检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Krahmer, Felix Veselovska, Anna Technical University of Munich Department of Mathematics and Munich Data Science Institute Munich Center for Machine Learning Germany

The evolution of image halftoning, from its analog roots to contemporary digital methodologies, encapsulates a fascinating journey marked by technological advancements and creative innovations. Yet the theoretical understanding of halftoning is much more recent. In this article, we explore various approaches towards shedding light on the design of halftoning approaches and why they work. We discuss both halftoning in a continuous domain and on a pixel grid. We start by reviewing the mathematical foundation of the so-called electrostatic halftoning method, which departed from the heuristic of considering the back dots of the halftoned image as charged particles attracted by the grey values of the image in combination with mutual repulsion. Such an attraction-repulsion model can be mathematically represented via an energy functional in a reproducing kernel Hilbert space allowing for a rigorous analysis of the resulting optimization problem as well as a convergence analysis in a suitable topology. A second class of methods that we discuss in detail is the class of error diffusion schemes, arguably among the most popular halftoning techniques due to their ability to work directly on a pixel grid and their ease of application. The main idea of these schemes is to choose the locations of the black pixels via a recurrence relation designed to agree with the image in terms of the local averages. We discuss some recent mathematical understanding of these methods that is based on a connection to ΣΔ quantizers, a popular class of algorithms for analog-to-digital *** Codes 94A08, 62H35 © 2024, CC BY-NC-SA.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Expected probabilistic hierarchies 24

Expected probabilistic hierarchies

引用

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

作者： Marcel Kollovieh Bertrand Charpentier Daniel Zügner Stephan Günnemann School of Computation Information and Technology Technical University of Munich and Munich Data Science Institute and Munich Center for Machine Learning Pruna AI Microsoft Research AI for Science School of Computation Information and Technology Technical University of Munich and Munich Data Science Institute and Munich Center for Machine Learning and Pruna AI

ISBN: (纸本)9798331314385

Hierarchical clustering has usually been addressed by discrete optimization using heuristics or continuous optimization of relaxed scores for hierarchies. In this work, we propose to optimize expected scores under a probabilistic model over hierarchies. (1) We show theoretically that the global optimal values of the expected Dasgupta cost and Tree-Sampling divergence (TSD), two unsupervised metrics for hierarchical clustering, are equal to the optimal values of their discrete counterparts contrary to some relaxed scores. (2) We propose Expected Probabilistic Hierarchies (EPH), a probabilistic model to learn hierarchies in data by optimizing expected scores. EPH uses differentiable hierarchy sampling enabling end-to-end gradient descent based optimization, and an unbiased subgraph sampling approach to scale to large datasets. (3) We evaluate EPH on synthetic and real-world datasets including vector and graph datasets. EPH outperforms all other approaches quantitatively and provides meaningful hierarchies in qualitative evaluations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EPR-Net: constructing a non-equilibrium potential landscape via a variational force projection formulation

引用

National science Review 2024年第7期11卷 135-147页

作者： Yue Zhao Wei Zhang Tiejun Li Center for Data Science Peking University Zuse Institute Berlin Department of Mathematics and Computer Science Freie Universit?t Berlin Laboratory of Mathematics and Applied Mathematics(LMAM)and School of Mathematical Sciences Peking University Center for Machine Learning Research Peking University

We present EPR-Net, a novel and effective deep learning approach that tackles a crucial challenge in biophysics: constructing potential landscapes for high-dimensional non-equilibrium steady-state ***-Net leverages a nice mathematical fact that the desired negative potential gradient is simply the orthogonal projection of the driving force of the underlying dynamics in a weighted inner-product ***, our loss function has an intimate connection with the steady entropy production rate(EPR),enabling simultaneous landscape construction and EPR estimation. We introduce an enhanced learning strategy for systems with small noise, and extend our framework to include dimensionality reduction and the state-dependent diffusion coefficient case in a unified fashion. Comparative evaluations on benchmark problems demonstrate the superior accuracy, effectiveness and robustness of EPR-Net compared to existing methods. We apply our approach to challenging biophysical problems, such as an eight-dimensional(8D)limit cycle and a 52D multi-stability problem, which provide accurate solutions and interesting insights on constructed landscapes. With its versatility and power, EPR-Net offers a promising solution for diverse landscape construction problems in biophysics.

