检索结果-内蒙古大学图书馆

DataDecon: Data Cleansing Tools for Large Language Model with Efficient Decontamination Techniques

学校读者我要写书评

暂无评论

DataDecon: Data Cleansing Tools for Large Language Model wit...

International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSai-NLP)

作者： Sumeth Yuenyong Norapat Buppodom Koravich Sangkaew Konthee Boonmeeprakob Prachya Boonkwan Jillaphat Jaroenkantasima Pitikorn Khlaisamniang Anuruth Lertpiya Apivadee Piyatumrong Peerawat Rojratchadakorn Thaweewat Rugsujarit Teerapol Saengsukhiran Kriangkrai Saetan Isada Sukprapa Thanachot Thavornmongkol Nucharee Thongthungwong Patteera Triamamornwooth Chanon Utupon Kobkrit Viriyayudhakorn Phoochit Witchutanon Sadit Wongprayon Thepchai Supnithi Department of Computer Engineering Faculty of Engineering Mahidol University National Electronics and Computer Technology Center Pathumthani Thailand Artificial Intelligence Asssociation of Thailand Big Data Institute (Public Organization) Bangkok Department of Electrical Engineering Faculty of Engineering Kasetsart University Looloo Technology Faculty of Engineering Kasetsart University Kasikorn Labs Kasikorn Business Technology Group Faculty of Science King Mongkut’s Institute of Technology Ladkrabang School of Information Computer and Communication Technology Sirindhorn International Institute of Technology Thammasat University Next AI Solutions Department of Biomedical Engineering Faculty of Engineering Mahidol University Department of Computer Science University of Liverpool Department of Mechanical Engineering King Mongkut’s University of Technology North Bangkok Artificial Intelligence Entrepreneur Association of Thailand Department of Computer Engineering Faculty of Engineering Chulalongkorn University

ISBN: (数字)9798331509910

ISBN: (纸本)9798331509927

Large language models (LLMs) play an important role in modern NLP technology as they are versatile for a wide array of NLP tasks. However, constructing an LLM is challenging due to concealed construction pipelines, the lack of cleansed datasets, and hyperparameter settings, making it almost irreproducible. This paper presents an efficient pipeline for constructing an LLM tailored to a low-to-medium-sourced language with a high level of data contamination and tools to cleanse the dataset. Following our pipeline, we constructed OpenThaiGPT, an LLM for Thai, with only open-sourced datasets such as CC100, OSCAR, and mC4, and achieved the state-of-the-art accuracies on our downstream tasks. Here, we disclosed the data statistics and all hyperparameter settings for reproducibility.

关键词： Accuracy Large language models Decontamination Pipelines Data visualization Data models Natural language processing Reproducibility of results Arrays Contamination

Multi-Stage NMPC for a MAV based Collision Free Navigation under Varying Communication Delays

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Papadimitriou, Andreas Jafari, Hedyeh Mansouri, Sina Sharif Nikolakopoulos, George Department of Computer Electrical and Space Engineering Robotic & AI Team Luleå University of Technology SE-97187 Sweden Autonomous Driving Lab Scania Group SödertäljeSE-15139 Sweden

Time delays in communication networks are one of the main concerns in deploying robots with computation boards on the edge. This article proposes a multi-stage Nonlinear Model Predictive Control (NMPC) that is capable of handling varying network-induced time delays for establishing a control framework being able to guarantee collision-free Micro Aerial Vehicles (MAVs) navigation. This study introduces a novel approach that considers different sampling times by a tree of discretization scenarios contrary to the existing typical multi-stage NMPC where system uncertainties are modeled by a tree of scenarios. Additionally, the proposed method considers adaptive weights for the multi-stage NMPC scenarios based on the probability of time delays in the communication link. As a result of the multi-stage NMPC, the obtained optimal control action is valid for multiple sampling times. Finally, the overall effectiveness of the proposed novel control framework is demonstrated in various tests and different simulation environments. Copyright © 2022, The Authors. All rights reserved.

关键词： Time delay

Neuro-symbolic Explainable Artificial Intelligence Twin for Zero-touch IoE in Wireless Network

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Munir, Shirajum Kim, Ki Tae Adhikary, Apurba Saad, Walid Shetty, Sachin Park, Seong-Bae Hong, Choong Seon Virginia Modeling Analysis and Simulation Center Department of Computational Modeling and Simulation Engineering Old Dominion University SuffolkVA23435 United States Department of Computer Science and Engineering Kyung Hee University Yongin-si17104 Korea Republic of Department of Computer Science and Engineering School of Computing Kyung Hee University Kyung Hee University Yongin-si17104 Korea Republic of Wireless@VT Group Bradley Department of Electrical and Computer Engineering Virginia Tech ArlingtonVA22203 United States

