检索结果-内蒙古大学图书馆

Asymptotic and compound e-values: multiple testing and empirical Bayes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ignatiadis, Nikolaos Wang, Ruodu Ramdas, Aaditya Department of Statistics and Data Science Institute University of Chicago United States Department of Statistics and Actuarial Science University of Waterloo Canada Departments of Statistics & Machine Learning Carnegie Mellon University United States

We explicitly define the notions of (exact, approximate or asymptotic) compound p-values and e-values, which have been implicitly presented and extensively used in the recent multiple testing literature. While it is known that the e-BH procedure with compound e-values controls the FDR, we show the converse: every FDR controlling procedure can be recovered by instantiating the e-BH procedure with certain compound e-values. Since compound e-values are closed under averaging, this allows for combination and derandomization of FDR procedures. We then connect compound e-values to empirical Bayes. In particular, we use the fundamental theorem of compound decision theory to derive the log-optimal simple separable compound e-value for testing a set of point nulls against point alternatives: it is a ratio of mixture likelihoods. We extend universal inference to the compound setting. As one example, we construct approximate compound e-values for multiple t-tests, where the (nuisance) variances may be different across hypotheses. Finally, we provide connections to related notions in the literature stated in terms of p-values. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision theory

Assessing Robustness via Score-Based Adversarial Image Generation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kollovieh, Marcel Gosch, Lukas Lienen, Marten Scholten, Yan Schwinn, Leo Günnemann, Stephan School of Computation Information and Technology Technical University of Munich Germany Munich Data Science Institute Germany Munich Center for Machine Learning Germany

Most adversarial attacks and defenses focus on perturbations within small p-norm constraints. However, p threat models cannot capture all relevant semantics-preserving perturbations, and hence, the scope of robustness evaluations is limited. In this work, we introduce Score-Based Adversarial Generation (ScoreAG), a novel framework that leverages the advancements in score-based generative models to generate unrestricted adversarial examples that overcome the limitations of p-norm constraints. Unlike traditional methods, ScoreAG maintains the core semantics of images while generating adversarial examples, either by transforming existing images or synthesizing new ones entirely from scratch. We further exploit the generative capability of ScoreAG to purify images, empirically enhancing the robustness of classifiers. Our extensive empirical evaluation demonstrates that ScoreAG improves upon the majority of state-of-the-art attacks and defenses across multiple benchmarks. This work highlights the importance of investigating adversarial examples bounded by semantics rather than p-norm constraints. ScoreAG represents an important step towards more encompassing robustness assessments. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

Predicting Indian Sign Language Gestures Using Deep learning and machine learning Techniques

学校读者我要写书评

暂无评论

Predicting Indian Sign Language Gestures Using Deep Learning...

Sustainable Expert Systems (ICSES), International Conference on

作者： Bhushan Fulkar Rushikesh Burle Pramod Mahale Utkrsha Pacaharaney Department of Artificial intelligence And Data science Datta Meghe institute of Higher Education and Research Wardha India Department of Artificial Intelligence And Machine Learning Datta Meghe institute of Higher Education and Research(DU) Wardha Maharashtra Department of Artificial Intelligence And Machine Learning Datta Meghe institute of Higher Education and Research Wardha India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Indian Sign Language is the language used by people with disabilities in India. Unfortunately, the general public's ignorance of sign language makes it difficult for the especially abled and the general public to communicate. We are releasing a strategy to reduce this difference. We have adopted two distinct strategies to deal with this problem. first by employing the depth+RGB data acquired with a Microsoft Kinect to make gesture predictions in real-time. To segment the hand region from the RGB-D camera data, we used affine transformation and 3D reconstruction to map the RGB and depth information. Convolutional neural networks were trained with inputs that were segmented hand images or videos. With 50 static Indian Sign Language hand gestures used for training, a 97.18% classification accuracy was achieved on test data. Furthermore, this model achieved a 97.71 % classification accuracy when we transferred learning American Sign Language. A convolutional kernel and an LSP were used to train twenty dynamic gestures. This model's classification accuracy was 98.88%. Nevertheless, as soon as we implemented this system, we found that the methodology was flawed. Essentially, it is absurd to need to carry around both a bulky Microsoft Kinect and a device capable of performing the computation required for human-to-person interaction. We attempted to address this issue by using semantic segmentation of the hands. U-Net and ResNet 101 were combined.

