检索结果-内蒙古大学图书馆

Label Structure Preserving Contrastive Embedding for Multi-Label learning with Missing Labels

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ma, Zhongchen Li, Lisha Mao, Qirong Chen, Songcan The School of Computer Science and Communications Engineering Jiangsu University Zhenjiang212013 China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China Nanjing211106 China

Contrastive learning (CL) has shown impressive advances in image representation learning in whichever supervised multi-class classification or unsupervised learning. However, these CL methods fail to be directly adapted to multi-label image classification due to the difficulty in defining the positive and negative instances to contrast a given anchor image in multi-label scenario, let the label missing one alone, implying that borrowing a commonly-used way from contrastive multi-class learning to define them will incur a lot of false negative instances unfavorable for learning. In this paper, with the introduction of a label correction mechanism to identify missing labels, we first elegantly generate positives and negatives for individual semantic labels of an anchor image, then define a unique contrastive loss for multilabel image classification with missing labels (CLML), the loss is able to accurately bring images close to their true positive images and false negative images, far away from their true negative images. Different from existing multi-label CL losses, CLML also preserves low-rank global and local label dependencies in the latent representation space where such dependencies have been shown to be helpful in dealing with missing labels. To the best of our knowledge, this is the first general multi-label CL loss in the missing-label scenario and thus can seamlessly be paired with those losses of any existing multi-label learning methods just via a single hyperparameter. The proposed strategy has been shown to improve the classification performance of the Resnet101 model by margins of 1.2%, 1.6%, and 1.3% respectively on three standard datasets, MSCOCO, VOC, and NUS-WIDE. Code is available at https://***/chuangua/ContrastiveLossMLML. Copyright © 2022, The Authors. All rights reserved.

关键词： learning systems

Children at risk: Effects of a four-year head start transition program on special education identification

学校读者我要写书评

暂无评论

Journal of Child and Family Studies 2001年第2期10.0卷 255-270页

作者： Redden, Sandra Cluett Forness, Steven R. Ramey, Sharon L. Ramey, Craig T. Brezausek, Carl M. Kavale, Kenneth A. Glenwood Children's Resource Center Center for Development and Learning University of North Carolina at Chapel Hill Chapel Hill NC United States Department of of Psychiatry and Biobehavioral Sciences Inpatient School Principal UCLA Neuropsychiatric Hospital Los Angeles CA United States Dept. of of Psychiat. Psychol. Pediat. Sociol. Nursing Matern. and Child Hlth. and Neurbio. Civitan International Research Center Birmingham AL United States Dept. of of Psychology Pediatrics Sociology Maternal and Child Health Nursing and Neurobiology Civitan International Research Center Birmingham AL United States Information Systems and Data Analysis Department Civitan International Research Center University of Alabama at Birmingham Birmingham AL United States Department of of Special Education University of Iowa Iowa City IA United States Birmingham AL 35209 1933 Richard Arrington Jr. Blvd. South United States

Children in Head Start are at risk for school learning or behavioral problems. While Head Start has decreased special education placement, there has been little systematic data until recently on identification of children in disability categories following preschool. In this study, two cohorts of 6,162 children across 30 sites were followed through third grade. Approximately half of these children were provided transition assistance from kindergarten through third grade. This included school transition and curricular modifications, parent involvement activities, health screening or referrals, and family social services, all similar to those received in Head Start. They were compared to a similar group of Head Start children who did not receive such services beyond the Head Start experience. Special education eligibility was determined from school records in the spring of third grade. Only 0.89% of children in the transition group were identified in the mental retardation category compared to 1.26% in the non-transition group. In the category of emotional disturbance, these same figures were 1.21% and 1.65% respectively. Both differences were statistically significant, but an opposite effect was found in the category of speech or language impairment. Findings are discussed in relation to differences in disability categories and implications for early identification. © 2001 Human Sciences Press, Inc.

关键词： Head start Identification Risk Special education Transition services

Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network research

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hille, Tobias Stubbemann, Maximilian Hanika, Tom Knowledge & Data Engineering Group University of Kassel Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Kassel Germany Information Systems and Machine Learning Lab University of Hildesheim Hildesheim Germany Institute of Computer Science University of Hildesheim Hildesheim Germany

Difficulties in replication and reproducibility of empirical evidences in machine learning research have become a prominent topic in recent years. Ensuring that machine learning research results are sound and reliable requires reproducibility, which verifies the reliability of research findings using the same code and data. This promotes open and accessible research, robust experimental workflows, and the rapid integration of new findings. Evaluating the degree to which research publications support these different aspects of reproducibility is one goal of the present work. For this we introduce an ontology of reproducibility in machine learning and apply it to methods for graph neural networks. Building on these efforts we turn towards another critical challenge in machine learning, namely the curse of dimensionality, which poses challenges in data collection, representation, and analysis, making it harder to find representative data and impeding the training and inference processes. Using the closely linked concept of geometric intrinsic dimension we investigate to which extend the used machine learning models are influenced by the intrinsic dimension of the data sets they are trained *** Codes 68T01 68T07 68T09 51F99 Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

