检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jafari, Farnoush Rezaei Montavon, Grégoire Müller, Klaus-Robert Eberle, Oliver Machine Learning Group Technische Universität Berlin Berlin10587 Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany Department of Mathematics and Computer Science Freie Universität Berlin Arnimallee 14 Berlin14195 Germany Department of Artificial Intelligence Korea University Seoul136-713 Korea Republic of Max Planck Institute for Informatics Stuhlsatzenhausweg 4 Saarbrücken66123 Germany Google DeepMind Berlin Germany

Recent sequence modeling approaches using selective state space sequence models, referred to as Mamba models, have seen a surge of interest. These models allow efficient processing of long sequences in linear time and are rapidly being adopted in a wide range of applications such as language modeling, demonstrating promising performance. To foster their reliable use in real-world scenarios, it is crucial to augment their transparency. Our work bridges this critical gap by bringing explainability, particularly Layer-wise Relevance Propagation (LRP), to the Mamba architecture. Guided by the axiom of relevance conservation, we identify specific components in the Mamba architecture, which cause unfaithful explanations. To remedy this issue, we propose MambaLRP, a novel algorithm within the LRP framework, which ensures a more stable and reliable relevance propagation through these components. Our proposed method is theoretically sound and excels in achieving state-of-the-art explanation performance across a diverse range of models and datasets. Moreover, MambaLRP facilitates a deeper inspection of Mamba architectures, uncovering various biases and evaluating their significance. It also enables the analysis of previous speculations regarding the long-range capabilities of Mamba models. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unbiased Test Error Estimation in the Poisson Means Problem via Coupled Bootstrap Techniques

arXiv

引用

arXiv 2022年

作者： Oliveira, Natalia L. Lei, Jing Tibshirani, Ryan J. Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University United States

We propose a coupled bootstrap (CB) method for the test error of an arbitrary algorithm that estimates the mean in a Poisson sequence, often called the Poisson means problem. The idea behind our method is to generate two carefully-designed data vectors from the original data vector, by using synthetic binomial noise. One such vector acts as the training sample and the second acts as the test sample. To stabilize the test error estimate, we average this over multiple bootstrap B of the synthetic noise. A key property of the CB estimator is that it is unbiased for the test error in a Poisson problem where the original mean has been shrunken by a small factor, driven by the success probability p in the binomial noise. Further, in the limit as B → ∞ and p → 0, we show that the CB estimator recovers a known unbiased estimator for test error based on Hudson's lemma, under no assumptions on the given algorithm for estimating the mean (in particular, no smoothness assumptions). Our methodology applies to two central loss functions that can be sused to define test error: Poisson deviance and squared loss. Via a bias-variance decomposition, for each loss function, we analyze the effects of the binomial success probability and the number of bootstrap samples and on the accuracy of the estimator. We also investigate our method empirically across a variety of settings, using simulated as well as real data. © 2022, CC BY.

关键词： Error analysis

来源：评论

学校读者我要写书评

暂无评论

A Permutation-Free Kernel Independence Test

引用

Journal of machine learning Research 2023年 24卷

作者： Shekhar, Shubhanshu Kim, Ilmun Ramdas, Aaditya Department of Statistics and Data Science Carnegie Mellon University PittsburghPA15213 United States Department of Statistics and Data Science Department of Applied Statistics Yonsei University Seodaemun-gu Seoul03722 Korea Republic of Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States

In nonparametric independence testing, we observe i.i.d. data {(Xi,Yi)}in=1, where X ∈ X,Y ∈ Y lie in any general spaces, and we wish to test the null that X is independent of Y. Modern test statistics such as the kernel Hilbert–Schmidt Independence Criterion (HSIC) and Distance Covariance (dCov) have intractable null distributions due to the degeneracy of the underlying U-statistics. Hence, in practice, one often resorts to using permutation testing, which provides a nonasymptotic guarantee at the expense of recalculating the quadratic-time statistics (say) a few hundred times. In this paper, we provide a simple but nontrivial modification of HSIC and dCov (called xHSIC and xdCov, pronounced "cross" HSIC/dCov) so that they have a limiting Gaussian distribution under the null, and thus do not require permutations. We show that our new tests, like the originals, are consistent against fixed alternatives, and minimax rate optimal against smooth local alternatives. Numerical simulations demonstrate that compared to the permutation tests, our variants have the same power within a constant factor, giving practitioners a new option for large problems or data-analysis pipelines where computation, not sample size, could be the bottleneck. © 2023 Shubhanshu Shekhar, Ilmun Kim, and Aaditya Ramdas.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation under Open Set Label Shift

arXiv

引用

arXiv 2022年

作者： Garg, Saurabh Balakrishnan, Sivaraman Lipton, Zachary C. Machine Learning Department Department of Statistics and Data Science Carnegie Mellon University United States