Explainable artificial intelligence (Xai) twin systems will be a fundamental enabler of zero-touch network and service management (ZSM) for sixth-generation (6G) wireless networks. A reliable Xai twin system for ZSM requires two composites: an extreme analytical ability for discretizing the physical behavior of the Internet of Everything (IoE) and rigorous methods for characterizing the reasoning of such behavior. In this paper, a novel neuro-symbolic explainable artificial intelligence twin framework is proposed to enable trustworthy ZSM for a wireless IoE. The physical space of the Xai twin executes a neural-network driven multivariate regression to capture the time-dependent wireless IoE environment while determining unconscious decisions of IoE service aggregation. Subsequently, the virtual space of the Xai twin constructs a directed acyclic graph (DAG)-based Bayesian network that can infer a symbolic reasoning score over unconscious decisions through a first-order probabilistic language model. Furthermore, a Bayesian multi-arm bandits-based learning problem is proposed for reducing the gap between the expected explained score and current obtained score of the proposed neuro-symbolic Xai twin. To address the challenges of extensible, modular, and stateless management functions in ZSM, the proposed neuro-symbolic Xai twin framework consists of two learning systems: 1) implicit learner that acts as an unconscious learner in physical space, and 2) explicit leaner that can exploit symbolic reasoning based on implicit learner decisions and prior evidence. Experimental results show that the proposed neuro-symbolic Xai twin can achieve around 96.26% accuracy while guaranteeing from 18% to 44% more trust score in terms of reasoning and closed-loop automation. © 2022, CC BY-NC-ND.

关键词： Internet of Everything

AADNet: An End-to-End Deep Learning Model for Auditory Attention Decoding

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Nguyen, Nhan Duc Thanh Phan, Huy Geirnaert, Simon Mikkelsen, Kaare Kidmose, Preben Center for Ear-EEG Department of Electrical and Computer Engineering Aarhus University Aarhus N8200 Denmark Amazon CambridgeMA02142 United States Stadius Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven and Leuven.AI - KU Leuven institute for AI Kasteelpark Arenberg 10 LeuvenB-3001 Belgium The Department of Neurosciences Research Group ExpORL Herestraat 49 box 721 LeuvenB-3000 Belgium

Auditory attention decoding (AAD) is the process of identifying the attended speech in a multi-talker environment using brain signals, typically recorded through electroencephalography (EEG). Over the past decade, AAD has undergone continuous development, driven by its promising application in neuro-steered hearing devices. Most AAD algorithms are relying on the increase in neural entrainment to the envelope of attended speech, as compared to unattended speech, typically using a two-step approach. First, the algorithm predicts representations of the attended speech signal envelopes;second, it identifies the attended speech by finding the highest correlation between the predictions and the representations of the actual speech signals. In this study, we proposed a novel end-to-end neural network architecture, named AADNet, which combines these two stages into a direct approach to address the AAD problem. We compare the proposed network against the traditional approaches, including linear stimulus reconstruction, canonical correlation analysis, and an alternative non-linear stimulus reconstruction using two different datasets. AADNet shows a significant performance improvement for both subject-specific and subject-independent models. Notably, the average subject-independent classification accuracies from 56.1% to 82.7% with analysis window lengths ranging from 1 to 40 seconds, respectively, show a significantly improved ability to generalize to data from unseen subjects. These results highlight the potential of deep learning models for advancing AAD, with promising implications for future hearing aids, assistive devices, and clinical assessments. © 2024, CC BY-NC-SA.

关键词： Hearing aids

Two-dimensional Parameter Relationships for W UMa-type Systems Revisited

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Poro, Atila Paki, Ehsan Alizadehsabegh, ailar Khodadadilori, Mehdi Salehian, Selda Ranjbar Hedayatjoo, Mahya Hashemi, Fatemeh Dashti, Yasaman Mohammadizadeh, Fatemeh Astronomy Department The Raderon AI Lab BurnabyBC Canada Faculty of Electrical and Computer Engineering Department of Photonics University of Tabriz Tabriz51664 Iran Department of Electrical Engineering Amirkabir University of Technology Tehran Iran Astronomy Students’ Scientific Association University of Tabriz Tabriz51664 Iran Department of Physics Iran University of Science and Technology Tehran Iran Astronomy Group Bojnord Iran Department of Mechanical Engineering Amirkabir University of Technology Tehran Iran Aerospace Engineering Department Science and Research Branch Islamic Azad University Tehran Iran

Reviewing the empirical and theoretical parameter relationships between various parameters is a good way to understand more about contact binary systems. In this investigation, two-dimensional (2D) relationships for P −MV(system), P −L1,2, M1,2 −L1,2, and q−Lratio were revisited. The sample used is related to 118 contact binary systems with an orbital period shorter than 0.6 days whose absolute parameters were estimated based on the Gaia Data Release 3 (DR3) parallax. We reviewed previous studies on 2D relationships and updated six parameter relationships. Therefore, Markov chain Monte Carlo (MCMC) and Machine Learning (ML) methods were used, and the outcomes were compared. We selected 22 contact binary systems from eight previous studies for comparison, which had light curve solutions using spectroscopic data. The results show that the systems are in good agreement with the results of this study. © 2023, CC BY.

