检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Sakarvadia, Mansi Khan, Arham Ajith, Aswathy Grzenda, Daniel Hudson, Nathaniel Bauer, André Chard, Kyle Foster, Ian Department of Computer Science University of Chicago United States Data Science & Learning Division Argonne National Laboratory United States

Transformer-based Large Language Models (LLMs) are the state-of-the-art for natural language tasks. Recent work has attempted to decode, by reverse engineering the role of linear layers, the internal mechanisms by which LLMs arrive at their final predictions for text completion tasks. Yet little is known about the specific role of attention heads in producing the final token prediction. We propose Attention Lens, a tool that enables researchers to translate the outputs of attention heads into vocabulary tokens via learned attention-head-specific transformations called lenses. Preliminary findings from our trained lenses indicate that attention heads play highly specialized roles in language models. The code for Attention Lens is available at ***/msakarvadia/AttentionLens. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Octopus: Experiences with a Hybrid Event-Driven Architecture for Distributed Scientific Computing 24

Octopus: Experiences with a Hybrid Event-Driven Architecture...

引用

Proceedings of the SC '24 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis

作者： Haochen Pan Ryan Chard Sicheng Zhou Alok Kamatar Rafael Vescovi Valérie Hayot-Sasson André Bauer Maxime Gonthier Kyle Chard Ian Foster Department of Computer Science University of Chicago Chicago IL USA Data Science and Learning Division Argonne National Laboratory Lemont IL USA Department of Computer Science Southern University of Science and Technology Guangdong China Department of Computer Science Illinois Institute of Technology Chicago IL USA Department of Computer Science University of Chicago Chicago IL USA and Data Science and Learning Division Argonne National Laboratory Lemont IL USA

ISBN: (纸本)9798350355543

Scientific research increasingly relies on distributed computational resources, storage systems, networks, and instruments, ranging from HPC and cloud systems to edge devices. Event-driven architecture (EDA) benefits applications targeting distributed research infrastructures by enabling the organization, communication, processing, reliability, and security of events generated from many sources. To support the development of scientific EDA, we introduce Octopus, a hybrid, cloud-to-edge event fabric designed to link many local event producers and consumers with cloud-hosted brokers, and to provide a fabric for developing resilient applications. Octopus can be scaled to meet demand, permits the deployment of highly available Triggers for automatic event processing, and enforces fine-grained access control. We identify requirements in self-driving laboratories, scientific data automation, online task scheduling, epidemic modeling, and dynamic workflow management use cases, and present results demonstrating Octopus' ability to meet those requirements. Octopus supports producing and consuming events at a rate of over 4.2 M and 9.6 M events per second, respectively, from distributed clients.

关键词： Event-driven architecture

来源：评论

学校读者我要写书评

暂无评论

Machine learning for automated experimentation in scanning transmission electron microscopy

引用

npj Computational Materials 2023年第1期9卷 25-40页

作者： Sergei V.Kalinin Debangshu Mukherjee Kevin Roccapriore Benjamin J.Blaiszik Ayana Ghosh Maxim A.Ziatdinov Anees Al-Najjar Christina Doty Sarah Akers Nageswara S.Rao Joshua C.Agar Steven R.Spurgeon Department of Materials Science and Engineering University of TennesseeKnoxvilleTN 37996USA Computational Sciences and Engineering Division Oak Ridge National LaboratoryOak RidgeTN 37831USA Center for Nanophase Materials Sciences Oak Ridge National LaboratoryOak RidgeTN 37831USA Argonne National Laboratory Data Science and Learning DivisionChicagoIL 60439USA University of Chicago GlobusChicagoIL 60637USA National Security Directorate Pacific Northwest National LaboratoryRichlandWA 99352USA Department of Materials Science and Engineering Drexel UniversityPhiladelphiaPA 19104USA Department of Physics University of WashingtonSeattleWA 98195USA

Machine learning(ML)has become critical for post-acquisition data analysis in(scanning)transmission electron microscopy,(S)TEM,imaging and *** emerging trend is the transition to real-time analysis and closed-loop microscope *** effective use of ML in electron microscopy now requires the development of strategies for microscopy-centric experiment workflow design and ***,we discuss the associated challenges with the transition to active ML,including sequential data analysis and out-of-distribution drift effects,the requirements for edge operation,local and cloud data storage,and theory in the loop ***,we discuss the relative contributions of human scientists and ML agents in the ideation,orchestration,and execution of experimental workflows,as well as the need to develop universal hyper languages that can apply across multiple *** considerations will collectively inform the operationalization of ML in next-generation experimentation.

关键词： optimization automated execution

来源：评论

学校读者我要写书评

暂无评论

WebSight: An AI-based Approach to Enhance Web Accessibility for the Visually Impaired

WebSight: An AI-based Approach to Enhance Web Accessibility ...