We introduce the problem of domain adaptation under Open Set Label Shift (OSLS) where the label distribution can change arbitrarily and a new class may arrive during deployment, but the class-conditional distributions p(x|y) are domain-invariant. OSLS subsumes domain adaptation under label shift and Positive-Unlabeled (PU) learning. The learner's goals here are two-fold: (a) estimate the target label distribution, including the novel class;and (b) learn a target classifier. First, we establish necessary and sufficient conditions for identifying these quantities. Second, motivated by advances in label shift and PU learning, we propose practical methods for both tasks that leverage black-box predictors. Unlike typical open set domain adaptation problems, which tend to be ill-posed and amenable only to heuristics, OSLS offers a well-posed problem amenable to more principled machinery. Experiments across numerous semi-synthetic benchmarks on vision, language, and medical datasets demonstrate that our methods consistently outperform open set domain adaptation baselines, achieving 10-25% improvements in target domain accuracy. Finally, we analyze the proposed methods, establishing finite-sample convergence to the true label marginal and convergence to optimal classifier for linear models in a Gaussian setup. Copyright © 2022, The Authors. All rights reserved.

关键词： machinery

来源：评论

学校读者我要写书评

暂无评论

Online Selective Conformal Prediction: Errors and Solutions

arXiv

引用

arXiv 2025年

作者： Sale, Yusuf Ramdas, Aaditya Institute of Computer Science Ludwig-Maximilians Universität München Germany Department of Statistics and Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States Germany

In online selective conformal inference, data arrives sequentially, and prediction intervals are constructed only when an online selection rule is met. Since online selections may break the exchangeability between the selected test datum and the rest of the data, one must correct for this by suitably selecting the calibration data. In this paper, we evaluate existing calibration selection strategies and pinpoint some fundamental errors in the associated claims that guarantee selection-conditional coverage and control of the false coverage rate (FCR). To address these shortcomings, we propose novel calibration selection strategies that provably preserve the exchangeability of the calibration data and the selected test datum. Consequently, we demonstrate that online selective conformal inference with these strategies guarantees both selection-conditional coverage and FCR control. Our theoretical findings are supported by experimental evidence examining tradeoffs between valid methods. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

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

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

引用

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

来源：评论

学校读者我要写书评

暂无评论

Development of Punjabi Automatic Speech Recognition Application for Mobile Devices

Development of Punjabi Automatic Speech Recognition Applicat...

引用

International Conference on Computing Communication Control and Automation (ICCUBEA)

作者： Puneet Mittal Sukhwinder Sharma Department of Artificial Intelligence & Machine Learning Manipal University Jaipur Jaipur India Department of Data Science & Engineering Manipal University Jaipur Jaipur India

Speech recognition based mobile device applications are gaining popularity due to their ease of use, flexibility as well as ability to provide hands-free access to device features and functions for persons without hands or with disabilities like blindness. The increased accuracy of Automatic Speech Recognition (ASR) systems and support to multiple languages is further motivating the researchers to develop such applications. The development of an application for mobile device helps to validate the applicability of an ASR system in real world environment. An android based speech recognition application for calling and messaging features has been designed and developed in this paper. User can send message or call to any phone number or contact stored in the mobile phone using Punjabi speech. Punjabi based ASR system having pronunciation dictionary, acoustic model and language model is used to implement the underlying speech recognition for Punjabi speakers. Speech user interface has been designed using Android, while AndroidPocketSphinx has been used as speech decoder. The successfully running application has been tested for multiple male and female native Punjabi speakers, followed by thorough performance analysis. The results shown are quite optimistic with a very low combined error of 1.6% for all female speakers and 2.1% for all male speakers. The application gives 98.4% success rate or recognition accuracy for female speakers and 97.9% for male speakers for the underlying Punjabi based ASR system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated learning in Medical Imaging: Part II: Methods, Challenges, and Considerations

