检索结果-内蒙古大学图书馆

Towards artificial general intelligence via a multimodal foundation model

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fei, Nanyi Lu, Zhiwu Gao, Yizhao Yang, Guoxing Huo, Yuqi Wen, Jingyuan Lu, Haoyu Song, Ruihua Gao, Xin Xiang, Tao Sun, Hao Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China School of Information Renmin University of China Beijing China Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Department of Electrical and Electronic Engineering University of Surrey Guildford United Kingdom

The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of human. Despite tremendous success in the AI research, most of existing methods have only single-cognitive ability. To overcome this limitation and take a solid step towards artificial general intelligence (AGI), we develop a foundation model pre-trained with huge multimodal data, which can be quickly adapted for various downstream cognitive tasks. To achieve this goal, we propose to pre-train our foundation model by self-supervised learning with weak semantic correlation data crawled from the Internet and show that promising results can be obtained on a wide range of downstream tasks. Particularly, with the developed model-interpretability tools, we demonstrate that strong imagination ability is now possessed by our foundation model. We believe that our work makes a transformative stride towards AGI, from our common practice of "weak or narrow AI" to that of "strong or generalized AI". © 2021, CC BY.

关键词： Semantics

Correction to: Duplex Detection of Antibiotics in Milk Powder Using Lateral-Flow Assay Based on Surface-Enhanced Raman Spectroscopy

学校读者我要写书评

暂无评论

Food Analytical methods 2022年第3期15卷 845-845页

作者： Li, Xiaozhou Wang, Xinruo Wang, Lianyan Yang, Tianyue Wang, Deli School of Science Shenyang Ligong University Shenyang China School of Environment Liaoning University Shenyang China Department of Ecology and Environment of Liaoning Province Liaoning Science and Technology Center for Ecological and Environmental Protection Shenyang China Department of Computer and Mathematics Teaching Shenyang Normal University Shenyang China

Artificial intelligence in multimodal learning analytics: A systematic literature review

学校读者我要写书评

暂无评论

computers and Education: Artificial Intelligence 2025年 8卷

作者： Mohammadi, Mehrnoush Tajik, Elham Martinez-Maldonado, Roberto Sadiq, Shazia Tomaszewski, Wojtek Khosravi, Hassan School of Electrical Engineering and Computer Science The University of Queensland Brisbane Australia Department of Educational Psychology and Learning Systems Florida State University Tallahassee United States Centre for Learning Analytics at Monash Faculty of Information Technology Monash University Melbourne Australia Australian Research Council Centre of Excellence for Children and Families Over the Life Course The University of Queensland Brisbane Australia Institute for Social Science Research The University of Queensland Brisbane Australia Institute for Teaching and Learning Innovation The University of Queensland Brisbane Australia

The proliferation of educational technologies has generated unprecedented volumes of diverse, multimodal learner data, offering rich insights into learning processes and outcomes. However, leveraging this complex, multimodal data requires advanced analytical methods. While Multimodal Learning Analytics (MMLA) offers promise for exploring this data, the potential of Artificial Intelligence (AI) to enhance MMLA remains largely unexplored. This paper bridges these two evolving domains by conducting the first systematic literature review at the intersection of AI and MMLA, analyzing 43 peer-reviewed papers from 11 reputable databases published between 2019 and 2024. The findings indicate a growing trend in AI-enhanced MMLA studies published predominantly in high-quality venues, led by education researchers with a predominant focus on tertiary education targeting diverse stakeholders. Guided by a novel conceptual framework, our analysis highlights the transformative role of AI across the MMLA process, particularly in model learning and feature engineering. However, it also uncovers significant gaps, including limited AI implementation in components requiring deep integration with learning theories, insufficient application of advanced AI techniques, and lack of large-scale studies in authentic learning environments. The review identifies key benefits, such as enhanced personalization and real-time feedback, while also addressing challenges related to ethical considerations, data integration, and scalability. Our study contributes by offering comprehensive recommendations for future research, emphasizing international collaboration, multi-level studies, and ethical AI implementation. These findings advance the theoretical understanding of AI's role in education, providing a foundation for developing sophisticated, interpretable, and scalable AI-enhanced MMLA approaches, potentially revolutionizing personalized learning across diverse educational settings. © 2025

关键词： Educational robots

Opinion mining in e-commerce: Evaluating machine learning approaches for sentiment analysis

