检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Musslick, Sebastian Bartlett, Laura K. Chandramouli, Suyog H. Dubova, Marina Gobet, Fernand Griffiths, Thomas L. Hullman, Jessica King, Ross D. Nathan Kutz, J. Lucas, Christopher G. Mahesh, Suhas Pestilli, Franco Sloman, Sabina J. Holmes, William R. Institute of Cognitive Science Osnabrück University Osnabrück49090 Germany Department of Cognitive Linguistic & Psychological Sciences Brown University ProvidenceRI02912 United States Centre for Philosophy of Natural and Social Science London School of Economics Lakatos Building Houghton Street LondonWC2A 2AE United Kingdom AaltoFI-00076 Finland Department of Computing Science University of Alberta 8900 114 St NW EdmontonABT6G 2S4 Canada Cognitive Science Program Indiana University 1101 E 10th St BloomingtonIN47405 United States School of Psychology University of Roehampton LondonSW15 4JD United Kingdom Departments of Psychology and Computer Science Princeton University PrincetonNJ United States Department of Computer Science Northwestern University IL United States Department of Chemical Engineering and Biotechnology University of Cambridge CambridgeCB3 0AS United Kingdom Department of Computer Science and Engineering Chalmers University of Technology Gothenburg412 96 Sweden Department of Applied Mathematics and Electrical and Computer Engineering University of Washington Seattle98195 United States School of Informatics University of Edinburgh 10 Crichton St. EH8 9AB United Kingdom Department of Materials Science and Engineering University of Toronto Canada Department of Psychology Department of Neuroscience The University of Texas AustinTX United States Department of Computer Science University of Manchester M13 9PL United Kingdom

Automation transformed various aspects of our human civilization, revolutionizing industries and streamlining processes. In the domain of scientific inquiry, automated approaches emerged as powerful tools, holding promise for accelerating discovery, enhancing reproducibility, and overcoming the traditional impediments to scientific progress. This article evaluates the scope of automation within scientific practice and assesses recent approaches. Furthermore, it discusses different perspectives to the following questions: Where do the greatest opportunities lie for automation in scientific practice?;What are the current bottlenecks of automating scientific practice?;and What are significant ethical and practical consequences of automating scientific practice? By discussing the motivations behind automated science, analyzing the hurdles encountered, and examining its implications, this article invites researchers, policymakers, and stakeholders to navigate the rapidly evolving frontier of automated scientific practice. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Preface

EAI/Springer Innovations in Communication and Computing

引用

EAI/Springer Innovations in Communication and Computing 2023年 Part F274卷 vii-viii页

作者： Joseph, Ferdin Joe John Balas, Valentina Emilia Rajest, S. Suman Regin, R. Thai-Nichi Institute of Technology Bangkok Thailand Department of Automation and Applied Informatics Aurel Vlaicu University of Arad Arad Arad Romania Department of Research Arts and Humanities Bharath Institute of Higher Education and Research Tamil Nadu Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Tamil Nadu Chennai India

来源：评论

学校读者我要写书评

暂无评论

Accelerating SDN control plane with GPGPU-based packet classification

Accelerating SDN control plane with GPGPU-based packet class...

引用

International Conference on Emerging eLearning Technologies and Applications (ICETA)

作者： Martin Baláž Pavol Helebrandt Slovak University of Technology Institute of Computer Engineering and Applied Informatics Bratislava Slovakia

ISBN: (数字)9781728149677

ISBN: (纸本)9781728149684

The increasing number of network traffic and packet processing in Software Defined Networks can be a challenge for the slower handling performance by control plane in software. Parallel processing of network traffic offers a solution to increase the performance of software-based control planes. Integrating large amounts of additional general-purpose CPU cores is relatively costly for achieving a substantial boost in packet classification by parallel processing. In contrast, simplified compute cores in the GPUs of today deliver better performance in execution of massively parallel tasks and offer better scalability. The motivation of this work is to utilize the performance of the GPU computational power for acceleration of control plane. The focus of this paper is packet classification in parallel processing on GPU by applying the principles of parallel programming into existing algorithms.