引用

Journal of the American College of Radiology 2022年第8期19卷 975-982页

作者： Darzidehkalani, Erfan Ghasemi-rad, Mohammad van Ooijen, P.M.A. Department of Radiation Oncology University Medical Center Groningen University of Groningen Groningen Netherlands Machine Learning Lab Data Science Center in Health University Medical Center Groningen University of Groningen Netherlands Department of Interventional Radiology Baylor College of Medicine Houston Texas

Federated learning is a machine learning method that allows decentralized training of deep neural networks among multiple clients while preserving the privacy of each client's data. Federated learning is instrumental in medical imaging because of the privacy considerations of medical data. Setting up federated networks in hospitals comes with unique challenges, primarily because medical imaging data and federated learning algorithms each have their own set of distinct characteristics. This article introduces federated learning algorithms in medical imaging and discusses technical challenges and considerations of real-world implementation of them. © 2022 American College of Radiology

关键词： Federated learning medical imaging privacy-preserving machine learning

来源：评论

学校读者我要写书评

暂无评论

Bounding the number of reticulation events for displaying multiple trees in a phylogenetic network

arXiv

引用

arXiv 2024年

作者： Wu, Yufeng Zhang, Louxin School of Computing University of Connecticut StorrsCT06269 United States Department of Mathematics Center for Data Science and Machine Learning National University of Singapore Singapore119076 Singapore

Reconstructing a parsimonious phylogenetic network that displays multiple phylogenetic trees is an important problem in phylogenetics, where the complexity of the inferred networks is measured by reticulation numbers. The reticulation number for a set of trees is defined as the minimum number of reticulations in a phylogenetic network that displays those trees. A mathematical problem is bounding the reticulation number for multiple trees over a fixed number of taxa. While this problem has been extensively studied for two trees, much less is known about the upper bounds on the reticulation numbers for three or more arbitrary trees. In this paper, we present a few non-trivial upper bounds on reticulation numbers for three or more *** Codes 5C30 © 2024, CC BY.

关键词： Abiotic

来源：评论

学校读者我要写书评

暂无评论

Impact of Ensemble of Vector Embeddings on Speculative Retrieval Augmented Generation 5

Impact of Ensemble of Vector Embeddings on Speculative Retri...

引用

5th International Conference on data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Kukreja, Sanjay Kumar, Tarun Bharate, Vishal Singh, Rajat Dasgupta, Abhijit Guha, Debashis Sp Jain School of Global Management Department of Machine Learning Mumbai India EClerx Services Ltd. Coe AI-ML Chandigarh India EClerx Services Ltd. Coe AI-ML Pune India EClerx Services Ltd. Coe AI-ML Mumbai India Sp Jain School of Global Management Department of Data Science Mumbai India

ISBN: (纸本)9798350389609

Recent developments in Natural Language Processing (NLP) have impacted all fields. Retrieval Augmented Generation (RAG) has played significant part in resent advancements in NLP applications. RAG architecture combines the powers of retrieval-based methods and generative models to increase the relevance and accuracy of generated texts. This paper deals with the performance comparison on speculative RAG, recent development in RAG systems, with different state-of-the-art vector embedding models and their ensembles. Two approaches were adopted to carry out this research: one-to-one mapping context with response-rationale and mapping of clustered contexts with response and rationale. The performance measures semantic answer similarity (SAS), and Rouge score on descriptive-type NCERT books dataset. State-of-the-art vector embedding models, BAAI/bge-base-en, thenlper/gte-base and intfloat/e5-base-v2, were used individually and to create average and weighted average ensemble *** responses of the systems corresponding to the 200 questions used for evaluation were validated against the NCERT Solution dataset. The result showed that the ensemble of vector embedding models outperforms state-of-the-art embedding models with weighted average ensemble achieving the highest accuracy. Further, the clustered context approach consistently outperforms the one-to-one mapping approach with noticeably higher SAS and Rouge metric values corresponding to each vector embedding method employed. For weighted average ensemble, the clustering approach improves the semantic answer similarity value by 8.24% over the one-to-one mapping approach. The performance of the systems may be improved by optimizing the weights of the weighted average ensemble and better clustering approaches. Various institutions using RAG systems for descriptive question-answer solutions may benefit from employing advancement in RAG systems. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：