline methods, on several datasets and learning tasks. The experiment results show that the proposed method outperforms the baseline ones in most of the tasks and datasets. © 2018 IEEE.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

Linear and Nonlinear Reconstruction Algorithms for Atomic-Resolution Tomography Using Phase Contrast Electron Microscopy

引用

Microscopy and Microanalysis 2018年第S1期24卷 110-111页

作者： Colin Ophus David Ren Michael Chen Catherine Groschner Mary Scott Laura Waller Molecular Foundry Lawrence Berkeley National Laboratory Berkeley USA Department of Electrical Engineering and Computer Science UC Berkeley Berkeley CA Materials Science and Engineering UC Berkeley Berkeley CA

来源：评论

学校读者我要写书评

暂无评论

34Improving the security of visual challenges

引用

ACM Transactions on Cyber-Physical Systems 2019年第3期3卷

作者： Valente, Junia Bahirat, Kanchan Venechanos, Kelly Cardenas, Alvaro A. Balakrishnan, Prabhakaran University of California Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas 800W. Campbell Road RichardsonTX75080 United States Jack Baskin School of Engineering UC Santa Cruz 1156 High Street Santa CruzCA95064 United States

This article proposes new tools to detect the tampering of video feeds from surveillance cameras. Our proposal illustrates the unique cyber-physical properties that sensor devices can leverage for their cyber-security. While traditional attestation algorithms exchange digital challenges between devices authenticating each other, our work instead proposes challenges that manifest physically in the field of view of the camera (e.g., a QR code in a display). This physical (challenge) and cyber (verification) attestation mechanism can help protect systems even when the sensors (cameras) and actuators (a display, infrared LEDs, color light bulbs) are compromised. In this article, we consider skillful adversaries that can capture the correct challenges (our system is sending) and can re-create them in the response to try fooling our verification system, and we propose new algorithms to detect these powerful attackers. Also, we introduce new visual challenges that make harder for anti-forensics attackers to succeed, and we present experimental results showing how our system is robust against a variety of attacks ranging from naive attacks to more sophisticated anti-forensics attackers. © 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Efficient and safe exploration in deterministic markov decision processes with unknown transition models

arXiv

引用

arXiv 2019年

作者： Biyik, Erdem Margoliash, Jonathan Alimo, Shahrouz Ryan Sadigh, Dorsa Electrical Engineering Stanford University CA94305 Jet Propulsion Laboratory California Institute of Technology CA91109 United States UC San Diego Jacobs School of Engineering CA92093 Computer Science Stanford University CA94305 United States

We propose a safe exploration algorithm for deterministic Markov Decision Processes with unknown transition models. Our algorithm guarantees safety by leveraging Lipschitz-continuity to ensure that no unsafe states are visited during exploration. Unlike many other existing techniques, the provided safety guarantee is deterministic. Our algorithm is optimized to reduce the number of actions needed for exploring the safe space. We demonstrate the performance of our algorithm in comparison with baseline methods in simulation on navigation tasks. Copyright © 2019, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Towards automated pain detection in children using facial and electrodermal activity 1

Towards automated pain detection in children using facial an...

引用

1st Joint Workshop on AI in Health, AIH 2018

作者： Xu, Xiaojing Susam, Büsra Tu gçe Nezamfar, Hooman Diaz, Damaris Craig, Kenneth D. Goodwin, Matthew S. Akcakaya, Murat Huang, Jeannie S. De Sa, Virginia R. Department of Electrical and Computer Engineering UC San Diego San DiegoCA United States Department of Electrical and Computer Engineering University of Pittsburgh PittsburghPA United States Department of Electrical and Computer Engineering Northeastern University BostonMA United States Rady Childrens Hospital Department of Pediatrics UC San Diego CA United States Department of Psychology University of British Columbia VancouverBC Canada Department of Health Sciences Northeastern University BostonMA United States Department of Cognitive Science UC San Diego San DiegoCA United States

Accurately determining pain levels in children is difficult, even for trained professionals and parents. Facial activity and electrodermal activity (EDA) provide rich information about pain, and both have been used in automated pain detection. In this paper, we discuss preliminary steps towards fusing models trained on video and EDA features respectively. We demonstrate the benefit of the fusion with a special test case involving domain adaptation and improved accuracy relative to using EDA and video features alone. © CEUR-WS. All rights reserved.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

Inferring diploid 3D chromatin structures from Hi-C data 19

Inferring diploid 3D chromatin structures from Hi-C data

引用

19th International Workshop on Algorithms in Bioinformatics, WABI 2019

作者： Cauer, Alexandra Gesine Yardımcı, Gürkan Vert, Jean-Philippe Varoquaux, Nelle Noble, William Stafford Department of Genome Sciences University of Washington SeattleWA United States Google Brain Paris France Centre for Computational Biology MINES ParisTech PSL University Paris France Department of Statistics UC BerkeleyCA United States Department of Genome Sciences University of Washington SeattleWA United States Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States

ISBN: (纸本)9783959771238

The 3D organization of the genome plays a key role in many cellular processes, such as gene regulation, differentiation, and replication. Assays like Hi-C measure DNA-DNA contacts in a high-throughput fashion, and inferring accurate 3D models of chromosomes can yield insights hidden in the raw data. For example, structural inference can account for noise in the data, disambiguate the distinct structures of homologous chromosomes, orient genomic regions relative to nuclear landmarks, and serve as a framework for integrating other data types. Although many methods exist to infer the 3D structure of haploid genomes, inferring a diploid structure from Hi-C data is still an open problem. Indeed, the diploid case is very challenging, because Hi-C data typically does not distinguish between homologous chromosomes. We propose a method to infer 3D diploid genomes from Hi-C data. We demonstrate the accuracy of the method on simulated data, and we also use the method to infer 3D structures for mouse chromosome X, confirming that the active homolog exhibits a bipartite structure, whereas the active homolog does not. © Alexandra Gesine Cauer, Gürkan Yardımcı, Jean-Philippe Vert, Nelle Varoquaux, and William Stafford Noble

关键词： Genes

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：