关键词： high-dimensional potential landscape non-equilibrium system entropy production rate dimensionality reduction deep learning

来源：评论

学校读者我要写书评

暂无评论

Comparing zero-shot self-explanations with human rationales in text classification

arXiv

引用

arXiv 2024年

作者： Brandl, Stephanie Eberle, Oliver Center for Social Data Science University of Copenhagen Denmark Machine Learning Group Technische Universität Berlin Germany

Instruction-tuned LLMs are able to provide an explanation about their output to users by generating self-explanations. These do not require gradient computations or the application of possibly complex XAI methods. In this paper, we analyse whether this ability results in a good explanation. We evaluate self-explanations in the form of input rationales with respect to their plausibility to humans as well as their faithfulness to models. We study two text classification tasks: sentiment classification and forced labour detection, i.e., identifying pre-defined risk indicators of forced labour. In addition to English, we include Danish and Italian translations of the sentiment classification task and compare self-explanations to human annotations for all samples. To allow for direct comparisons, we also compute post-hoc feature attribution, i.e., layer-wise relevance propagation (LRP) and analyse 4 LLMs. We show that self-explanations align more closely with human annotations compared to LRP, while maintaining a comparable level of faithfulness. This finding suggests that self-explanations indeed provide good explanations for text classification. © 2024, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Towards Predicting Menstrual Cycle Phases Exploiting Paralinguistic Features 46

Towards Predicting Menstrual Cycle Phases Exploiting Paralin...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Spiesberger, Anika A. Mallol-Ragolta, Adria Triantafyllopoulos, Andreas Schuller, Björn W. Chi - Health Informatics Klinikum rechts der Isar Technical University of Munich Germany Glam - Group on Language Audio & Music Imperial College London United Kingdom Mcml - Munich Center for Machine Learning Germany Mdsi - Munich Data Science Institute Germany

ISBN: (纸本)9798350371499

As a growing number of people focus on understanding their bodies, the menstrual cycle and its impact on reproduction are gaining attention. Several studies have shown that the voice changes during the menstrual cycle. However, existing research primarily employs comparative analysis to detect these differences. This paper proposes using machine learning methods to analyse paralinguistic features extracted from women's voices for predicting menstrual cycle phases. We leverage available data recorded during the menstrual and late follicular phases of 44 naturally cycling women. Using eight paralinguistic features, we achieve an accuracy of 60 %, showcasing the feasibility of classifying those two phases using speech signals. We discuss implications and suggest future research avenues, such as the need to use personalised approaches. © 2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Using time-aware graph neural networks to predict temporal centralities in dynamic graphs 24

Using time-aware graph neural networks to predict temporal c...

引用

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

作者： Franziska Heeg Ingo Scholtes Chair of Machine Learning for Complex Networks Center for Artificial Intelligence and Data Science (CAIDAS) Julius-Maximilans-Universität Würzburg

ISBN: (纸本)9798331314385

Node centralities play a pivotal role in network science, social network analysis, and recommender systems. In temporal data, static path-based centralities like closeness or betweenness can give misleading results about the true importance of nodes in a temporal graph. To address this issue, temporal generalizations of betweenness and closeness have been defined that are based on the shortest time-respecting paths between pairs of nodes. However, a major issue of those generalizations is that the calculation of such paths is computationally *** this issue, we study the application of De Bruijn Graph Neural Networks (DBGNN), a time-aware graph neural network architecture, to predict temporal path-based centralities in time series data. We experimentally evaluate our approach in 13 temporal graphs from biological and social systems and show that it considerably improves the prediction of betweenness and closeness centrality compared to (i) a static Graph Convolutional Neural Network, (ii) an efficient sampling-based approximation technique for temporal betweenness, and (iii) two state-of-the-art time-aware graph learning techniques for dynamic graphs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Regression in EO: Are VLMs Up to the Challenge?

arXiv

引用

arXiv 2025年

作者： Xue, Xizhe Zhu, Xiao Xiang Data Science in Earth Observation Technical University of Munich Munich80333 Germany Munich Center for Machine Learning Munich80333 Germany

