检索结果-内蒙古大学图书馆

Med-IC: Fusing a Single Layer Involution with Convolutions for Enhanced Medical Image Classification and Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Islam, Md. Farhadul Zabeen, Sarah Manab, Meem Arafat Mahin, Mohammad Rakibul Hasan Mondal, Joyanta Jyoti Reza, Md. Tanzim Hasan, Md Zahidul Haque, Munima Sadeque, Farig Noor, Jannatun Research Group Department of Computer Science and Engineering School of Data and Sciences BRAC University Dhaka Bangladesh Department of Computer Science and Engineering School of Data and Sciences BRAC University Dhaka Bangladesh Biotechnology Program Department of Mathematics and Natural Sciences School of Data and Sciences BRAC University Dhaka Bangladesh Department of Computer and Information Sciences University of Delaware United States School of Law and Government Dublin City University Ireland Gina Cody School of Engineering and Computer Science Concordia University Canada

The majority of medical images, especially those that resemble cells, have similar characteristics. These images, which occur in a variety of shapes, often show abnormalities in the organ or cell region. The convolution operation possesses a restricted capability to extract visual patterns across several spatial regions of an image. The involution process, which is the inverse operation of convolution, complements this inherent lack of spatial information extraction present in convolutions. In this study, we investigate how applying a single layer of involution prior to a convolutional neural network (CNN) architecture can significantly improve classification and segmentation performance, with a comparatively negligible amount of weight parameters. The study additionally shows how excessive use of involution layers might result in inaccurate predictions in a particular type of medical image. According to our findings from experiments, the strategy of adding only a single involution layer before a CNN-based model outperforms most of the previous *** Codes 68T45 © 2024, CC BY-NC-SA.

关键词： Convolutional neural networks

Graphical dirichlet process for clustering non-exchangeable grouped data

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2024年第1期25卷 15795-15851页

作者： Arhit Chakrabarti Yang Ni Ellen Ruth A. Morris Michael L. Salinas Robert S. Chapkin Bani K. Mallick Department of Statistics Texas A&M University College Station TX Department of Statistics CPRIT Single Cell Data Science Core Texas A&M University College Station TX Department of Nutrition Program in Integrative Nutrition & Complex Diseases Texas A&M Veterinary Medical Diagnostic Laboratory Texas A&M University College Station TX Department of Nutrition Program in Integrative Nutrition & Complex Diseases CPRIT Single Cell Data Science Core Texas A&M University College Station TX

We consider the problem of clustering grouped data with possibly nonexchangeable groups whose dependencies can be characterized by a known directed acyclic graph. To allow the sharing of clusters among the non-exchangeable groups, we propose a Bayesian nonparametric approach, termed graphical Dirichlet process, that jointly models the dependent group-specific random measures by assuming each random measure to be distributed as a Dirichlet process whose concentration parameter and base probability measure depend on those of its parent groups. The resulting joint stochastic process respects the Markov property of the directed acyclic graph that links the groups. We characterize the graphical Dirichlet process using a novel hypergraph representation as well as the stick-breaking representation, the restaurant-type representation, and the representation as a limit of a finite mixture model. We develop an efficient posterior inference algorithm and illustrate our model with simulations and a real grouped single-cell data set.

关键词： Bayesian nonparametrics clustering directed acyclic graph family-owned restaurant process non-exchangeable groups

Parameter Estimation for Partially Observed McKean-Vlasov Diffusions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jasra, Ajay Maama, Mohamed Tempone, Raul School of Data Science The Chinese University of Hong Kong CN 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 Chair of Mathematics for Uncertainty Quantification RWTH Aachen University Aachen52062 Germany

In this article we consider likelihood-based estimation of static parameters for a class of partially observed McKean-Vlasov (POMV) diffusion process with discrete-time observations over a fixed time interval. In particular, using the framework of [5] we develop a new randomized multilevel Monte Carlo method for estimating the parameters, based upon Markovian stochastic approximation methodology. New Markov chain Monte Carlo algorithms for the POMV model are introduced facilitating the application of [5]. We prove, under assumptions, that the expectation of our estimator is biased, but with expected small and controllable bias. Our approach is implemented on several examples. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

Large Area Mapping of Urban Deprivation from Sentinel-2 and Google Open Buildings using Deep Learning

学校读者我要写书评

暂无评论

Large Area Mapping of Urban Deprivation from Sentinel-2 and ...

