检索结果-内蒙古大学图书馆

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

BIM: Improving Graph Neural Networks with Balanced Influence Maximization

学校读者我要写书评

暂无评论

BIM: Improving Graph Neural Networks with Balanced Influence...

International Conference on data Engineering

作者： Wentao Zhang Xinyi Gao Ling Yang Meng Cao Ping Huang Jiulong Shan Hongzhi Yin Bin Cui Center for Machine Learning Research Peking University Institute of Advanced Algorithms Research Shanghai National Engineering Labratory for Big Data Analytics and Applications The University of Queensland Australia Key Lab of High Confidence Software Technologies Peking University Apple Inc. Institute of Computational Social Science Peking University Qingdao

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

The imbalanced data classification problem has aroused lots of concerns from both academia and industry since data imbalance is a widespread phenomenon in many real-world scenarios. Although this problem has been well researched from the view of imbalanced class samples, we further argue that graph neural networks (GNNs) expose a unique source of imbalance from the influenced nodes of different classes of labeled nodes, i.e., labeled nodes are imbalanced in terms of the number of nodes they influenced during the influence propagation in GNNs. To tackle this previously unexplored influence-imbalance issue, we connect social influence maximization with the imbalanced node classification problem and propose balanced influence maximization (BIM). Specifically, BIM greedily assigns the pseudo label to the node which can maximize the number of influenced nodes in GNN training while making the influence of each class more balance. Experimental results on five public datasets demonstrate the effectiveness of our method in relieving the influence-imbalance issue. For example, when training a GCN with an imbalance ratio of 0.1, BIM significantly outperforms the most competitive baseline by 0.6% -9.8% in five public datasets in terms of the F1 score.

关键词： Training Industries data engineering Graph neural networks

Self-supervised multimodal neuroimaging yields predictive representations for a spectrum of Alzheimer's phenotypes

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fedorov, Alex Geenjaar, Eloy Wu, Lei Sylvain, Tristan DeRamus, Thomas P. Luck, Margaux Misiura, Maria Hjelm, R. Devon Plis, Sergey M. Calhoun, Vince D. Tri-Institutional Center for Translational Research in Neuroimaging and Data Science Georgia State Georgia Tech Emory AtlantaGA United States Mila - Quebec AI Institute MontréalQC Canada Apple Machine Learning Research SeattleWA United States Borealis AI MontréalQC Canada

Recent neuroimaging studies that focus on predicting brain disorders via modern machine learning approaches commonly include a single modality and rely on supervised over-parameterized models. However, a single modality provides only a limited view of the highly complex brain. Critically, supervised models in clinical settings lack accurate diagnostic labels for training. Coarse labels do not capture the long-tailed spectrum of brain disorder phenotypes, which leads to a loss of generalizability of the model that makes them less useful in diagnostic settings. This work presents a novel multi-scale coordinated framework for learning multiple representations from multimodal neuroimaging data. We propose a general taxonomy of informative inductive biases to capture unique and joint information in multimodal self-supervised fusion. The taxonomy forms a family of decoder-free models with reduced computational complexity and a propensity to capture multi-scale relationships between local and global representations of the multimodal inputs. Furthermore, we provide a methodology for analyzing learned inductive biases in deep learning models via downstream classification tasks, representation alignment, and saliency measures. We conduct a comprehensive evaluation of the taxonomy using functional and structural magnetic resonance imaging (MRI) data across a spectrum of Alzheimer’s disease phenotypes and show that self-supervised models reveal disorder-relevant brain regions—including precuneus, hippocampus, and cingulate cortex—and multimodal links without access to the labels during pre-training. The proposed multimodal self-supervised learning yields representations with improved classification performance for both modalities. The representations also outperform unimodal supervised counterparts on fMRI data and advance the state-of-the-art in asymmetric coordinated fusion by exceeding the supervised model performance on one of the modalities. The concomitant rich and flexib

关键词： Taxonomies

Analyzing the Structure of Attention in a Transformer Language Model

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Vig, Jesse Belinkov, Yonatan Palo Alto Research Center Machine Learning and Data Science Group Interaction and Analytics Lab Palo AltoCA United States Harvard John A. Paulson School of Engineering and Applied Sciences MIT Computer Science and Artificial Intelligence Laboratory CambridgeMA United States

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the GPT-2 small pretrained model. We visualize attention for individual instances and analyze the interaction between attention and syntax over a large corpus. We find that attention targets different parts of speech at different layer depths within the model, and that attention aligns with dependency relations most strongly in the middle layers. We also find that the deepest layers of the model capture the most distant relationships. Finally, we extract exemplar sentences that reveal highly specific patterns targeted by particular attention heads. Copyright © 2019, The Authors. All rights reserved.

关键词： Recurrent neural networks

ADVISor: Automatic Visualization Answer for Natural-Language Question on Tabular data

学校读者我要写书评

暂无评论

ADVISor: Automatic Visualization Answer for Natural-Language...