关键词： Training Sign language Accuracy Three-dimensional displays Webcams Speech recognition Auditory system Speech enhancement Real-time systems Videos

Strictly positive definite kernels on compact Riemannian manifolds

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Guella, Jean Carlo Jäger, Janin Unicamp Institute of Mathematics Statistics and Scientific Computing Campinas Brazil KU Eichstätt-Ingolstadt Mathematisches Institute for machine learning and data science Ingolstadt Germany

The paper studies strictly positive definite kernels on compact Riemannian manifolds. We state new conditions to ensure strict positive definiteness for general kernels and kernels with certain convolutional structure. We also state conditions for such kernels on product manifolds. As an example conditions for products of two-point homogeneous spaces are *** Codes 33B10, 33C20, 42A16, 46E22, 65D05 Copyright © 2023, The Authors. All rights reserved.

关键词： Geometry

Enhancing Alzheimer's Disease Diagnosis Using Multi-Relation Graph Convolutional Networks and Structural MRI data 5

学校读者我要写书评

暂无评论

Enhancing Alzheimer's Disease Diagnosis Using Multi-Relation...

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Kanna, P. Rajesh Gunasundari, C. Senthamarai, M. Pandiaraja, P. Nithin, P. Chitra, K. Bannari Amman Institute of Technology Department of Computer Science and Engineering Tamil Nadu Erode India SRM Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Trichy India Nandha Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Erode India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Bannari Amman Institute of Technology Department of Artificial Intelligence and Machine Learning Tamil Nadu Erode India Kongu Engineering College Department of Computer Applications Tamil Nadu Erode India

ISBN: (纸本)9798331518097

Alzheimer's disease (AD) has substantial obstacles to early detection, which frequently leads to therapy delays. In this article a unique method that uses structural MRI data and Multi-Relation Graph Convolutional Networks (MR-GCN) to improve AD diagnostic accuracy. Which can capture the nuanced interactions that characterize neurodegenerative disorders by representing the intricate relationships between various brain regions as a multi-relational graph. This strategy provides a comprehensive picture of brain function and pathology through the combination of relational data and structural MRI features. Using a large dataset, the resusts are evaluated and contrasted in MR-GCN method with other machine-learning techniques and single-relation graph models. The findings demonstrate that this method outperforms current models in terms of classification accuracy and resilience, achieving higher sensitivity and specificity in distinguishing between individuals in good health and various stages of AD. Then for further exploration the interpretability of the model is identified in critical brain regions that support the diagnosing process. This work provides a promising framework for the integration of sophisticated graph-based medical imaging tools, which could lead to more sophisticated clinical applications in the diagnosis and monitoring of neurodegenerative diseases in addition to improving our understanding of how AD progresses. © 2024 IEEE.

关键词： Convolutional neural networks

Multi-Stage Bidirectional Cross-Attention Model for Predicting Prognosis in Multiple Peritoneum Lesions with Clinical Information

学校读者我要写书评

暂无评论

Multi-Stage Bidirectional Cross-Attention Model for Predicti...

IEEE International Symposium on Biomedical Imaging

作者： Haoshen Li Jieyuan Cai Yiyuan Wei Zifan Chen Heyun Chen Jie Zhao Yanjie Shi Bin Dong Lei Tang Xiaotian Zhang Li Zhang Center for Data Science Peking University China Peking University Cancer Hospital & Institute China National Engineering Laboratory for Big Data Analysis and Applications Peking University China Peking University Changsha Institute for Computing and Digital Economy China Beijing International Center for Mathematical Research Peking University China Center for Machine Learning Research Peking University China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Peritoneal metastasis occurs when cancer cells spread from the primary tumor to the peritoneum, leading to morphological alterations that significantly impact patient survival. The specific changes across multiple peritoneal sites can effectively indicate a patient's risk level and prognosis. However, the considerable variation in peritoneal shape, size, and location poses significant challenges for feature extraction and prognostic analysis. Traditional multi-instance learning approaches typically fuse instance features extracted by the backbone network at the final stage, but their lack of intermediate interaction limits the ability to capture both common and distinct features. To address this limitation, we propose a Multi-Stage BiDirectional Cross-Attention framework (MSBDCA). Our approach enhances feature extraction and prognostic analysis by facilitating interaction among different peritoneal instances and incorporating clinical information. Experimental comparisons with five baseline models demonstrate our method's superiority, achieving improvements of 8.7% in Area Under Curve (AUC) and 5.9% in Concordance Index (C_index). These results suggest a promising direction for survival and prognostic analysis using peritoneal lesions. Our code is available at https://***/HaoshenLi/MSBDCA.