学校读者我要写书评

暂无评论

Results in Control and Optimization 2025年 19卷

作者： Lakshmi, L. Ali, Ali B.M. Devi, K Dhana Sree Rafiq, Muhammad Shernazarov, Iskandar Othman, Nashwan Adnan Khan, M. Ijaz Department of DS & AI Faculty of Science and Technology ICFAI Foundation for Higher Education (IFHE) Hyderabad -501203 India Air Conditioning Engineering Department College of Engineering University of Warith Al-Anbiyaa Karbala Iraq Department of CSE GSOT GITAM University Hyderabad India College of Business Administration Prince Mohammad Bin Fahd University Saudi Arabia Department of Chemistry and Its Teaching Methods Tashkent State Pedagogical University Tashkent Uzbekistan Department of Computer Engineering College of Engineering Knowledge University Erbil 44001 Iraq Department of Computer Engineering Al-Kitab University Altun Kupri Iraq Department of Mechanical Engineering College of Engineering Prince Mohammad Bin Fahd University Al-Khobar Saudi Arabia Department of Mechanical Engineering Lebanese American University Beirut Lebanon

In recent years, opinion mining has played a major role in analyzing text data from various sources such as Amazon, Capterra, Facebook, Google, GetApp, and Twitter. It enables companies to actively refine their business strategies. Sentiment analysis involves interpreting and classifying customer emotions (positive, neutral, and negative) expressed in reviews using sentiment analysis techniques such as BING and AFINN. This paper presents four approaches for customer review analysis and classification: the grade-based approach, content-based approach, content-based NRC-Emotion Lexicon approach, and collaborative approach. We employ three machine learning algorithms—stacking, random forest, and LogitBoost—to evaluate the performance of these approaches. A real-time dataset from Amazon product reviews is used for training and testing the model. Empirical results reveal that the collaborative approach outperforms the grade-based, content-based, and content-based NRC-Emotion Lexicon approaches across all three machine learning algorithms. Additionally, all approaches demonstrate outstanding performance when using the boosting algorithm for customer review classification. © 2025 The Author(s)

关键词： Machine learning NRC-lexicon Product reviews Sentiment analysis Text classification

Enhancing image quality in fast neutron-based range verification of proton therapy using a deep learning-based prior in LM-MAP-EM reconstruction

学校读者我要写书评

暂无评论

Physics in medicine and biology 2025年第12期70卷 2025 Jun 5页

作者： Lena Marie Setterdahl Kyrre Skjerdal Hunter Nathaniel Ratliff Kristian Smeland Ytre-Hauge William R B Lionheart Sean Holman Helge Egil Seime Pettersen Francesco Blangiardi Danny Lathouwers Ilker Meric Department of Computer science Electrical engineering and Mathematical sciences Western Norway University of Applied Sciences Inndalsveien 28 Bergen Hordaland 5063 NORWAY. Department of Physics and Technology University of Bergen Allégaten 55 Bergen Hordaland 5007 NORWAY. Department of Mathematics The University of Manchester Alan Turing Building Upper Brook St Manchester England M13 9SR UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND. Department of Oncology and Medical Physics Haukeland Universitetssjukehus Jonas Lies veg 65 Postboks 1400 Bergen Hordaland 5021 NORWAY. Technology Methods and Systems Data Based Methods Fraunhofer Institute for Electronic Nano Systems ENAS Technologie-Campus 3 Chemnitz SN 09126 GERMANY. Department of Radiation Science and Technology Delft University of Technology Mekelweg 15 Delft 2629 JD NETHERLANDS. Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Inndalsveien 28 Bergen Hordaland 5063 NORWAY.

This study investigates the use of list-mode (LM) maximum a posteriori (MAP) expectation maximization (EM) incorporating prior information predicted by a convolutional neural network for image reconstruction in fast neutron (FN)-based proton therapy range verification. Approach. A conditional generative adversarial network (pix2pix) was trained on progressively noisier data, where detector resolution effects were introduced gradually to simulate realistic conditions. FN data were generated using Monte Carlo simulations of an 85 MeV proton pencil beam in a computed tomography (CT)-based lung cancer patient model, with range shifts emulating weight gain and loss. The network was trained to estimate the expected two-dimensional (2D) ground truth FN production distribution from simple back-projection images. Performance was evaluated using mean squared error (MSE), structural similarity index (SSIM), and the correlation between shifts in predicted distributions and true range shifts. Main results. Our results show that pix2pix performs well on noise-free data but suffers from significant degradation when detector resolution effects are introduced. Among the LM-MAP-EM approaches tested, incorporating a mean prior estimate into the reconstruction process improved performance, with LM-MAP-EM using a mean prior estimate outperforming naïve LM maximum likelihood EM (LM-MLEM) and conventional LM-MAP-EM with a smoothing quadratic energy function in terms of SSIM. Significance. Findings suggest that deep learning techniques can enhance iterative reconstruction for range verification in proton therapy. However, the effectiveness of the model is highly dependent on data quality, limiting its robustness in high-noise scenarios. .