Pacific (formerly Asia-Pacific APVIS) Visualization Symposium

作者： Can Liu Yun Han Ruike Jiang Xiaoru Yuan Key Laboratory of Machine Perception (Ministry of Education) and School of EECS Peking University Beijing China National Engineering Laboratory for Big Data Analysis and Application Peking University Beijing China Beijing Engineering Technology Research Center of Virtual Simulation and Visualization Peking University Beijing China

We propose an automatic pipeline to generate visualization with annotations to answer natural-language questions raised by the public on tabular data. With a pre-trained language representation model, the input natural language questions and table headers are first encoded into vectors. According to these vectors, a multi-task end-to-end deep neural network extracts related data areas and corresponding aggregation type. We present the result with carefully designed visualization and annotations for different attribute types and tasks. We conducted a comparison experiment with state-of-the-art works and the best commercial tools. The results show that our method outperforms those works with higher accuracy and more effective visualization.

关键词： Annotations Natural languages Pipelines Neural networks data visualization Tools data mining

Improving generative model-based unfolding with Schrödinger bridges

学校读者我要写书评

暂无评论

Physical Review D 2024年第7期109卷 076011-076011页

作者： Sascha Diefenbacher Guan-Horng Liu Vinicius Mikuni Benjamin Nachman Weili Nie Physics Division Lawrence Berkeley National Laboratory Berkeley California 94720 USA Autonomous Control and Decision Systems Laboratory Georgia Institute of Technology Atlanta Georgia 30332 USA National Energy Research Scientific Computing Center Berkeley Lab Berkeley California 94720 USA Berkeley Institute for Data Science University of California Berkeley California 94720 USA Machine Learning Research Group NVIDIA Research

machine learning-based unfolding has enabled unbinned and high-dimensional differential cross section measurements. Two main approaches have emerged in this research area; one based on discriminative models and one based on generative models. The main advantage of discriminative models is that they learn a small correction to a starting simulation while generative models scale better to regions of phase space with little data. We propose to use Schrödinger bridges and diffusion models to create sbunfold, an unfolding approach that combines the strengths of both discriminative and generative models. The key feature of sbunfold is that its generative model maps one set of events into another without having to go through a known probability density as is the case for normalizing flows and standard diffusion models. We show that sbunfold achieves excellent performance compared to state of the art methods on a synthetic Z+jets dataset.

关键词： machine learning Particle detectors Probability theory

Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference machines

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Adam, Alexandre Perreault-Levasseur, Laurence Hezaveh, Yashar Welling, Max Department of Physics Université de Montréal Montréal Canada Mila - Quebec Artificial Intelligence Institute Montréal Canada Ciela - Montreal Institute for Astrophysical Data Analysis and Machine Learning Montréal Canada Center for Computational Astrophysics Flatiron Institute 162 5th Avenue New YorkNY10010 United States Microsoft Research AI4Science

Modeling strong gravitational lenses in order to quantify the distortions in the images of background sources and to reconstruct the mass density in the foreground lenses has been a difficult computational challenge. As the quality of gravitational lens images increases, the task of fully exploiting the information they contain becomes computationally and algorithmically more difficult. In this work, we use a neural network based on the Recurrent Inference machine (RIM) to simultaneously reconstruct an undistorted image of the background source and the lens mass density distribution as pixelated maps. The method iteratively reconstructs the model parameters (the image of the source and a pixelated density map) by learning the process of optimizing the likelihood given the data using the physical model (a ray-tracing simulation), regularized by a prior implicitly learned by the neural network through its training data. When compared to more traditional parametric models, the proposed method is significantly more expressive and can reconstruct complex mass distributions, which we demonstrate by using realistic lensing galaxies taken from the IllustrisTNG cosmological hydrodynamic simulation. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroimaging

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hashemi, Ali Gao, Yijing Cai, Chang Ghosh, Sanjay Müller, Klaus-Robert Nagarajan, Srikantan S. Haufe, Stefan Uncertainty Inverse Modeling and Machine Learning Group Technische Universität Berlin Germany Machine Learning Group Technische Universität Berlin Germany Department of Radiology and Biomedical Imaging University of California San Francisco United States National Engineering Research Center for E-Learning Central China Normal University China BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin Germany Department of Artificial Intelligence Korea University Korea Republic of Max Planck Institute for Informatics Saarbrücken Germany Physikalisch-Technische Bundesanstalt Berlin Germany Charité – Universitätsmedizin Berlin Germany Bernstein Center for Computational Neuroscience Berlin Germany

Several problems in neuroimaging and beyond require inference on the parameters of multi-task sparse hierarchical regression models. Examples include M/EEG inverse problems, neural encoding models for task-based fMRI analyses, and temperature monitoring of climate or CPU and GPU. In these domains, both the model parameters to be inferred and the measurement noise may exhibit a complex spatio-temporal structure. Existing work either neglects the temporal structure or leads to computationally demanding inference schemes. Overcoming these limitations, we devise a novel flexible hierarchical Bayesian framework within which the spatio-temporal dynamics of model parameters and noise are modeled to have Kronecker product covariance structure. Inference in our framework is based on majorization-minimization optimization and has guaranteed convergence properties. Our highly efficient algorithms exploit the intrinsic Riemannian geometry of temporal autocovariance matrices. For stationary dynamics described by Toeplitz matrices, the theory of circulant embeddings is employed. We prove convex bounding properties and derive update rules of the resulting algorithms. On both synthetic and real neural data from M/EEG, we demonstrate that our methods lead to improved performance. © 2021, CC BY-NC-ND.

关键词： Inverse problems