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Ryan Engstrom Maxwell Owusu Mina Hanna Amir Jafari Dana R. Thomson Monika Kuffer Department of Geography George Washington University Washington DC USA Data Science Program George Washington University Washington DC USA Faculty of Geo-Information Science and Earth Observation University of Twente ITC Enschede Netherlands Center for International Earth Science Information Network (CIESIN) Columbia University New York USA

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

This study explores the potential of a synergistic approach combining Sentinel-2 data and Google Open Buildings (GOB) for mapping urban deprivation over large areas at a 100m spatial resolution. Urban deprivation, including slums, is a crucial aspect of Sustainable Development Goal 11 (SDG): Make cities and human settlements inclusive, safe, resilient and sustainable. Using a Convolutional Neural Network (CNN) and a VGG19 architecture, we experimented with pre-training, self-training, and post-processing using OpenStreetMap to improve classification accuracy. Our results show that combining outputs from both Sentinel-2 and GOB models improves the overall model performance with an F1 score of 81%. The incorporation of post-processing is useful for the final map creation, particularly in correcting for mis-classifications in areas with obvious morphological similarities to deprived areas, such as markets. This approach, which reduces known errors in the model, holds promise for advancing the precision and reliability of urban deprivation mapping over extensive geographical areas.

关键词： Deep learning Architecture Buildings Urban areas Geoscience and remote sensing Internet Convolutional neural networks

Graph Coordinates and Conventional Neural Networks - An Alternative for Graph Neural Networks

学校读者我要写书评

暂无评论

Graph Coordinates and Conventional Neural Networks - An Alte...

IEEE International Conference on Big data

作者： Zheyi Qin Randy Paffenroth Anura P. Jayasumana Electrical and Computer Engineering Colorado State University Fort Collins USA Department of Data Science Program Worcester Polytechnic Institute Worcester MA USA

Graph-based data present unique challenges and opportunities for machine learning. Graph Neural Networks (GNNs), and especially those algorithms that capture graph topology through message passing for neighborhood aggregation, have been a leading solution. However, these networks often require substantial computational resources and may not optimally leverage the information contained in the graph’s topology, particularly for large-scale or complex *** propose Topology Coordinate Neural Network (TCNN) and Directional Virtual Coordinate Neural Network (DVCNN) as novel and efficient alternatives to message passing GNNs, that directly leverage the graph’s topology, sidestepping the computational challenges presented by competing algorithms. Our proposed methods can be viewed as a reprise of classic techniques for graph embedding for neural network feature engineering, but they are novel in that our embedding techniques leverage ideas in Graph Coordinates (GC) that are lacking in current *** results, benchmarked against the Open Graph Benchmark Leaderboard, demonstrate that TCNN and DVCNN achieve competitive or superior performance to message passing GNNs. For similar levels of accuracy and ROC-AUC, TCNN and DVCNN need far fewer trainable parameters than contenders of the OGBN Leaderboard. The proposed TCNN architecture requires fewer parameters than any neural network method currently listed in the OGBN Leaderboard for both OGBN-Proteins and OGBN-Products datasets. Conversely, our methods achieve higher performance for a similar number of trainable parameters. These results hold across diverse datasets and edge features, underscoring the robustness and generalizability of our methods. By providing an efficient and effective alternative to message passing GNNs, our work expands the toolbox of techniques for graph-based machine learning. A significantly lower number of tunable parameters for a given evaluation metric makes TCNN and DVCNN especiall

关键词：

Sampling-Based Estimates of the Weight Enumerators of Reed-Muller Codes

学校读者我要写书评

暂无评论

IEEE Transactions on Communications 2025年

作者： Arvind Rameshwar, V. Jain, Shreyas Kashyap, Navin Indian Institute of Science India Urban Data Exchange Program Unit Bengaluru560012 India IISER Department of Mathematical Sciences Mohali140306 India Indian Institute of Science Department of Electrical Communication Engineering Bengaluru560012 India