关键词： Stars

Next-Generation Sequencing Data Compression and Storage Solutions

学校读者我要写书评

暂无评论

Next-Generation Sequencing Data Compression and Storage Solu...

Communication, Computing and Signal Processing (IICCCS), IEEE International Conference on

作者： Sandeep Pandey Jejji Singh Arora Kassem AL-Attabi Ikramova Madina Sunnatilla Qizi G. Sathi Uk Urmila Department of Electrical & Electronics Engineering IES College of Technology Bhopal M.P. India Department of Computer Application Chandigarh Engineering College Chandigarh Group of Colleges Mohali Punjab India Department Of Computers Techniques Engineering College Of Technical Engineering The Islamic University Najaf Iraq Department Of Computers Techniques Engineering College Of Technical Engineering The Islamic University Of Al Diwaniyah Al Diwaniyah Iraq Tashkent Institute of Irrigation and Agricultural Mechanization Engineers" National Research University Tashkent Uzbekistan Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Department of AI & ML Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu India

ISBN: (数字)9798350390759

ISBN: (纸本)9798350390766

They produce huge amount of data which require efficient compression and management mechanisms hence the need to adopt Next-Generation Sequencing (NGS). In this paper, the performance of different compression algorithms and their implementation with local and cloud-based storage systems are assessed and compared using the lossless and lossy storage efficiency analysis. This study reveals that reference-based compression shows the highest compression ratio on the whole with lossy methods having shorter processing time ahead of other methods. A comparison of the costs shows the feasibility of local and cloud storage options to bear substantial costs. The study further supports that sophisticated algorithms as well as universally recognized formats are crucial for organizing NGS data Stream.

关键词： Cloud computing Sequential analysis Costs Signal processing algorithms Data compression Signal processing Telecommunication computing Reliability Next generation networking Compression algorithms

The Conditional Cauchy-Schwarz Divergence with Applications to Time-Series Data and Sequential Decision Making

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yu, Shujian Li, Hongming Løkse, Sigurd Jenssen, Robert Príncipe, José C. Machine Learning Group UiT - The Arctic University of Norway Tromsø Norway The Quantitative Data Analytics Group Vrije Universiteit Amsterdam Netherlands Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States Drones and Autonomous Systems group NORCE Norwegian Research Centre Tromsø Norway Pioneer AI Centre Copenhagen University Denmark The Norwegian Computing Center Oslo Norway

The Cauchy-Schwarz (CS) divergence was developed by Príncipe et al. in 2000. In this paper, we extend the classic CS divergence to quantify the closeness between two conditional distributions and show that the developed conditional CS divergence can be elegantly estimated by a kernel density estimator from given samples. We illustrate the advantages (e.g., rigorous faithfulness guarantee, lower computational complexity, higher statistical power, and much more flexibility in a wide range of applications) of our conditional CS divergence over previous proposals, such as the conditional KL divergence and the conditional maximum mean discrepancy. We also demonstrate the compelling performance of conditional CS divergence in two machine learning tasks related to time series data and sequential inference, namely time series clustering and uncertainty-guided exploration for sequential decision making. The code of conditional CS divergence is available at https://***/SJYuCNEL/conditional_CS_divergence. Copyright © 2023, The Authors. All rights reserved.