Earth Observation (EO) data encompass a vast range of remotely sensed information, featuring multi-sensor and multi-temporal, playing an indispensable role in understanding our planet’s dynamics. Recently, Vision Language Models (VLMs) have achieved remarkable success in perception and reasoning tasks, bringing new insights and opportunities to the EO field. However, the potential for EO applications, especially for scientific regression related applications remains largely unexplored. This paper bridges that gap by systematically examining the challenges and opportunities of adapting VLMs for EO regression tasks. The discussion first contrasts the distinctive properties of EO data with conventional computer vision datasets, then identifies four core obstacles in applying VLMs to EO regression: 1) the absence of dedicated benchmarks, 2) the discrete-versus-continuous representation mismatch, 3) cumulative error accumulation, and 4) the suboptimal nature of text-centric training objectives for numerical tasks. Next, a series of methodological insights and potential subtle pitfalls are explored. Lastly, we offer some promising future directions for designing robust, domain-aware solutions. Our findings highlight the promise of VLMs for scientific regression in EO, setting the stage for more precise and interpretable modeling of critical environmental processes. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Federated learning in Medical Imaging: Part I: Toward Multicentral Health Care Ecosystems

引用

Journal of the American College of Radiology 2022年第8期19卷 969-974页

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

With recent developments in medical imaging facilities, extensive medical imaging data are produced every day. This increasing amount of data provides an opportunity for researchers to develop data-driven methods and deliver better health care. However, data-driven models require a large amount of data to be adequately trained. Furthermore, there is always a limited amount of data available in each data center. Hence, deep learning models trained on local data centers might not reach their total performance capacity. One solution could be to accumulate all data from different centers into one center. However, data privacy regulations do not allow medical institutions to easily combine their data, and this becomes increasingly difficult when institutions from multiple countries are involved. Another solution is to use privacy-preserving algorithms, which can make use of all the data available in multiple centers while keeping the sensitive data private. Federated learning (FL) is such a mechanism that enables deploying large-scale machine learning models trained on different data centers without sharing sensitive data. In FL, instead of transferring data, a general model is trained on local data sets and transferred between data centers. FL has been identified as a promising field of research, with extensive possible uses in medical research and practice. This article introduces FL, with a comprehensive look into its concepts and recent research trends in medical imaging. © 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

Deep-learning-Based Large-Scale Forest Height Generation

Deep-Learning-Based Large-Scale Forest Height Generation

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Qi Zhang Yuanyuan Wang Xiao Xiang Zhu Chair of Data Science in Earth Observation Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

The vegetation height has been identified as a key biophysical parameter to justify the role of forests in the carbon cycle and ecosystem productivity. Therefore, consistent and large-scale forest height is essential for managing terrestrial ecosystems, mitigating climate change, and preventing biodiversity loss. Since spaceborne multispectral instruments, Light Detection and Ranging (LiDAR), and Synthetic Aperture Radar (SAR) have been widely used for large-scale earth observation for years, this paper explores the possibility of generating largescale and high-accuracy forest heights with the synergy of the Sentinel-1, Sentinel-2, and ICESat-2 data. A Forest Height Generative Adversarial Network (FH-GAN) is developed to retrieve forest height from Sentinel-1 and Sentinel-2 images sparsely supervised by the ICESat-2 data. This model is made up of a cascade forest height and coherence generator, where the output of the forest height generator is fed into the spatial discriminator to regularize spatial details, and the coherence generator is connected to a coherence discriminator to refine the vertical details. A progressive strategy further underpins the generator to boost the accuracy of multi-source forest height estimation. Results indicated that FH-GAN achieves the best RMSE of 2.10 m at a large scale compared with the LVIS reference and the best RMSE of 6.16 m compared with the ICESat-2 reference.

关键词： Forests Accuracy Ecosystems Sentinel-1 Estimation Coherence Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Investor Risk Profile Determination Model 16

Investor Risk Profile Determination Model

引用

16th International Conference Management of Large-Scale System Development, MLSD 2023

作者： Gorelik, Victor Zolotova, Tatiana Federal Research Center 'Computer Science and Control' of the Russian Academy of Sciences Department of Simulation Systems and Operations Research Moscow Russia Financial University under the Government of the Russian Federation Department of Data Analysis and Machine Learning Moscow Russia

ISBN: (纸本)9798350337907

An assessment of the investor's risk profile is proposed as a risk coefficient in a model with a linear convolution of expected return and variance. The value of the risk coefficient is found from solving the optimization problem of the model with a limitation on profitability. The proposed method is implemented in the form of a software package using the example of the stock market. © 2023 IEEE.

关键词： Convolution

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：