检索结果-内蒙古大学图书馆

Technology Innovation and Its Applications (ICTIIA), International Conference on

作者： Atikah Rahayu Mandasari Erna Budhiarti Nababan Herman Mawengkang Master of Informatics Program Universitas Sumatera Utara Medan Indonesia Faculty Of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Faculty of Mathematics and Natural Sciences Universitas Sumatera Utara Medan Indonesia

ISBN: (数字)9798350351613

ISBN: (纸本)9798350351620

This research discusses the improvement of Long Short-Term Memory (LSTM) model accuracy in translating Batak to Indonesian by utilizing FastText and GloVe embeddings. Traditional LSTM models often struggle with the complexity and richness of underrepresented languages like Batak. By integrating FastText and GloVe, which provide word vectors with deeper semantic meanings, the translation quality can be significantly enhanced. Experimental results show that this approach offers a substantial performance improvement compared to conventional LSTM models, producing more accurate and contextual translations. These findings have the potential to be applied in broader multilingual translation systems and support the preservation and digital accessibility of minority languages.

关键词： Long short term memory Training Vectors Accuracy Machine translation Vocabulary Predictive models Numerical models Decoding Context modeling

来源：评论

学校读者我要写书评

暂无评论

Drawing Lines for Measurement-Based Probabilistic Timing Analysis

Drawing Lines for Measurement-Based Probabilistic Timing Ana...

引用

Real-Time Systems Symposium (RTSS)

作者： Tadeu Nogueira C. Andrade George Lima Verônica Maria Cadena Lima Graduate Program in Computer Science Federal University of Bahia Salvador Bahia Brazil Institute of Computing Federal University of Bahia Salvador Bahia Brazil Institute of Mathematics and Statistics Federal University of Bahia Salvador Bahia Brazil

ISBN: (数字)9798331540265

ISBN: (纸本)9798331540272

We describe DBL-MBPTA, a new approach for measurement-based probabilistic timing analysis (MBPTA). Unlike the usual MBPTA, which treats the time a program executes as a random variable, we consider both the number n of instructions executed in each measurement and the time $T(n)$ they took to execute. By taking tuples $(n, T(n))$, for various values of n, DBL-MBPTA allows for multiple execution path analysis. We show that $(n, T(n))$ can be bounded from below and above by two reference lines. The modeled random variable is the relative distance ($n, T(n)$) from these lines, which explains the term distance between lines (DBL) given to the approach. According to DBL-MBPTA, samples can be analyzed and improved, for which we employ deep neural networks. Once sample coverage is deemed representative, probabilistic bounds on execution time are estimated via the modeled relative distance. We evaluate our approach using both synthetic data and data collected through measurements on a multi-core platform. The results obtained demonstrate the effectiveness of DBL-MBPTA.

关键词： Lower bound Codes Processor scheduling Bandwidth Artificial neural networks Probabilistic logic Real-time systems Timing Random variables Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Autonomous Electron Tomography Reconstruction Using Bayesian Optimization

引用

Microscopy and microanalysis : the official journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada 2023年第1期29卷 1915-1916页

作者： Millsaps, William Schwartz, Jonathan Di, Zichao Wendy Jiang, Yi Hovden, Robert Department of Nuclear Engineering Radiological Sciences University of Michigan Ann Arbor MI United States Department of Materials Science and Engineering University of Michigan Ann Arbor MI United States Mathematics and Computer Science Division Argonne National Laboratory Lemont IL United States Advanced Photon Source Facility Argonne National Laboratory Lemont IL United States Applied Physics Program University of Michigan Ann Arbor MI United States

来源：评论

学校读者我要写书评

暂无评论

Modeling of Measurement Error in Financial Returns Data

arXiv

引用

arXiv 2024年

作者： Jasra, Ajay Maama, Mohamed Mijatović, Aleksandar School of Data Science The Chinese University of Hong Kong Shenzhen China Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Department of Statistics University of Warwick United Kingdom

In this paper we consider the modeling of measurement error for fund returns data. In particular, given access to a time-series of discretely observed log-returns and the associated maximum over the observation period, we develop a stochastic model which models the true log-returns and maximum via a Lévy process and the data as a measurement error there-of. The main technical difficulty of trying to infer this model, for instance Bayesian parameter estimation, is that the joint transition density of the return and maximum is seldom known, nor can it be simulated exactly. Based upon the novel stick breaking representation of [12] we provide an approximation of the model. We develop a Markov chain Monte Carlo (MCMC) algorithm to sample from the Bayesian posterior of the approximated posterior and then extend this to a multilevel MCMC method which can reduce the computational cost to approximate posterior expectations, relative to ordinary MCMC. We implement our methodology on several applications including for real data. Copyright © 2024, The Authors. All rights reserved.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Real Time Monitoring System of Drinking Water Quality Using Internet of Things 24

Real Time Monitoring System of Drinking Water Quality Using ...

引用

24th International Electronics Symposium, IES 2022

作者： Abidin, Zainul Maulana, Eka Nurrohman, Muhammad Yogi Wardana, Fitri Candra Warsito Universitas Brawijaya Faculty of Computer Science Department of Computer Engineering Malang Indonesia Universitas Brawijaya Faculty of Engineering Department of Electrical Engineering Malang Indonesia Universitas Brawijaya Master Program in Environmental Resources and Development Management Postgraduate School Malang Indonesia Universitas Brawijaya Faculty of Mathematics and Natural Sciences Department of Chemistry Malang Indonesia

ISBN: (数字)9781665489713

ISBN: (纸本)9781665489713

In order to reduce Polyethylene Terephthalate (PET) bottle plastic waste, Universitas Brawijaya (UB) provided reverse osmosis drinking water in some buildings. Water monitoring is needed to keep the water quality. Therefore, a water monitoring system based on Total Dissolved Solids (TDS), pH, and water flow was proposed. Since the UB buildings have good internet connection (WiFi), Internet of Things (IoT) was employed to the system to support real time monitoring. So, data of TDS, pH, and water flow can be periodically sent to cloud and displayed to a specific website. The system worked very well and the data can be summarized and used by operator as indicators of performance of the reverse osmosis machine. When water quality and performance decrease, operator must check filters membrane or water pump for further maintenance to support long life use. Although the sensors have been calibrated properly, some measurement errors occur. The measurement error percentages of TDS and pH are 0.62% and 0.94%, respectively. © 2022 IEEE.

