检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Farnoush Rezaei Jafari Grégoire Montavon Klaus-Robert Müller Oliver Eberle Machine Learning Group Technische Universität Berlin Berlin Germany and BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin Germany Department of Mathematics and Computer Science Freie Universitat Berlin Berlin Germany and BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin Germany and Machine Learning Group Technische Universität Berlin Berlin Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin Germany and Machine Learning Group Technische Universität Berlin Berlin Germany and Department of Artificial Intelligence Korea University Seoul South Korea and Max Planck Institute for Informatics Saarbrücken Germany and Google DeepMind Berlin Germany

ISBN: (纸本)9798331314385

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Merging uncertainty sets via majority vote

arXiv

引用

arXiv 2024年

作者： Gasparin, Matteo Ramdas, Aaditya Machine Learning Department Carnegie Mellon University United States Department of Statistics and Data Science Carnegie Mellon University United States Department of Statistical Sciences University of Padova Italy

Given K uncertainty sets that are arbitrarily dependent — for example, confidence intervals for an unknown parameter obtained with K different estimators, or prediction sets obtained via conformal prediction based on K different algorithms on shared data — we address the question of how to efficiently combine them in a black-box manner to produce a single uncertainty set. We present a simple and broadly applicable majority vote procedure that produces a merged set with nearly the same error guarantee as the input sets. We then extend this core idea in a few ways: we show that weighted averaging can be a powerful way to incorporate prior information, and a simple randomization trick produces strictly smaller merged sets without altering the coverage guarantee. Further improvements can be obtained if the sets are exchangeable. We also show that many modern methods, like split conformal prediction, median of means, HulC and cross-fitted "double machine learning", can be effectively derandomized using these ideas. Copyright © 2024, The Authors. All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Conformal online model aggregation

arXiv

引用

arXiv 2024年

Conformal prediction equips machine learning models with a reasonable notion of uncertainty quantification without making strong distributional assumptions. It wraps around any black-box prediction model and converts point predictions into set predictions that have a predefined marginal coverage guarantee. However, conformal prediction only works if we fix the underlying machine learning model in advance. A relatively unaddressed issue in conformal prediction is that of model selection and/or aggregation: for a given problem, which of the plethora of prediction methods (random forests, neural nets, regularized linear models, etc.) should we conformalize? This paper proposes a new approach towards conformal model aggregation in online settings that is based on combining the prediction sets from several algorithms by voting, where weights on the models are adapted over time based on past performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep learning Application for Images Augmentation in Electrical Component Classification System 3rd

Deep Learning Application for Images Augmentation in Electri...

引用

3rd International Conference on Advances in Information and Communication Technology, ICTA 2024

作者： Long, Nguyen The Huong, Nguyen Thu Lien, Pham Thi Gen, Anna Shmeleva Viet, Tran Tuan Department of Informatics Institute of Cybersecurity and Digital Technologies MIREA –Russian Technological University Moscow119454 Russia Laboratory of Artificial Intelligence and Machine Learning Institute of Information Technology and Data Science Irkutsk National Research Technical University Irkutsk664074 Russia University of Information and Communication Technology Thai Nguyen University Thai Nguyen70000 Viet Nam

ISBN: (纸本)9783031809422

The possibility of application a convolutional neural network to assess the augmentation of electrical images is proposed. We studied various conditions for sample preparation, optimizer algorithms, the number of pixels in the samples, the size of the training sample, color schemes, compression quality, and other photometric parameters in view of effect on training the neural network. Due to the proposed preliminary data preparation, the optimum of the architecture and hyperparameters of the neural network we achieved a classification accuracy of at least 98%. This paper outlines measurements of several devices and a process for simulating large amounts of annotated data based on those measurements. A convolutional neural net (CNN) algorithm for classifying signals is described. Performance of the CNN is compared to that of dynamic time warping (DTW) and correlation algorithms, with respect to varying training data set size and noise level. The CNN has the best performance for almost all cases considered. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Homophily and Incentive Effects in Use of Algorithms 44

Homophily and Incentive Effects in Use of Algorithms

引用

44th Annual Meeting of the Cognitive science Society: Cognitive Diversity, CogSci 2022

作者： Fogliato, Riccardo Fazelpour, Sina Gupta, Shantanu Lipton, Zachary Danks, David Department of Statistics and Data Science Carnegie Mellon University United States Department of Philosophy and Religion Khoury College of Computer Sciences Northeastern University United States Machine Learning Department Carnegie Mellon University United States Halicioğlu Data Science Institute Department of Philosophy University of California San Diego United States

As algorithmic tools increasingly aid experts in making consequential decisions, the need to understand the precise factors that mediate their influence has grown commensurately. In this paper, we present a crowdsourcing vignette study designed to assess the impacts of two plausible factors on AI-informed decision-making. First, we examine homophily-do people defer more to models that tend to agree with them?-by manipulating the agreement during training between participants and the algorithmic tool. Second, we considered incentives-how do people incorporate a (known) cost structure in the hybrid decision-making setting?-by varying rewards associated with true positives vs. true negatives. Surprisingly, we found limited influence of either homophily and no evidence of incentive effects, despite participants performing similarly to previous studies. Higher levels of agreement between the participant and the AI tool yielded more confident predictions, but only when outcome feedback was absent. These results highlight the complexity of characterizing human-algorithm interactions, and suggest that findings from social psychology may require re-examination when humans interact with algorithms. © 2022 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY)

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

I Want’Em All (At Once) – Ultrametric Cluster Hierarchies

arXiv

引用

arXiv 2025年

作者： Draganov, Andrew Weber, Pascal Jørgensen, Rasmus Skibdahl Melanchton Beer, Anna Plant, Claudia Assent, Ira Department of Computer Science Aarhus University Aarhus Denmark Data Mining and Machine Learning University of Vienna Vienna Austria UniVie Doctoral School Computer Science University of Vienna Vienna Austria Data Science @ Uni Vienna University of Vienna Vienna Austria