关键词： Time series

DPA-2:a large atomic model as a multitask learner

学校读者我要写书评

暂无评论

npj Computational Materials 2024年第1期10卷 185-199页

作者： Duo Zhang Xinzijian Liu Xiangyu Zhang Chengqian Zhang Chun Cai Hangrui Bi Yiming Du Xuejian Qin Anyang Peng Jiameng Huang Bowen Li Yifan Shan Jinzhe Zeng Yuzhi Zhang Siyuan Liu Yifan Li Junhan Chang Xinyan Wang Shuo Zhou Jianchuan Liu Xiaoshan Luo Zhenyu Wang Wanrun Jiang Jing Wu Yudi Yang Jiyuan Yang Manyi Yang Fu-Qiang Gong Linshuang Zhang Mengchao Shi Fu-Zhi Dai Darrin M.York Shi Liu Tong Zhu Zhicheng Zhong Jian Lv Jun Cheng Weile Jia Mohan Chen Guolin Ke Weinan E Linfeng Zhang Han Wang AI for Science Institute BeijingP.R.China DP Technology BeijingP.R.China Academy for Advanced Interdisciplinary Studies Peking UniversityBeijingP.R.China State Key Lab of Processors Institute of Computing TechnologyChinese Academy of SciencesBeijingP.R.China University of Chinese Academy of Sciences BeijingP.R.China HEDPS CAPTCollege of EngineeringPeking UniversityBeijingP.R.China Ningbo Institute of Materials Technology and Engineering Chinese Academy of SciencesNingboP.R.China CAS Key Laboratory of Magnetic Materials and Devices and Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Chinese Academy of SciencesNingboP.R.China School of Electronics Engineering and Computer Science Peking UniversityBeijingP.R.China Shanghai Engineering Research Center of Molecular Therapeutics&New Drug Development School of Chemistry and Molecular EngineeringEast China Normal UniversityShanghaiP.R.China Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine and Department of Chemistry and Chemical BiologyRutgers UniversityPiscatawayNJUSA Department of Chemistry Princeton UniversityPrincetonNJUSA College of Chemistry and Molecular Engineering Peking UniversityBeijingP.R.China Yuanpei College Peking UniversityBeijingP.R.China School of Electrical Engineering and Electronic Information Xihua UniversityChengduP.R.China State Key Laboratory of Superhard Materials College of PhysicsJilin UniversityChangchunP.R.China Key Laboratory of Material Simulation Methods&Software of Ministry of Education College of PhysicsJilin UniversityChangchunP.R.China International Center of Future Science Jilin UniversityChangchunP.R.China Key Laboratory for Quantum Materialsof Zhejiang Province Department of PhysicsSchool of ScienceWestlake UniversityHangzhouP.R.China Atomistic Simulations Italian Institute of TechnologyGenovaItaly State Key Laboratory of Physical Chemistry of Solid Surface iChEMCollege of Chemistry and Chemical EngineeringXiame

The rapid advancements in artificial intelligence(ai)are catalyzing transformative changes in atomic modeling,simulation,and ***-driven potential energy models havedemonstrated the capability to conduct large-scale,long-duration simulations with the accuracy of ab initio electronic structure ***,the model generation process remains a bottleneck for large-scale *** propose a shift towards a model-centric ecosystem,wherein a large atomic model(LAM),pretrained across multiple disciplines,can be efficiently fine-tuned and distilled for various downstream tasks,thereby establishing a new framework for molecular *** this study,we introduce the DPA-2 architecture as a prototype for ***-trained on a diverse array of chemical and materials systemsusing a multi-task approach,DPA-2demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning *** approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.

关键词： DPA establishing thereby

Spectroscopic Study, Hirshfeld Surface, DFT, In-Silico Molecular Docking and ADMET Studies of 2,6-Bis(4-Chlorophenyl)-3,3-Dimethylpiperidin-4-One (BCDP): a Potent Antiviral Agent

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Ramalingam, Arulraj Sambandam, Sivakumar Louis, Hitler Imojara, Anna Mathias, Gideon E. Department of Electrical and Computer Engineering National University of Singapore 117 583 Singapore Research and Development Centre Bharathiar University Tamil Nadu Coimbatore641 046 India BPJ College of Arts and Science Kozhai Srimushnam Tamil Nadu Cuddalore608703 India Computational and Bio-Simulation Research Group University of Calabar Calabar Nigeria

In this present study, the possibility of using 2,6-bis(4-chlorophenyl)-3,3-dimethylpiperidin-4-one (BCDP) as an antiviral agent against HIV was carefully evaluated. In order to achieve this, the compound BCDP was synthesized and characterized employing various spectroscopic methods including FT-IR, 13C-NMR and 1H- NMR. The theoretical calculations for the compound were carried out using the DFT using 6-311++(2d,2p) basic set and ωBD7XD functional. Both structural and electronic properties of the compound have also been studied. The frontier molecular orbital and the global reactivity descriptors were determined and the energy gap E obtained is 8.220 eV. The chemical hardness value for the BCDP obtained is 4.110 eV. In order to provide essential details concerning the non-covalent interaction of the molecules, the Hirshfeld analysis alongside finger plot has been carried out in this study. Furthermore, the NBO has been employed to provide more elucidation on charge transfer due to the inter and intramolecular interaction. Also, the antiviral potential of the BCDP compound against HIV was observed from the molecular docking studies. The docking result suggest that the drug has a good biological activity with values of -7.11, -5.9 and -7.8 kcal/mol for three different protein 5V4Y, 6IOC and 6OGP respectively. Furthermore, the SwissADME online tool was utilized to explore the pharmacokinetic and physicochemical features of the BCDP molecule. © 2023, The Authors. All rights reserved.

关键词： Molecules