关键词： LM-MAP-EM Monte Carlo simulation fast neutron imaging generative adversarial network organic scintillators proton therapy range verification

Nonlinear dynamics of quadratic gravity in spherical symmetry

学校读者我要写书评

暂无评论

Physical Review D 2021年第8期104卷 084075-084075页

作者： Aaron Held Hyun Lim Blackett Laboratory Imperial College London London SW7 2AZ United Kingdom Computational Physics and Methods (CCS-2) Los Alamos National Laboratory Los Alamos 87545 NM United States Center for Theoretical Astrophysics Los Alamos National Laboratory Los Alamos 87545 NM United States Applied Computer Science (CCS-7) Los Alamos National Laboratory Los Alamos 87545 NM United States

We present the first numerically stable nonlinear evolution for the leading-order gravitational effective field theory (quadratic gravity) in the spherically-symmetric sector. The formulation relies on (i) the harmonic gauge to cast the evolution system into quasilinear form (ii) the Cartoon method to reduce to spherical symīmetry in keeping with the harmonic gauge, and (iii) order reduction to first order (in time) by means of introducing auxiliary variables. The well posedness of the respective initial-value problem is numerically confirmed by evolving randomly perturbed flat-space and black-hole initial data. Our study serves as a proof-of-principle for the possibility of stable numerical evolution in the presence of higher derivatives.

关键词： Classical black holes General relativity equations & solutions Quantum gravity Numerical relativity

DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zeng, Jinzhe Zhang, Duo Peng, Anyang Zhang, Xiangyu He, Sensen Wang, Yan Liu, Xinzijian Bi, Hangrui Li, Yifan Cai, Chun Zhang, Chengqian Du, Yiming Zhu, Jia-Xin Mo, Pinghui Huang, Zhengtao Zeng, Qiyu Shi, Shaochen Qin, Xuejian Yu, Zhaoxi Luo, Chenxing Ding, Ye Liu, Yun-Pei Shi, Ruosong Wang, Zhenyu Bore, Sigbjørn Løland Chang, Junhan Deng, Zhe Ding, Zhaohan Han, Siyuan Jiang, Wanrun Ke, Guolin Liu, Zhaoqing Lu, Denghui Muraoka, Koki Oliaei, Hananeh Singh, Anurag Kumar Que, Haohui Xu, Weihong Xu, Zhangmancang Zhuang, Yong-Bin Dai, Jiayu Giese, Timothy J. Jia, Weile Xu, Ben York, Darrin M. Zhang, Linfeng Wang, Han School of Artificial Intelligence and Data Science Unversity of Science and Technology of China Hefei China AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100871 China University of Chinese Academy of Sciences Beijing China Baidu Inc. Beijing China Department of Computer Science University of Toronto TorontoON Canada Department of Chemistry Princeton University PrincetonNJ08540 United States University of Chinese Academy of Sciences Beijing100871 China State Key Laboratory of Physical Chemistry of Solid Surfaces iChEM College of Chemistry and Chemical Engineering Xiamen University Xiamen361005 China College of Integrated Circuits Hunan University Changsha410082 China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Center for Smart Materials and Device Integration School of Material Science and Engineering Wuhan University of Technology Wuhan430070 China College of Science National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Extreme Matter and Applications National University of Defense Technology Changsha410073 China ByteDance Research Beijing100098 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Theoretical and Computational Photochemistry of Ministry of Education College of Chemistry Beijing Normal University Beijing100875 China Department of Geosciences Princeton University PrincetonNJ08544 United States Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States IKKEM Fujian Xiamen361005 China Graduate