Hierarchical clustering is a powerful tool for exploratory data analysis, organizing data into a tree of clusterings from which a partition can be chosen. This paper generalizes these ideas by proving that, for any reasonable hierarchy, one can optimally solve any center-based clustering objective over it (such as k-means). Moreover, these solutions can be found exceedingly quickly and are themselves necessarily hierarchical. Thus, given a cluster tree, we show that one can quickly access a plethora of new, equally meaningful hierarchies. Just as in standard hierarchical clustering, one can then choose any desired partition from these new hierarchies. We conclude by verifying the utility of our proposed techniques across datasets, hierarchies, and partitioning schemes. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

iSCAN: identifying causal mechanism shifts among nonlinear additive noise models 23

iSCAN: identifying causal mechanism shifts among nonlinear a...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Tianyu Chen Kevin Bello Bryon Aragam Pradeep Ravikumar Department of Statistics and Data Science University of Texas at Austin Booth School of Business University of Chicago and Machine Learning Department Carnegie Mellon University Booth School of Business University of Chicago Machine Learning Department Carnegie Mellon University

Structural causal models (SCMs) are widely used in various disciplines to represent causal relationships among variables in complex systems. Unfortunately, the underlying causal structure is often unknown, and estimating it from data remains a challenging task. In many situations, however, the end goal is to localize the changes (shifts) in the causal mechanisms between related datasets instead of learning the full causal structure of the individual datasets. Some applications include root cause analysis, analyzing gene regulatory network structure changes between healthy and cancerous individuals, or explaining distribution shifts. This paper focuses on identifying the causal mechanism shifts in two or more related datasets over the same set of variables—without estimating the entire DAG structure of each SCM. Prior work under this setting assumed linear models with Gaussian noises; instead, in this work we assume that each SCM belongs to the more general class of nonlinear additive noise models (ANMs). A key technical contribution of this work is to show that the Jacobian of the score function for the mixture distribution allows for the identification of shifts under general non-parametric functional mechanisms. Once the shifted variables are identified, we leverage recent work to estimate the structural differences, if any, for the shifted variables. Experiments on synthetic and real-world data are provided to showcase the applicability of this approach. Code implementing the proposed method is open-source and publicly available at https://***/kevinsbello/iSCAN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Abnormal Load Patterns Detection in Smart Grids Using Temporal Convolutional Neural Network Based Gated Recurrent Units Networks with Multi-Head Temporal Attention 4

Abnormal Load Patterns Detection in Smart Grids Using Tempor...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Balassem, Zayd Srikanteswara, Ramya Esakki Madura, E. Anjaneyulu, Madugula Devi, M. College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Bengaluru India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science India Gokaraju Rangaraju Institute of Engineering and Technology Department of Artificial Intelligence and Machine Learning Hyderabad India New Prince Shri Bhavani College of Engineering and Technology Department of Electrical and Electronics Engineering Chennai India

ISBN: (纸本)9798350352931

In recent era, the advancement in smart grid technologies and the integration of renewable energy sources have modernized the power distribution landscape. The efficiency and stability of overall system is ensured by the controlling of power converters. In existing, Support Vector machine (SVM) is utilized but it assumes the normal data follows Gaussian distribution which is not be the same for smart grid data. In this research, Temporal Convolutional Neural Network based Gated Recurrent Units Networks with Multi-Head Temporal Attention (TCN-GRU-MTA) is proposed. Initially, the input signals are considered from Smart Grid Stability (SGS) dataset. Then, the signals are further preprocessed with autoencoders to reduce noise and to improve quality of signals. The Siamese Neural Networks (SNN) feature extractor efficiently learns relevant features from smart grid data which are indicative of abnormal behavior. After that, the SNN is introduced for extracting features from preprocessed data. Next, the proposed TCN-GRU-MTA is utilized to detect the abnormal load patterns in smart grid networks. From the results, the proposed-established better results including accuracy (99.10%), precision (89.98%), recall (99.05%) and F1-score (95.20%) when compared to existing Quadratic SVM. © 2024 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Advancing OCT-Based Retinal Disease Classification with XLSTM: A Framework for Variable-Length Volume Processing 22

Advancing OCT-Based Retinal Disease Classification with XLST...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Sükei, Emese Oghbaie, Marzieh Schmidt-Erfurth, Ursula Klambauer, Günter Bogunović, Hrvoje Medical University of Vienna Optima Lab Department of Ophthalmology Austria Institute of Artificial Intelligence Medical University of Vienna Center for Medical Data Science Austria Institute for Machine Learning Johannes Kepler University Lit Ai Lab Austria Nxai GmbH Linz Austria

ISBN: (纸本)9798331520526

This paper presents a method for retinal disease classification using optical coherence tomography (OCT) scans, specifically addressing the challenge of variable B-scan density across dataset volumes. Deep learning methods often struggle with fluctuations in the number of B-scans within OCT volumes, which can limit their effectiveness. To address this, we propose an extended long short-term memory (xLSTM) model capable of processing variable-length B-scan sequences, capturing spatial and contextual information across entire volumes regardless of slice count. Leveraging xLSTM's advanced memory structure, our method enhances classification accuracy while maintaining computational efficiency. We evaluated the xLSTM-based approach on public and private datasets, demonstrating its robustness against inter-study variability and domain shifts. Experimental results show that this approach performs on par with or surpasses state-of-the-art baselines and offers a scalable solution for accurate 3D volume classification. © 2025 IEEE.

关键词： 3D volume classification Optical coherence tomography retinal disease classification xLSTM

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：