引用

science, Technology, Engineering and Management (ICSTEM), International Conference on

作者： Sri Ram M S Emmanuel Joy Leka Shree J Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798350376913

ISBN: (纸本)9798350388473

Web accessibility plays a significant role in shaping our online experiences in today's ever-changing digital world. People with vision impairmentsstill have trouble using most websites. This paper introduces WebSight an innovative AI-based Image Description Generator web extension to address these challenges. By seamlessly interfacing with a Flask server, Optical Character Recognition, and a dedicated Image Description Generator model, this browser extension systematically enhances web accessibility by methodically replacing ‘alt’ attributes of images with meticulously generated descriptions. This approach significantly contributes to web inclusivity, providing visually impaired users with accurate and contextually rich information. The extension's commitment to inclusivity is further demonstrated through the intelligent integration of Tesseract-OCR and Text-to-Speech ensuring a novel and far-reaching impact, offering an enhanced and tailored browsing experience for users with visual impairments.

关键词： Training Technological innovation Accuracy Visual impairment Optical character recognition Web pages Transformers

来源：评论

学校读者我要写书评

暂无评论

System for Identifying and Avoiding Obstructions on Railway Tracks in Forest Areas

System for Identifying and Avoiding Obstructions on Railway ...

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： P B Hemanthkumar Ruth Moly Benjamin Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

Railways often faces the challenge of obstructions on the tracks especially passing through the forest area as not much precautions or announcements will be given to there also animals won't be able to understand the arrival of the train. Which results a significant safety risk to trains, travelling passengers and intruding creatures. This paper addresses for identifying the obstacles on railway tracks especially in forest areas which helps to take necessary actions to avoid those obstructions above. The system needs a camera, that has to be installed on the adjacent sides of the railway path which captures the real time data of the track. This captured data is then processed and analyzed to identify any potential obstruction on the tracks using Convolutional Neural Networks You Only Look Once version 8 is used. YOLOv8 is a high speed and accurate model; is trained with a custom dataset which is proposed in this paper. If any obstruction is detected it will inform to the train pilot and nearest stations for testing purpose mailing service is used which helps in taking necessary actions. With appropriate alerts will improve safety and efficiency on railway tracks in the forest areas by providing real time information about potential obstructions on the tracks. This directly helps in preventing accidents and delays. Ensures a safer and more reliable railway network.

关键词： YOLO Training Accuracy Computational modeling Forestry Streaming media Real-time systems data models Safety Object recognition

来源：评论

学校读者我要写书评

暂无评论

Enhanced Radiological Anomaly Detection using Optimized YOLO-NAS Model

Enhanced Radiological Anomaly Detection using Optimized YOLO...

引用

Advances in Modern Age Technologies for Health and Engineering science (AMATHE), International Conference on

作者： Leka Shree J Emmanuel Joy Sri Ram M S Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798350371567

ISBN: (纸本)9798350371574

Chest X-rays are commonly used to detect lung diseases. Chest radiographs often have a lot of perceptual errors. The application of image processing in diagnosing lung diseases has improved medical imaging. This has also enabled the creation of databases for classifying chest radiographs. However, current methods are not accurate enough to reliably detect anomalies. Aimed at improving the shortcomings of existing techniques, the proposed approach uses the Automated Neural Architecture Construction (AutoNAC) engine, a proprietary of Neural Architecture Search (NAS). Comparative evaluations against established models, including YOLOv3, YOLOv5, YOLOv7, and YOLOv8, showcase the superiority of YOLO-NAS in mean Average Precision (mAP@0.5), precision, and recall metrics. The originality of this study lies in introducing NAS specifically AutoNAC, to optimize neural network architectures for chest X-ray anomaly detection, marking a significant advancement in diagnostic capabilities in medical imaging.

关键词： YOLO Pulmonary diseases X-rays Reliability Diagnostic radiography Anomaly detection X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

Advances in Privacy Preserving Federated learning to Realize a Truly learning Healthcare System

Advances in Privacy Preserving Federated Learning to Realize...

引用

IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)

作者： Ravi Madduri Zilinghan Li Tarak Nandi Kibaek Kim Minseok Ryu Alex Rodriguez Data Science and Learning Division Argonne National Laboratory Lemont IL USA Mathematics and Computer Science Argonne National Laboratory Lemont IL USA School of Computing and Augmented Intelligence Arizona State University Tempe AZ USA Data Science and Learning Argonne National Laboratory Lemont IL USA

ISBN: (数字)9798350386745

ISBN: (纸本)9798350386752

The concept of a learning healthcare system (LHS) envisions a self-improving network where multimodal data from patient care are continuously analyzed to enhance future healthcare outcomes. However, realizing this vision faces significant challenges in data sharing and privacy protection. Privacy-Preserving Federated learning (PPFL) is a transformative and promising approach that has the potential to address these challenges by enabling collaborative learning from decentralized data while safeguarding patient privacy. This paper proposes a vision for integrating PPFL into the healthcare ecosystem to achieve a truly LHS as defined by the Institute of Medicine (IOM) Roundtable.