In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications. These packages, typically built on specific machine learning frameworks such as TensorFlow, PyTorch, or JAX, face integration challenges when advanced applications demand communication across different frameworks. The previous TensorFlow-based implementation of DeePMD-kit exemplified these limitations. In this work, we introduce DeePMD-kit version 3, a significant update featuring a multi-backend framework that supports TensorFlow, PyTorch, JAX, and PaddlePaddle backends, and demonstrate the versatility of this architecture through the integration of other MLPs packages and of Differentiable Molecular Force Field. This architecture allows seamless backend switching with minimal modifications, enabling users and developers to integrate DeePMD-kit with other packages using different machine learning frameworks. This innovation facilitates the development of more complex and interoperable workflows, paving the way for broader applications of MLPs in scientific research. Copyright © 2025, The Authors. All rights reserved.

关键词： Molecular dynamics

Particle In Cell Simulations of Mildly Relativistic Outflows in Kilonova Emissions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Rassel, Mohira Kilian, Patrick Aberham, Vito Spanier, Felix Lloyd-Ronning, Nicole Fryer, Chris L. Center for Theoretical Astrophysics Los Alamos National Laboratory Los AlamosNM87545 United States Center for Non Linear Studies Los Alamos National Laboratory Los AlamosNM87545 United States Space Science Institute 4765 Walnut St Suite B BoulderCO80301 United States Institut für Theoretische Astrophysik Universität Heidelberg Heidelberg69120 Germany Computational Physics and Methods Group Los Alamos National Laboratory Los AlamosNM87545 United States Department of Math Engineering & Science University of New Mexico Los AlamosNM87545 United States Computer Computational and Statistical Sciences Division Los Alamos National Laboratory Los AlamosNM87545 United States The University of Arizona TucsonAZ85721 United States Department of Physics and Astronomy The University of New Mexico AlbuquerqueNM87131 United States The George Washington University WashingtonDC20052 United States

The electromagnetic emission from neutron star mergers is comprised of multiple components. Synchrotron emission from the disk-powered jet as well as thermal emission from the merger ejecta (powered by a variety of sources) are among the most studied sources. The low masses and high velocities of the merger ejecta quickly develop conditions where emission from collisionless shocks becomes critical and synchrotron emission from the merger ejecta constitutes a third component to the observed signal. The aim of this project is to examine shock development, magnetic field generation and particle acceleration in the case of mildly relativistic shocks, which are expected when the tidal ejecta of neutron star mergers drive a shock into the external medium. Using LANL’s VPIC (vector particle-in-cell) code, we have run simulations of such mildly-relativistic, collisionless, weakly-magnetized plasmas and compute the resultant magnetic fields and particle energy spectra. We show the effects of varying plasma conditions, as well as explore the validity of using different proton to electron mass ratios in VPIC. Our results have implications for observing late-time electromagnetic counterparts to gravitational wave detections of neutron star mergers. Copyright © 2023, The Authors. All rights reserved.

关键词： Merging

Mining implicit entity preference from user-item interaction data for Knowledge Graph Completion via adversarial learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： He, Gaole Li, Junyi Zhao, Wayne Xin Liu, Peiju Wen, Ji-Rong School of Information Renmin University of China China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods School of Electronics Engineering and Computer Science Peking University China

The task of Knowledge Graph Completion (KGC) aims to automatically infer the missing fact information in Knowledge Graph (KG). In this paper, we take a new perspective that aims to leverage rich user-item interaction data (user interaction data for short) for improving the KGC task. Our work is inspired by the observation that many KG entities correspond to online items in application systems. However, the two kinds of data sources have very different intrinsic characteristics, and it is likely to hurt the original performance using simple fusion strategy. To address this challenge, we propose a novel adversarial learning approach by leveraging user interaction data for the KGC task. Our generator is isolated from user interaction data, and serves to improve the performance of the discriminator. The discriminator takes the learned useful information from user interaction data as input, and gradually enhances the evaluation capacity in order to identify the fake samples generated by the generator. To discover implicit entity preference of users, we design an elaborate collaborative learning algorithms based on graph neural networks, which will be jointly optimized with the discriminator. Such an approach is effective to alleviate the issues about data heterogeneity and semantic complexity for the KGC task. Extensive experiments on three real-world datasets have demonstrated the effectiveness of our approach on the KGC task. The source code is publicly available at https://***/RUCAIBox/UPGAN. Copyright © 2020, The Authors. All rights reserved.

关键词： Knowledge graph