检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

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. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Learner Action Patterns in the Problem-Solving Process Related to program Code Composition Based on Tracking System Activities 7

Learner Action Patterns in the Problem-Solving Process Relat...

引用

7th International Conference on Informatics and Computing, ICIC 2022

作者： Syahidi, Aulia Akhrian Supianto, Ahmad Afif Hirashima, Tsukasa Watanobe, Yutaka Politeknik Negeri Banjarmasin Smart City Information System Applied Undergraduate Program Banjarmasin City Indonesia Research Center for Data and Information Sciences Bandung City Indonesia Graduate School of Advanced Science and Engineering Hiroshima University Kagamiyama Learning Engineering Laboratory Higashihiroshima Japan University of Aizu Division of Information Systems Department of Computer Science and Engineering Fukushima AizuWakamatsu Japan

ISBN: (纸本)9798350345711

Learning activities are an indicator of the learner's desire to learn during the learning process. The pattern of learner action is related to learning activities. In this case, in extracting the learning process, it is necessary to collect a lot of data through analysis of the learning process. The purpose of this study is to recommend and report the performance of an activity tracking system equipped with visual artifacts as an educational data mining approach to analyze action patterns when learners complete the arrangement of program code lines in each programming problem. In this study, data were taken from activity recordings when learners used interactive learning media for a basic programming subject called TOLSYASUPI-EduMed which had problem-solving learning models embedded in their interactions. Learning Analytics is used as a method of this research and data relationships from learner actions during the learning process using the 'if-then' rule. Log data is used for recording and detecting activities carried out by learners. We confirm that the results of the study are based on the findings of the data relationship that if the lines of program code are too long (more than five lines) then almost all learners experience a bottleneck condition. The completion time of each question and the number of iterations in completing the program code lines for each question have also been recorded and have a pattern of connection between the data. The information that has been obtained is then forwarded to teachers or stakeholders as key information to make appropriate feedback to learners based on the results as a means of analyzing and evaluating the programming learning process. © 2022 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

GENERATIVE MODELING OF TIME-DEPENDENT DENSITIES VIA OPTIMAL TRANSPORT AND PROJECTION PURSUIT

arXiv

引用

arXiv 2023年

作者： Botvinick-Greenhouse, Jonah Yang, Yunan Maulik, Romit Center for Applied Mathematics Cornell University IthacaNY14850 United States Department of Mathematics Cornell University IthacaNY14853 United States College of Information Science and Technology Pennsylvania State University University ParkPA16802 United States Joint Appointment Faculty Mathematics and Computer Science Division Argonne National Laboratory LemontIL60439 United States

Motivated by the computational difficulties incurred by popular deep learning algorithms for the generative modeling of temporal densities, we propose a cheap alternative which requires minimal hyperparameter tuning and scales favorably to high dimensional problems. In particular, we use a projection-based optimal transport solver [Meng et al., 2019] to join successive samples and subsequently use transport splines [Chewi et al., 2020] to interpolate the evolving density. When the sampling frequency is sufficiently high, the optimal maps are close to the identity and are thus computationally efficient to compute. Moreover, the training process is highly parallelizable as all optimal maps are independent and can thus be learned simultaneously. Finally, the approach is based solely on numerical linear algebra rather than minimizing a nonconvex objective function, allowing us to easily analyze and control the algorithm. We present several numerical experiments on both synthetic and real-world datasets to demonstrate the efficiency of our method. In particular, these experiments show that the proposed approach is highly competitive compared with state-of-the-art normalizing flows conditioned on time across a wide range of dimensionalities. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Narrative Analysis of True Crime Podcasts With Knowledge Graph-Augmented Large Language Models

arXiv

引用

arXiv 2024年

作者： Leng, Xinyi Liang, Jason Mauro, Jack Wang, Xu Chapman, James Bertozzi, Andrea L. Lin, Junyuan Chen, Bohan Ye, Chenchen Daniel, Temple Brantingham, P. Jeffrey Carleton College Department of Mathematics and Statistics United States Claremont McKenna College Department of Mathematical Sciences United States University of California Los Angeles Department of Mathematics United States Loyola Marymount University Department of Mathematics Statistics and Data Science United States California Institute of Technology Computing + Mathematical Sciences Division of Engineering and Applied Science United States University of California Los Angeles Department of Computer Science United States University of California Los Angeles Department of Anthropology United States