关键词： Internet of things

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 41

Position: Bayesian Deep Learning is Needed in the Age of Lar...

引用

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

Cryptocurrency Analysis using Machine Learning and Deep Learning

Cryptocurrency Analysis using Machine Learning and Deep Lear...

引用

2021 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2021

作者： Thomas, C. Watson, Z. Kim, M. Baidya, A. Lamsal, M. Chowdhury, M.H. Basnet, M. Poudel, K.N. East Central University Department of Mathematics and Computer Science AdaOK United States Middle Tennessee State University Computational Science Program MurfreesboroTN United States University of Memphis Department of Electrical and Computer Engineering MemphisTN United States Embry-Riddle Aeronautical University Department of Mathematics and Data Science FL United States

来源：评论

学校读者我要写书评

暂无评论

Multilevel Monte Carlo for a class of Partially Observed Processes in Neuroscience

arXiv

引用

arXiv 2023年

作者： Maama, Mohamed Jasra, Ajay Kamatani, Kengo Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia School of Data Science The Chinese University of Hong Kong CN Shenzhen China Institute of Statistical Mathematics Tokyo190-0014 Japan

In this paper we consider Bayesian parameter inference associated to a class of partially observed stochastic differential equations (SDE) driven by jump processes. Such type of models can be routinely found in applications, of which we focus upon the case of neuroscience. The data are assumed to be observed regularly in time and driven by the SDE model with unknown parameters. In practice the SDE may not have an analytically tractable solution and this leads naturally to a time-discretization. We adapt the multilevel Markov chain Monte Carlo method of [15], which works with a hierarchy of time discretizations and show empirically and theoretically that this is preferable to using one single time discretization. The improvement is in terms of the computational cost needed to obtain a pre-specified numerical error. Our approach is illustrated on models applied to examples of Bayesian inference problems using both simulated and real observed data from neuroscience. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

ICT-based Knowledge Sharing in Rural Agricultural Communities: A Bibliometric Approach

ICT-based Knowledge Sharing in Rural Agricultural Communitie...

引用

2022 IEEE Technology and Engineering Management Society Conference - Asia Pacific, TEMSCON-ASPAC 2022

作者： Vorraakkatham, Kridtaphob Wiriyapinit, Mongkolchai Bhattarakosol, Pattarasinee Rajchamaha, Kittichai Graduate School Chulalongkorn University Technopreneurship and Innovation Management Program Bangkok Thailand Chulalongkorn University Chulalongkorn Business School Department of Commerce Bangkok Thailand Chulalongkorn University Department of Mathematics and Computer Science Bangkok Thailand Mahidol University College of Management Bangkok Thailand

ISBN: (数字)9781665427692

ISBN: (纸本)9781665427692

The ICTs are powerful tools for effective Knowledge sharing (KS) and facilitate data accessibility of rural communities. Even so, the direction of development and application of the ICTs in the context of ASEAN is still unclear. Hence, this study aims to specify such direction and tendency by employing the bibliometric analysis with a dataset of 81 studies extracted from Scopus database and summative content analysis, reaching conclusion regarding crucial factors and sustainable agricultural development. The outcome of this study could help reveal the precise direction of development and application of the ICTs in Rural agricultural community (RAC) as well as shed some light on necessary determinants for system enhancement and constraints which are useful for future studies on rural agricultural community development. © 2022 IEEE.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

The Classification Model of Learners Based on Diagnostic Assessment Results in E-learning With Machine Learning

The Classification Model of Learners Based on Diagnostic Ass...

引用

Software Engineering and Information Technology (ICoSEIT), International Conference on

作者： Mesra Betty Yel Muhammad Zarlis Saib Suwilo Syahril Efendi Poltak Sihombing Department of Computer Science Graduate Program of Computer Science Universitas Sumatera Utara Medan Indonesia Department of Computer Science Universitas Binus Jakarta Indonesia Department of Mathematics Universitas Sumatera Utara Medan Indonesia Department Of Computer Science Universitas Sumatera Utara Medan Indonesia

ISBN: (纸本)9781665473040

The development of technology and artificial intelligence, especially in the era of Industrial Revolution 4.0 almost covers all fields, one of which is e-learning. In its development, it is very important to determine the factors to produce the quality of e-learning. Machine learning can help to find various solutions in the real world, especially to solve problems for which a specific algorithm has not been found. The implementation of e-learning is often ineffective and not on target which has an impact on learning achievement that is not achieved, this is due to several things namely the learning model is applied in general, the learning materials and weights are applied equally to all users. Seeing these problems, it is necessary to have a model to classify students according to their abilities, talents, and interests before starting learning to achieve their goals to be achieved. This paper aims to create a machine learning approach model to determine the level of ability and needs of students before starting learning which can reduce disparities between students and follow up learning materials. With the machine learning based on learning model, e-learning can provide teaching materials according to the abilities, and interests of students, sustainably and improve the quality of students.

关键词： Training Electronic learning Machine learning algorithms Clustering algorithms Machine learning Classification algorithms Information technology

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：