关键词： learning systems Shape Predictive models Feature extraction Metastasis Lesions Clinical diagnosis Prognostics and health management Abdomen Biomedical imaging

Counterfactually Comparing Abstaining Classifiers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Choe, Yo Joong Gangrade, Aditya Ramdas, Aaditya Data Science Institute University of Chicago United States Department of EECS University of Michigan United States Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University United States

Abstaining classifiers have the option to abstain from making predictions on inputs that they are unsure about. These classifiers are becoming increasingly popular in high-stakes decision-making problems, as they can withhold uncertain predictions to improve their reliability and safety. When evaluating black-box abstaining classifier(s), however, we lack a principled approach that accounts for what the classifier would have predicted on its abstentions. These missing predictions matter when they can eventually be utilized, either directly or as a backup option in a failure mode. In this paper, we introduce a novel approach and perspective to the problem of evaluating and comparing abstaining classifiers by treating abstentions as missing data. Our evaluation approach is centered around defining the counterfactual score of an abstaining classifier, defined as the expected performance of the classifier had it not been allowed to abstain. We specify the conditions under which the counterfactual score is identifiable: if the abstentions are stochastic, and if the evaluation data is independent of the training data (ensuring that the predictions are missing at random), then the score is identifiable. Note that, if abstentions are deterministic, then the score is unidentifiable because the classifier can perform arbitrarily poorly on its abstentions. Leveraging tools from observational causal inference, we then develop nonparametric and doubly robust methods to efficiently estimate this quantity under identification. Our approach is examined in both simulated and real data experiments. © 2023, CC BY-SA.

关键词： Forecasting

Multi-Scale Clinical-Guided Binocular Fusion Framework for Predicting New-Onset Hypertension Over a Four-Year Period

学校读者我要写书评

暂无评论

Multi-Scale Clinical-Guided Binocular Fusion Framework for P...

IEEE International Symposium on Biomedical Imaging

作者： Haoshen Li Zifan Chen Jie Zhao Heyun Chen Hexin Dong Mingze Yuan Bin Dong Li Zhang Center for Data Science Peking University China National Engineering Laboratory for Big Data Analysis and Applications Peking University China Peking University Changsha Institute for Computing and Digital Economy China Beijing International Center for Mathematical Research Peking University China Center for Machine Learning Research Peking University China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Hypertension is a major global health concern, linked to various cardiovascular diseases and associated with distinct ocular manifestations. While recent advances in artificial intelligence have enabled accurate diagnosis of current hypertension through fundus images, predicting the future onset of hypertension remains an uncharted domain. In this study, we introduce the multi-scale clinical-guided binocular fusion framework (MCBO), designed to predict the likelihood of developing hypertension within the next four years. MCBO uniquely integrates left and right fundus images and clinical data, utilizing a shared-weight multi-stage Transformer-based encoder. Our multi-scale clinical-guided module (MCM) ensures image feature extraction is clinically contextualized based on clinical information, and our binocular fusion module (BFM) fuses binocular information. Comparative performance against seven baseline models establishes MCBO’s supremacy, with improvements of 6.7% in Area Under Curve (AUC), 6.9% in Accuracy (ACC), 5.1% in Sensitivity (SEN) and 5.5% in Specificity (SPE). This approach offers a promising avenue for proactive hypertension management, underscoring the potential of integrating Deep learning with clinical data for enhanced healthcare outcomes. Our code is available at https://***/HaoshenLi/MCBO.

关键词： Hypertension Deep learning Accuracy Sensitivity Codes Fuses Feature extraction

machine learning-Based Security for Cloud Computing Challenges and Implications 3

学校读者我要写书评

暂无评论

Machine Learning-Based Security for Cloud Computing Challeng...

3rd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2024

作者： Dattangire, Rahul Burle, Rushikesh Biradar, Divya Dewangan, Leelkanth Data Engineering Independent Researcher HoustonTX77002 United States Datta Meghe Institute of Higher Education and Research Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Maharashtra Wardha442001 India University of Texas at Arlington Computer Science ArlingtonTX76013 United States G H Raisoni College of Engineering Maharashtra Nagpur India

ISBN: (纸本)9798350364569

Cloud computing"is a computer model that provides end users with quantifiable, scalable, and on-demand services. These days, almost every organization uses computer technology extensively for infrastructure, cost-cutting, advanced platforms, data processing, data analytics, and other uses. End users can use any online application from anywhere to access the cloud service providers' (CSP) services. It is imperative to guarantee the security of cloud infrastructure, and a multitude of research employing various technologies is used to provide more accurate and potent defenses against cloud threats. machine learning has shown to be a more useful technology in recent years for protecting cloud infrastructures. machine learning algorithms are trained to generate models that mechanize the process of recognizing cloud threats more precisely than any other technology by using a range of actual datasets as training grounds. A couple of the most recent research that has worked on machine learning to defend against cloud attacks are examined in this paper. © 2024 IEEE.

关键词： Adversarial machine learning