Narrative data spans all disciplines and provides a coherent model of the world to the reader or viewer. Recent advancement in machine learning and Large Language Models (LLMs) have enable great strides in analyzing natural language. However, Large language models (LLMs) still struggle with complex narrative arcs as well as narratives containing conflicting information. Recent work indicates LLMs augmented with external knowledge bases can improve the accuracy and interpretability of the resulting models. In this work, we analyze the effectiveness of applying knowledge graphs (KGs) in understanding true-crime podcast data from both classical Natural Language Processing (NLP) and LLM approaches. We directly compare KG-augmented LLMs (KGLLMs) with classical methods for KG construction, topic modeling, and sentiment analysis. Additionally, the KGLLM allows us to query the knowledge base in natural language and test its ability to factually answer questions. We examine the robustness of the model to adversarial prompting in order to test the model's ability to deal with conflicting information. Finally, we apply classical methods to understand more subtle aspects of the text such as the use of hearsay and sentiment in narrative construction and propose future directions. Our results indicate that KGLLMs outperform LLMs on a variety of metrics, are more robust to adversarial prompts, and are more capable of summarizing the text into topics. © 2024, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Day-Ahead Forecasting of Solar Irradiance & PV Power Output Through Statistical Machine Learning Methods

Day-Ahead Forecasting of Solar Irradiance & PV Power Output ...

引用

Saudi Arabia Smart Grid Conference (SASG)

作者： Yiannis Kamarianakis Yannis Pantazis Evangelia Kalligiannaki Theodoros D. Katsaounis Konstantinos Kotsovos Issam Gereige Marwan Abdullah Aqil Jamal Athanasios Tzavaras Data Science Group Institute of Applied and Computational Mathematics Foundation for Research and Technology-Hellas Greece Dept. of Mathematics and Applied Mathematics University of Crete Greece Carbon Management Division Saudi Aramco R&D Center Dhahran Saudi Arabia Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

Energy production from solar photovoltaic (PV) plants is unpredictable, mainly due to the stochastic formation and movement of clouds or aerosol - dust particles which scatter or disperse solar radiation. Accurate forecasts of PV output are essential to Distribution and Transportation System Operators as they assist efficient solar energy trading and management of electricity grids. This work evaluates an autoregressive, computationally-light KNN-regression scheme (TSFKNN) for hourly, day-ahead forecasts of solar irradiance and energy yield of various PV technologies. The model is being tested and validated using data measured in Thuwal, Saudi Arabia. The available measured records span a 60-month period. The developed forecasting models are designed for online systems and provide increased levels of accuracy and low computational cost. Several parametric and nonparametric specifications, coupled with conventional versus outlier-robust estimation procedures are tested, in order to derive an optimal month-specific daily profile (MDP). Current results demonstrate that including intraday variability to the monthly-based irradiance models achieve improved predictive accuracy between 10% and 25% on average.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A FLOW ARTIST FOR HIGH-DIMENSIONAL CELLULAR DATA

arXiv

引用

arXiv 2023年

作者： MacDonald, Kincaid Bhaskar, Dhananjay Thampakkul, Guy Nguyen, Nhi Zhang, Joia Perlmutter, Michael Adelstein, Ian Krishnaswamy, Smita Department of Mathematics Yale University United States Department of Genetics Yale School of Medicine United States Department of Computer Science Yale University United States Department of Mathematics Pomona College United States Applied Mathematics Program Yale University United States Department of Statistics University of Washington United States Department of Mathematics Boise State University United States Computational Biology and Bioinformatics Program Yale University United States

We consider the problem of embedding point cloud data sampled from an underlying manifold with an associated flow or velocity. Such data arises in many contexts where static snapshots of dynamic entities are measured, including in high-throughput biology such as single-cell transcriptomics. Existing embedding techniques either do not utilize velocity information or embed the coordinates and velocities independently, i.e., they either impose velocities on top of an existing point embedding or embed points within a prescribed vector field. Here we present FlowArtist, a neural network that embeds points while jointly learning a vector field around the points. The combination allows FlowArtist to better separate and visualize velocity-informed structures. Our results, on toy datasets and single-cell RNA velocity data, illustrate the value of utilizing coordinate and velocity information in tandem for embedding and visualizing high-dimensional data. © 2023, CC BY.