关键词： Graphics processing units Acceleration Classification algorithms Firewalls (computing) Telecommunication traffic Process control

来源：评论

学校读者我要写书评

暂无评论

Pruning neural networks without any data by iteratively conserving synaptic flow 20

Pruning neural networks without any data by iteratively cons...

引用

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Hidenori Tanaka Daniel Kunin Daniel L. K. Yamins Surya Ganguli Physics & Informatics Laboratories NTT Research Inc. Department of Applied Physics Stanford University Institute for Computational and Mathematical Engineering Stanford University Department of Psychology Department of Computer Science Stanford University Department of Applied Physics Stanford University

ISBN: (纸本)9781713829546

Pruning the parameters of deep neural networks has generated intense interest due to potential savings in time, memory and energy both during training and at test time. Recent works have identified, through an expensive sequence of training and pruning cycles, the existence of winning lottery tickets or sparse trainable subnetworks at initialization. This raises a foundational question: can we identify highly sparse trainable subnetworks at initialization, without ever training, or indeed without ever looking at the data? We provide an affirmative answer to this question through theory driven algorithm design. We first mathematically formulate and experimentally verify a conservation law that explains why existing gradient-based pruning algorithms at initialization suffer from layer-collapse, the premature pruning of an entire layer rendering a network untrainable. This theory also elucidates how layer-collapse can be entirely avoided, motivating a novel pruning algorithm Iterative Synaptic Flow Pruning (SynFlow). This algorithm can be interpreted as preserving the total flow of synaptic strengths through the network at initialization subject to a sparsity constraint. Notably, this algorithm makes no reference to the training data and consistently competes with or outperforms existing state-of-the-art pruning algorithms at initialization over a range of models (VGG and ResNet), datasets (CIFAR-10/100 and Tiny ImageNet), and sparsity constraints (up to 99.99 percent). Thus our data-agnostic pruning algorithm challenges the existing paradigm that, at initialization, data must be used to quantify which synapses are important.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cost optimization in CNN for big data of share price

引用

AIP Conference Proceedings 2023年第1期2587卷

作者： R. Saravanakumar Gokul Talele Ali Hazim Alyamoor Kaushal Kishor Bhatt Prashant Vats Malik Bader Alazzam Dept. of Computer Science and Engineering Dayananda Sagar Academy of Technology and Management Bangalore India Dept. of Data Science IIIT Banglore India Dept. of Accounting Economic and Administration College University of Mosul Ninawa Iraq Dept. of Computer Science and Engineering Birla Institute of Applied Science Bhimtal Nainital Uttarakhand India Dept. of Computer Science and Engineering Dr. Akhilesh Das Gupta Institute of Technology and Management New Delhi India Faculty of Computer Science and Informatics Amman Arab University Mubis-Amman Jordan

Optimization of share price in order to evaluate whether to invest in specific share or not is subject of study paper. Optimized value has been utilized to enhance the performance and accuracy when dataset is trained using CNN. Review has been given on big cap, mid cap & small cap fund which are accessible in large, medium and small amount for the purpose of investing. It has been found that share in big cap are more dependable but offers limited return. However share in case of mid cap are considered comparatively more hazardous than big cap yet return may be substantial. The suggested study has given mechanism that will make use of optimization mechanism to filter the data set considering PSO and MVO mechanism. The suggested CNN based training model is claimed high performance system with improved accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI

arXiv

引用

arXiv 2024年

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina Aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. © 2024, CC BY-NC-ND.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

The rank of contextuality

arXiv

引用

arXiv 2022年

作者： Horodecki, Karol Zhou, Jingfang Stankiewicz, Maciej Salazar, Roberto Horodecki, Pawel Raussendorf, Robert Horodecki, Ryszard Ramanathan, Ravishankar Tyhurst, Emily Institute of Informatics National Quantum Information Centre Faculty of Mathematics Physics and Informatics University of Gdańsk Wita Stwosza 57 Gdańsk80-308 Poland International Centre for Theory of Quantum Technologies University of Gdańsk Wita Stwosza 63 Gdańsk80-308 Poland Department of Applied Physics Graduate School of Engineering University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Kraków30-348 Poland Faculty of Applied Physics and Mathematics National Quantum Information Centre Gdańsk University of Technology Gabriela Narutowicza 11/12 Gdańsk80-233 Poland Department of Physics and Astronomy University of British Columbia VancouverBCV6T 1Z1 Canada Department of Computer Science The University of Hong Kong Pokfulam Road Hong Kong Department of Physics University of Toronto TorontoON Canada