关键词： Training data privacy Technological innovation Federated learning Biological system modeling Medical services data models Real-time systems Security Protection

来源：评论

学校读者我要写书评

暂无评论

From Galton to AI: A data-Driven Approach to Height Prediction Using Growth Curve Comparison and Parental data

From Galton to AI: A Data-Driven Approach to Height Predicti...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Praisy Petra C Sujitha Juliet Anitha J Division of Data Science and Cybersecurity Karunya Institute of Technology and Sciences Coimbatore India Division of Arificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Accurately predicting a child's height based on genetic and environmental factors is a longstanding challenge in medical and data science research. Traditional models, such as linear regression, SVM, and Random Forest, have been widely used. However, their accuracy varies due to the complexity of the environment, genetics which affects the height. This paper investigates the possibility of machine learning techniques, including deep learning techniques, accompanied by traditional models, to improve prediction accuracy for height. By combining more features and systematically partitioning datasets, the study compares various algorithms perform in predicting child height. These findings provide a comparative evaluation of these models, demonstrating the impact of feature selection and model architecture on prediction performance. The study aims to offer insights into selecting optimal models for practical applications in genetics, health analytics, and predictive modelling.

关键词： Deep learning Support vector machines Pediatrics Analytical models Accuracy Predictive models Epigenetics Complexity theory Cultural differences Random forests

来源：评论

学校读者我要写书评

暂无评论

Masked Sinogram Model with Transformer for ill-Posed Computed Tomography Reconstruction: a Preliminary Study

arXiv

引用

arXiv 2022年

作者： Liu, Zhengchun Kettimuthu, Rajkumar Foster, Ian Data Science and Learning Division Argonne National Laboratory United States

Computed Tomography (CT) is an imaging technique where information about an object are collected at different angles (called projections or scans). Then the cross-sectional image showing the internal structure of the slice is produced by solving an inverse problem. Limited by certain factors such as radiation dosage, projection angles, the produced images can be noisy or contain artifacts. Inspired by the success of transformer for natural language processing, the core idea of this preliminary study is to consider a projection of tomography as a word token, and the whole scan of the cross-section (A.K.A. sinogram) as a sentence in the context of natural language processing. Then we explore the idea of foundation model by training a masked sinogram model (MSM) and fine-tune MSM for various downstream applications including CT reconstruction under data collections restriction (e.g., photon-budget) and a data-driven solution to approximate solutions of the inverse problem for CT reconstruction. Models and data used in this study are available at https://***/lzhengchun/TomoTx. Copyright © 2022, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Real-time porosity mapping and visualization for synchrotron tomography

TechRxiv

引用

TechRxiv 2022年

作者： Tekawade, Aniket Nikitin, Viktor Satapathy, Yashas Liu, Zhengchun Zhang, Xuan Kenesei, Peter De Carlo, Francesco Kettimuthu, Rajkumar Foster, Ian Argonne National Laboratory United States The Data Science and Learning Division The X-ray Science Division The Nuclear Science Division

Applications of X-ray computed tomography (CT) for porosity characterization of engineering materials often involve an extended data analysis workflow that includes CT reconstruction of raw projection data, binarization, labeling and mesh extraction. It is often desirable to map the porosity in larger samples but the computational challenge of reducing gigabytes of raw data to porosity information poses a critical bottleneck. In this work, we describe algorithms and implementation of an end-to-end porosity mapping code that processes raw projection data from a synchrotron CT instrument into a porosity map and visualization in the form of triangular face mesh. Towards this objective, we report the development of a novel subset reconstruction scheme for X-ray CT using filtered back-projection and a convolutional neural network that allows us to reconstruct arbitrarily-shaped subsets of a tomography object. We build upon this scheme to implement the complete code for porosity mapping. The code first detects possible voids by performing a coarse reconstruction on down-sampled projections and then improves the shape of those voids with higher detail offered by reconstructing selected subsets from the original raw data. We report measurements of the time taken by this code to perform complete processing from raw data to a triangular face mesh for several visualization scenarios on a single high-performance workstation equipped with GPU. We show that we can now visualize local porosity within a 8 gigavoxel CT volume (12 gigabytes raw data) within 1 to 2 minutes and a 64 gigavoxel CT volume (100 gigabytes of raw data) within 3 to 7 minutes. © 2022, CC BY.

关键词： 3D printers

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：