Attention-Based Early Warning Framework for Abnormal Operating Conditions in Fluid Catalytic Cracking Units

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Chenwei, Tang Huang, Jialiang Xu, Mao Liu, Xu Yang, Fan Feng, Wentao He, Zhenan Lv, Jiancheng College of Computer Science Sichuan University Chengdu610065 China Engineering Research Center of Machine Learning and Industry Intelligence Ministry of Education Chengdu610065 China Algorithm and Bigdata Center Chengdu610041 China Data Intelligence Lab New Hope Liuhe Co.Ltd Chengdu610000 China

As a critical processing technology in the oil refining industry, Fluid Catalytic Cracking Unit (FCCU) plays a significant role in energy efficiency and environmental protection. However, FCCU often experiences various abnormal operating conditions, which can lead to safety hazards, downtime, and reduced production efficiency. Early warning of abnormal conditions in such complex industrial processes is essential yet challenging, especially when faced with high noise, strong hysteresis, and class imbalance problems. To address these challenges, we propose a universal attention-based early warning framework for abnormal operating conditions, called AEW-AOC, with applications in FCCU. Specifically, we propose a Self-Correlation Denoiser (SCD) module to reduce noise by utilizing spatiotemporal data correlation. Then, we employ a Convolutional Long Short-Term Memory (Conv-LSTM) module to solve the problem of strong hysteresis by extracting the temporal variation features of process parameters. Finally, based on the clustering results of historical abnormal instances, we propose an Anomaly Pattern Attention (APA) module to enhance the distinguishability of abnormal operating conditions. Extensive experiments demonstrate the effectiveness and superiority of our proposed AEW-AOC framework, especially in practical applications. The proposed universal early warning framework has the potential to enhance the safety, efficiency, and sustainability of industrial processes. © 2023, The Authors. All rights reserved.

关键词： Long short-term memory

Mining Negative Temporal Contexts For False Positive Suppression In Real-Time Ultrasound Lesion Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yu, Haojun Li, Youcheng Wu, QuanLin Zhao, Ziwei Chen, Dengbo Wang, Dong Wang, Liwei National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University Beijing China Center of Data Science Peking University Beijing China Center for Machine Learning Research Peking University Beijing China Yizhun Medical AI Co. Ltd Beijing China Guangdong China

During ultrasonic scanning processes, real-time lesion detection can assist radiologists in accurate cancer diagnosis. However, this essential task remains challenging and underexplored. General-purpose real-time object detection models can mistakenly report obvious false positives (FPs) when applied to ultrasound videos, potentially misleading junior radiologists. One key issue is their failure to utilize negative symptoms in previous frames, denoted as negative temporal contexts (NTC) [15]. To address this issue, we propose to extract contexts from previous frames, including NTC, with the guidance of inverse optical flow. By aggregating extracted contexts, we endow the model with the ability to suppress FPs by leveraging NTC. We call the resulting model UltraDet. The proposed UltraDet demonstrates significant improvement over previous state-of-the-arts and achieves real-time inference speed. We release the code, checkpoints, and high-quality labels of the CVA-BUS dataset [9] in https://***/HaojunYu1998/UltraDet. © 2023, CC BY-NC-ND.

关键词： Object detection

Bridging Traditional and machine learning-based Algorithms for Solving PDEs: The Random Feature Method

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Jingrun Chi, Xurong Weinan, E. Yang, Zhouwang School of Mathematical Sciences University of Science and Technology of China China Suzhou Institute for Advanced Research University of Science and Technology of China China AI for Science Institute Beijing and Center for Machine Learning Research School of Mathematical Sciences Peking University China School of Data Science University of Science and Technology of China China

One of the oldest and most studied subject in scientific computing is algorithms for solving partial differential equations (PDEs). A long list of numerical methods have been proposed and successfully used for various applications. In recent years, deep learning methods have shown their superiority for high-dimensional PDEs where traditional methods fail. However, for low dimensional problems, it remains unclear whether these methods have a real advantage over traditional algorithms as a direct solver. In this work, we propose the random feature method (RFM) for solving PDEs, a natural bridge between traditional and machine learning-based algorithms. RFM is based on a combination of well-known ideas: 1. representation of the approximate solution using random feature functions;2. collocation method to take care of the PDE;3. the penalty method to treat the boundary conditions, which allows us to treat the boundary condition and the PDE in the same footing. We find it crucial to add several additional components including multi-scale representation and rescaling the weights in the loss function. We demonstrate that the method exhibits spectral accuracy and can compete with traditional solvers in terms of both accuracy and efficiency. In addition, we find that RFM is particularly suited for complex problems with complex geometry, where both traditional and machine learning-based algorithms encounter difficulties. Copyright © 2022, The Authors. All rights reserved.