Quantum contextuality is one of the most recognized resources in quantum communication and computing scenarios. We provide a new quantifier of this resource, the rank of contextuality (RC). We define RC as the minimum number of non-contextual behaviors that are needed to simulate a contextual behavior. We show that the logarithm of RC is a natural contextuality measure satisfying several properties considered in the spirit of the resource-theoretic approach. The properties include faithfulness, monotonicity, and additivity under tensor product. We also give examples of how to construct contextual behaviors with an arbitrary value of RC exhibiting a natural connection between this quantifier and the arboricity of an underlying hypergraph. We also discuss exemplary areas of research in which the new measure appears as a natural quantifier. Copyright © 2022, The Authors. All rights reserved.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

Influence of Structural Defects on Charge Density Waves in 1T-TaS2

arXiv

引用

arXiv 2023年

作者： Lutsyk, I. Szalowski, K. Krukowski, P. Dabrowski, P. Rogala, M. Kozlowski, W. Le Ster, M. Piskorski, M. Kowalczyk, D.A. Rys, W. Dunal, R. Nadolska, A. Toczek, K. Przybysz, P. Lacinska, E. Binder, J. Wysmolek, A. Olszowska, N. Kolodziej, J.J. Gmitra, M. Hattori, T. Kuwahara, Y. Bian, G. Chiang, T.-C. Kowalczyk, P.J. Faculty of Physics and Applied Informatics University of Lodz Pomorska 149/153 Lodz90-236 Poland Faculty of Physics University of Warsaw Pasteura 5 Warsaw02-093 Poland Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Lojasiewicza 11 Krakow30-348 Poland National Synchrotron Radiation Centre SOLARIS Jagiellonian University Czerwone Maki 98 Kraków30-392 Poland Institute of Physics Faculty of Science Pavol Jozef Šafárik University in Košice Park Angelinum 9 Košice040 01 Slovakia Institute of Experimental Physics Slovak Academy of Sciences Watsonova 47 Košice040 01 Slovakia Department of Precision Engineering Graduate School of Engineering Osaka University 2-1 Yamada-oka Suita565-0871 Japan Department of Physics and Astronomy University of Missouri ColumbiaMO65211 United States Department of Physics Frederick Seitz Materials Research Laboratory University of Illinois at Urbana-Champaign UrbanaIL61801-3080 United States

The influence of intrinsic defects of 1T-TaS2 on charge density waves (CDW) is studied using scanning tunneling microscopy and spectroscopy (STM, STS), angle-resolved photoelectron spectroscopy (ARPES), and density functional theory (DFT). We identify several types of structural defects and find that most have a local character limited to the single CDW site, with single exception which effectively behaves as a dopant, leading to band bending and affecting multiple neighboring sites. While only one type of defect can be observed by STM topographic imaging, all defects are easily resolved by local density of states (LDOS) mapping with STS. We correlate atomically-resolved STM periodicity of defect-free 1T-TaS2 to top sulfur atoms and introduce tiling of the surface using equiangular hexagon. DFT calculations (with included Coulomb interactions) are used to investigate the electronic structure by introducing sulfur vacancy or substituting sulfur with oxygen. The sulfur vacancy is characterized by metallic properties and is identified as an origin of one of observed experimentally defects. Whereas in the case of the latter, the oxidation of 1T-TaS2 is found to result in the loss of magnetic properties expected in defect-free material. © 2023, CC0.