关键词： RNA

来源：评论

学校读者我要写书评

暂无评论

Feynman checkers: lattice quantum field theory with real time

arXiv

引用

arXiv 2022年

作者： Skopenkov, Mikhail Ustinov, Alexey King Abdullah University of Science and Technology Saudi Arabia HSE University Faculty of Mathematics Russia HSE University Faculty of Computer Science Russia Khabarovsk Division of the Institute for Applied Mathematics Far-Eastern Branch Russian Academy of Sciences Russia

We present a new completely elementary model that describes the creation, annihilation, and motion of non-interacting electrons and positrons along a line. It is a modification of the model known under the names Feynman checkers or one-dimensional quantum walk. It can be viewed as a six-vertex model with certain complex weights of the vertices. The discrete model is consistent with the continuum quantum field theory, namely, reproduces the known expected charge density as the lattice step tends to zero. It is exactly solvable in terms of hypergeometric functions. We introduce interaction resembling Fermi's theory and establish perturbation *** Codes 81T25, 81T27, 81T40, 82B20, 82B23, 33C45 Copyright © 2022, The Authors. All rights reserved.

关键词： Lattice theory

来源：评论

学校读者我要写书评

暂无评论

A Trusted Reputation Management Scheme for Cross-Chain Transactions

引用

Sensors 2023年第13期23卷 6033页

作者： Chen, Kuongho Lee, Lin-Fa Chiu, Wayne Su, Chunhua Yeh, Kuo-Hui Chao, Han-Chieh ezPay Co. Ltd Taipei11578 Taiwan Department of Information Management National Dong Hwa University Hualien97401 Taiwan Department of Applied Mathematics and Computer Science Technical University of Denmark Lyngby2800 Denmark Division of Computer Science University of Aizu Fukushima965-0006 Japan Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung80424 Taiwan Institute of Computer Science and Innovation UCSI University Kuala Lumpur5600 Malaysia

Blockchain has become a well-known, secured, decentralized datastore in many domains, including medical, industrial, and especially the financial field. However, to meet the requirements of different fields, platforms that are built on blockchain technology must provide functions and characteristics with a wide variety of options. Although they may share similar technology at the fundamental level, the differences among them make data or transaction exchange challenging. Cross-chain transactions have become a commonly utilized function, while at the same time, some have pointed out its security loopholes. It is evident that a secure transaction scheme is desperately needed. However, what about those nodes that do not behave? It is clear that not only a secure transaction scheme is necessary, but also a system that can gradually eliminate malicious players is of dire need. At the same time, integrating different blockchain systems can be difficult due to their independent architectures, and cross-chain transactions can be at risk if malicious attackers try to control the nodes in the cross-chain system. In this paper, we propose a dynamic reputation management scheme based on the past transaction behaviors of nodes. These behaviors serve as the basis for evaluating a node’s reputation to support the decision on malicious behavior and enable the system to intercept it in a timely manner. Furthermore, to establish a reputation index with high precision and flexibility, we integrate Particle Swarm Optimization (PSO) into our proposed scheme. This allows our system to meet the needs of a wide variety of blockchain platforms. Overall, the article highlights the importance of securing cross-chain transactions and proposes a method to prevent misbehavior by evaluating and managing node reputation. © 2023 by the authors.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Infected Lung Computed Tomography Segmentation and Supervised Classification Approach