This paper develops an algorithmic approach for obtaining estimates of the weight enumerators of Reed-Muller (RM) codes. Our algorithm is based on a technique for estimating the partition functions of spin systems, which in turn employs a sampler that produces codewords according to a suitably defined Gibbs distribution. We apply our method to moderate-blocklength RM RM) codes. Our algorithm is based on a technique for estimating the partition functions of spin systems, which in turn employs a sampler that produces codewords according to a suitably defined Gibbs distribution. We apply our method to moderate-blocklength RM codes and derive approximate values of their weight enumerators. We observe that the rates of the weight enumerator estimates returned by our method are close to the true rates when these rates are either known or computable by brute-force search;in other cases, our computations provide provably robust estimates. As a by-product, our sampling algorithm also allows us to put together the weight spectrum, i.e., the weights at which the enumerators are non-zero, of an RM code, by providing witnesses in the form of codewords at each weight in the spectrum. We illustrate our method by providing estimates of the hitherto unknown weight enumerators of the RM(11, 5) code for weights that are multiples of 4 between 512 and 1024. We also obtain the exact weight spectrum of the RM(10, 4) code. © 1972-2012 IEEE.

关键词： Weighing

Finite-time analysis of globally nonstationary multi-armed bandits

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2024年第1期25卷 5481-5536页

作者： Junpei Komiyama Edouard Fouché Junya Honda Stern School of Business New York University Institute for Program Structures and Data Organization Karlsruhe Institute of Technology Germany Department of Systems Science Graduate School of Informatics Kyoto University Japan Center for Advanced Intelligence Project RIKEN Japan

We consider nonstationary multi-armed bandit problems where the model parameters of the arms change over time. We introduce the adaptive resetting bandit (ADR-bandit), a bandit algorithm class that leverages adaptive windowing techniques from literature on data streams. We first provide new guarantees on the quality of estimators resulting from adaptive windowing techniques, which are of independent interest. Furthermore, we conduct a finite-time analysis of ADR-bandit in two typical environments: an abrupt environment where changes occur instantaneously and a gradual environment where changes occur progressively. We demonstrate that ADR-bandit has nearly optimal performance when abrupt or gradual changes occur in a coordinated manner that we call global changes. We demonstrate that forced exploration is unnecessary when we assume such global changes. Unlike the existing nonstationary bandit algorithms, ADR-bandit has optimal performance in stationary environments as well as nonstationary environments with global changes. Our experiments show that the proposed algorithms outperform the existing approaches in synthetic and real-world environments.

关键词： multi-armed bandits adaptive windows nonstationary bandits changepoint detection sequential learning

Bayesian Inference for Non-Synchronously Observed Diffusions

学校读者我要写书评

暂无评论

arXiv 2025年

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

We consider the problem of Bayesian inference for bi-variate data observed in time but with observation times which occur non-synchronously. In particular, this occurs in a wide variety of applications in finance, such as high-frequency trading or crude oil futures trading. We adopt a diffusion model for the data and formulate a Bayesian model with priors on unknown parameters along with a latent representation for the the so-called missing data. We then consider computational methodology to fit the model using Markov chain Monte Carlo (MCMC). We have to resort to time-discretization methods as the complete data likelihood is intractable and this can cause considerable issues for MCMC when the data are observed in low frequencies. In a high frequency observation frequencies we present a simple particle MCMC method based on an Euler–Maruyama time discretization, which can be enhanced using multilevel Monte Carlo (MLMC). In the low frequency observation regime we introduce a novel bridging representation of the posterior in continuous time to deal with the issues of MCMC in this case. This representation is discretized and fitted using MCMC and MLMC. We apply our methodology to real and simulated data to establish the efficacy of our methodology. © 2025, CC BY.

关键词： Crude oil

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Xianlong Gao, Yijing Liu, Ang Song, Fanghao Electrical Engineering and Computer Science Ohio University AthensOH45701 United States Data Science Institute Brown University ProvidenceRI02912 United States Global Urban Studies Program Rutgers University New BrunswickNJ08901 United States

This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs). Our two-step approach involves data point summarization and hidden state extraction. Initially, data is condensed via summarization using an LLM, reducing complexity and highlighting essential information in sentences. Subsequently, the summarization sentences are fed through another LLM to extract hidden states, serving as compact, feature-rich representations. This approach leverages the advanced comprehension and generative capabilities of LLMs, offering a scalable and efficient strategy for similarity identification across diverse datasets. We demonstrate the effectiveness of our method in identifying similar data points on multiple datasets. Additionally, our approach enables non-technical domain experts, such as fraud investigators or marketing operators, to quickly identify similar data points tailored to specific scenarios, demonstrating its utility in practical applications. In general, our results open new avenues for leveraging LLMs in data analysis across various domains. © 2024, CC BY.

关键词： Adversarial machine learning