关键词： Charge density waves

来源：评论

学校读者我要写书评

暂无评论

C3BAM-XAI: Convolutional Block Attention Module Enhanced Explainable Artificial Intelligence-Based Parkinson’s Disease Stage Classification

引用

Cognitive Computation 2025年第3期17卷 1-19页

作者： Abbas, Muhammad John Khan, Muhammad Attique Hamza, Ameer Alsenan, Shrooq Rehman, Aleesha Baili, Jamel Zhang, Yudong Department of Computer Science HITEC University Taxila47080 Pakistan Center of Artificial Intelligence College of Computer Engineering and Science Prince Mohammad Bin Fahd University Al-Khobar Saudi Arabia Centre of Real Time Computer Systems Kaunas University of Technology Kaunas51368 Lithuania Information Systems Department College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Pak-Austria Fachhochschule Institute of Applied Sciences and Technology Haripur Mang Pakistan Department of Computer Engineering College of Computer Science King Khalid University Abha61413 Saudi Arabia Department of Informatics University of Leicester Leicester United Kingdom

Parkinson’s disease (PD) is a progressive neurodegenerative disorder that causes significant impairment in neurons, physiological structures, and behavior of people. However, these changes are very subtle in the early stages of PD, making diagnosis and treatment challenging. To overcome such challenges, we proposed a novel convolutional neural network (CNN) architecture called C3BAM-XAI that is based on the convolutional block attention module (CBAM) enhanced CNN and explainable artificial intelligence (XAI). In the proposed architecture, the data imbalance issue was resolved at the initial stage by employing augmentation techniques for the training data. After that, the proposed CNN architecture is designed with CBAM. The CBAM architecture is based on two sub-modules—the channel attention module and the spatial attention module. The input of the initial convolutional layer is passed to the channel attention module, which is further passed to the spatial attention module for more critical information extraction. For smooth training, hyperparameters are selected using Nadam Optimization (NO) instead of manual assignment. In the testing phase, features are extracted from the dense layer and passed to several neural network classifiers. In addition to this, the designed model is interpreted using the explainable AI technique to see the predicted label and insight decision features. The experimental process was performed on the publically available PD Kaggle dataset and obtained an improved accuracy of 93.33%. In addition, several ablation studies were conducted, and it is concluded that the CBAM not only improved accuracy but also made this model a reliable tool for clinical diagnosis, both in terms of accuracy and interpretability. The results thus open new avenues toward applying deep learning models practically for applications in the medical domain and early-stage detection of Parkinson’s disease, thereby helping to improve patient outcomes. © The Author(s), under

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

SVTest: general purpose software for testing weakly random sources with exemplary application to seismic data analysis enabling quantum amplification

arXiv

引用

arXiv 2025年

作者： Stankiewicz, Maciej Salazar, Roberto Czechlewski, Mikolaj Jensen, Alejandra Muñoz Morales-Yáñez, Catalina Sakarya, Omer Carrasco, Julio Viveros Horodecki, Karol Institute of Informatics Faculty of Mathematics Physics and Informatics University of Gdańsk Wita Stwosza 57 Gdańsk80-308 Poland University of Malta MsidaMSD 2080 Malta Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Kraków30-348 Poland Institute of Informatics National Quantum Information Centre Faculty of Mathematics Physics and Informatics University of Gdańsk Wita Stwosza 57 Gdańsk80-308 Poland EMGG TerraData Limitada Concepción Chile Department of Geophysics Universidad de Concepción Concepción Chile Department of Civil Engineering Universidad Católica de la Santísima Concepción Concepción Chile

Generating private randomness is essential for numerous applications ranging from security proofs to online banking. Consequently, the capacity of quantum devices to amplify the privacy of a weak source of randomness, in cases unattainable by classical methods, constitutes a practical advantage. One of the theoretical models of such weak sources are the so-called Santha-Vazirani (SV) sources;however, finding natural sources satisfying the SV model is a paramount challenge. In this article, we take three significant steps on the way to simplify this hard task. We begin with an in-depth analysis of the mathematical background for estimating the quality of a weak randomness source by providing a set of axioms that systematize the possible approaches to such estimation. We then develop software (SVTest) to estimate the parameter characterizing the source’s randomness. The software is general-purpose, i.e., it can test the randomness of any target sequence of bits. Later, we apply the software to test seismic events (earthquakes and local noise) as potential sources of randomness. Our results demonstrate that seismic phenomena are possible sources of randomness, depending on the choice of discretization. Therefore, our work provides strong evidence of the potential of geophysical phenomena as a source of cryptographic resources, building an unprecedented bridge between both fields. Copyright © 2025, The Authors. All rights reserved.

关键词： Seismic response

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：