引用

computers, Materials & Continua 2021年第7期68卷 391-407页

作者： Aqib Ali Wali Khan Mashwani Samreen Naeem Muhammad Irfan Uddin Wiyada Kumam Poom Kumam Hussam Alrabaiah Farrukh Jamal Christophe Chesneau Department of Computer Science Concordia College BahawalpurBahawalpur63100Pakistan Department of Computer Science&IT Glim Institute of Modern StudiesBahawalpur63100Pakistan Institute of Numerical Sciences Kohat University of Science&TechnologyKohat26000Pakistan Institute of Computing Kohat University of Science and TechnologyKohat26000Pakistan Program in Applied Statistics Department of Mathematics and Computer ScienceFaculty of Science and TechnologyRajamangala University of Technology ThanyaburiThanyaburi12110Thailand Departments of Mathematics Faculty of ScienceCenter of Excellence in Theoretical and Computational Science(TaCS-CoE)&KMUTT Fixed Point Research LaboratoryRoom SCL 802 Fixed Point LaboratoryScience Laboratory BuildingKing Mongkut’s University of Technology Thonburi(KMUTT)Bangkok10140Thailand Department of Medical Research China Medical University HospitalTaichung40402Taiwan College of Engineering Al Ain UniversityAl Ain64141United Arab Emirates Department of Mathematics Tafila Technical UniversityTafila66110Jordan Department of Statistics The Islamia University of BahawalpurBahawalpur63100Pakistan 11Department of MathematicsUniversitéde CaenLMNOCaen14032France

The purpose of this research is the segmentation of lungs computed tomography(CT)scan for the diagnosis of COVID-19 by using machine learning *** dataset contains data from patients who are prone to the *** contains three types of lungs CT images(Normal,Pneumonia,and COVID-19)collected from two different sources;the first one is the Radiology Department of Nishtar Hospital Multan and Civil Hospital Bahawalpur,Pakistan,and the second one is a publicly free available medical imaging database known as *** the preprocessing,a novel fuzzy c-mean automated region-growing segmentation approach is deployed to take an automated region of interest(ROIs)and acquire 52 hybrid statistical features for each ***,12 optimized statistical features are selected via the chi-square feature reduction *** the classification,five machine learning classifiers named as deep learning J4,multilayer perceptron,support vector machine,random forest,and naive Bayes are deployed to optimize the hybrid statistical features *** is observed that the deep learning J4 has promising results(sensitivity and specificity:0.987;accuracy:98.67%)among all the deployed *** a complementary study,a statistical work is devoted to the use of a new statistical model to fit the main datasets of COVID-19 collected in Pakistan.

关键词： COVID-19 machine learning fuzzy c-mean deep learning J4

来源：评论

学校读者我要写书评

暂无评论

Parallel Approximations for High-Dimensional Multivariate Normal Probability Computation in Confidence Region Detection Applications

arXiv

引用

arXiv 2024年

作者： Zhang, Xiran Abdulah, Sameh Cao, Jian Ltaief, Hatem Sun, Ying Genton, Marc G. Keyes, David E. Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Saudi Arabia Statistics Program King Abdullah University of Science and Technology Saudi Arabia Extreme Computing Research Center King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Department of Mathematics The University of Houston HoustonTX United States

Addressing the statistical challenge of computing the multivariate normal (MVN) probability in high dimensions holds significant potential for enhancing various applications. For example, the critical task of detecting confidence regions where a process probability surpasses a specific threshold is essential in diverse applications, such as pinpointing tumor locations in magnetic resonance imaging (MRI) scan images, determining hydraulic parameters in groundwater flow issues, and forecasting regional wind power to optimize wind turbine placement, among numerous others. One common way to compute high-dimensional MVN probabilities is the Separation-of- Variables (SOV) algorithm. This algorithm is known for its high computational complexity of O(n3) and space complexity of O(n2), mainly due to a Cholesky factorization operation for an n × n covariance matrix, where n represents the dimensionality of the MVN problem. This work proposes a high-performance computing framework that allows scaling the SOV algorithm and, subsequently, the confidence region detection algorithm. The framework leverages parallel linear algebra algorithms with a task-based programming model to achieve performance scalability in computing process probabilities, especially on largescale systems. In addition, we enhance our implementation by incorporating Tile Low-Rank (TLR) approximation techniques to reduce algorithmic complexity without compromising the necessary accuracy. To evaluate the performance and accuracy of our framework, we conduct assessments using simulated data and a wind speed dataset. Our proposed implementation effectively handles high-dimensional multivariate normal (MVN) probability computations on shared and distributed-memory systems using finite precision arithmetics and TLR approximation computation. Performance results show a significant speedup of up to 20X in solving the MVN problem using TLR approximation compared to the reference dense solution without sacrificing the

关键词： Statistics

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：