关键词： Partial differential equations

A Bidirectional LSTM Model for Classifying Chatbot Messages

学校读者我要写书评

暂无评论

A Bidirectional LSTM Model for Classifying Chatbot Messages

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

作者： Nunthawat Lhasiw Nuttapong Sanglerdsinlapachai Tanatorn Tanantong Faculty of Science and Technology Thammasat University Pathum Thani Thailand Strategic Analytics Networks With Machine Learning and AI Research Team National Electronics and Computer Technology Center Pathum Thani Thailand Thammasat Research Unit in Data Innovation and Artificial Intelligence Faculty of Science and Technology Thammasat University Pathum Thani Thailand

ISBN: (纸本)9781665409483

Online channels, e.g., Facebook Messenger and Line, are widely used especially in COVID-19 pandemic. To quickly respond to their customer, chatbot system are implemented in many companies or organizations, connected to those channels. The Office of Registrar, Thammasat University also implements a chatbot to answer questions from students. An important step in the chatbot system is to know an intention of a question message. A bidirectional LSTM model is employed to classify a question message from the chatbot system into five intention classes. The experimental results shows that the obtained model yields an accuracy of 0.80 on our validation dataset.

关键词： Training COVID-19 Social networking (online) Pandemics data integrity Memory management Companies

Excel in mathematics: Applications of calculus

学校读者我要写书评

暂无评论

Excel in mathematics: Applications of calculus

2010 ASEE Annual Conference and Exposition

作者： Young, Cynthia Georgiopoulos, Michael Crouse, Tace Geiger, Cherie Islas, Alvaro Hagen, Scott Dagley-Falls, Melissa Ramsey, Patricia Lancey, Patrice Department of Mathematics College of Sciences UCF United States School of Electrical Engineering and Computer Science UCF United States Machine Learning Laboratory UCF United States Faculty Center for Teaching and Learning University of Central Florida United States Department of Chemistry College of Sciences UCF United States Civil Environmental and Construction Department UCF United States Coastal Hydroscience Analysis Modeling and Predictive Simulations Laboratory UCF United States Academic Affairs College of Engineering and Computer Science UCF United States Institutional Research University of Central Florida United States Department of Operational Excellence and Assessment Support University of Central Florida United States

Nationally only 40% of the incoming freshmen STEM majors are successful in earning a STEM degree [1]. The University of Central Florida (UCF) EXCEL program is an NSF funded STEP (Science, Technology, Engineering and Mathematics Talent Expansion Program) whose goal is to increase the number of UCF STEM graduates. One of the activities that EXCEL has identified as essential in retaining students in science and engineering disciplines is the development and teaching of special courses at the freshman level, called Applications of Calculus I and Applications of Calculus II, or Apps I and Apps II, respectively. In Apps I and II, science and engineering professors are asked to lecture twice, as guest lectures, and to demonstrate to students where calculus topics appear in upper level science and engineering classes as well as where faculty use calculus in their research programs. This paper outlines the process used in producing the educational materials for Apps I and II courses (textbook, presentations slides, in-class homework assignments, demos) and it also discusses the assessment results pertaining to this specific EXCEL activity. © American Society for Engineering Education, 2010.

关键词： Calculations

Marine Predators Algorithm for Energy Scheduling Problem Using Renewable Energy

学校读者我要写书评

暂无评论

Marine Predators Algorithm for Energy Scheduling Problem Usi...

Cyber Resilience (ICCR), International Conference on

作者： Sharif Naser Makhadmeh Ammar Kamal Abasi Mohammed Azmi Al-Betar Department of Data Science and Artificial Intelligence University of Petra Amman Jordan Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi United Arab Emirates Artificial Intelligence Research Center (AIRC) Ajman University Ajman United Arab Emirates

ISBN: (数字)9798350394962

ISBN: (纸本)9798350394979

The Energy Scheduling Problem (ESP) involves scheduling smart home appliances based on electricity pricing schemes. This entails adjusting the timing of operations for these appliances across different periods. The primary aim of this scheduling approach is to reduce cost and the Peak-to-Average Ratio (PAR), while enhancing user comfort. This study employs the Marine Predators Algorithm (MPA) to address ESP and derive an optimal schedule for smart home appliances. Additionally, a renewable energy source (RES) on the basis of a PV system is introduced to further optimize appliance schedules by providing a smart home with energy, particularly during peak periods. The obtained outcomes demonstrate the effectiveness of the introduced RES in reducing costs of electricity and enhancing user satisfaction. Furthermore, the performance of MPA is compared with that of the wind-driven optimization algorithm, with MPA proving superior in achieving ESP objectives.

关键词： Home appliances Optimization Pricing Heuristic algorithms Optimal scheduling Electricity Dynamic scheduling