检索结果-内蒙古大学图书馆

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

作者： Zhixun Li Liang Wang Xin Sun Yifan Luo Yanqiao Zhu Dingshuo Chen Yingtao Luo Xiangxin Zhou Qiang Liu Shu Wu Jeffrey Xu Yu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences and Department of Automation University of Science and Technology of China Department of Automation University of Science and Technology of China School of Cyberspace Security Beijing University of Posts and Telecommunications Department of Computer Science University of California Los Angeles Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University

Graph Structure learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exact Decomposition of Joint Low Rankness and Local Smoothness Plus Sparse Matrices

arXiv

引用

arXiv 2022年

作者： Peng, Jiangjun Wang, Yao Zhang, Hongying Wang, Jianjun Meng, Deyu School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi'an Jiaotong University Shaan'xi Xi’an710049 China The Center for Intelligent Decision-making and Machine Learning School of Management Xian Jiaotong University Shaan'xi Xi’an China The College of Artificial Intelligence Southwest University Chongqing400715 China Macau Institute of Systems Engineering Macau University of Science and Technology Taipa China

It is known that the decomposition in low-rank and sparse matrices (L+S for short) can be achieved by several Robust PCA techniques. Besides the low rankness, the local smoothness (LSS) is a vitally essential prior for many real-world matrix data such as hyperspectral images and surveillance videos, which makes such matrices have low-rankness and local smoothness property at the same time. This poses an interesting question: Can we make a matrix decomposition in terms of L&LSS +S form exactly? To address this issue, we propose in this paper a new RPCA model based on three-dimensional correlated total variation regularization (3DCTV-RPCA for short) by fully exploiting and encoding the prior expression underlying such joint low-rank and local smoothness matrices. Specifically, using a modification of Golfing scheme, we prove that under some mild assumptions, the proposed 3DCTV-RPCA model can decompose both components exactly, which should be the first theoretical guarantee among all such related methods combining low rankness and local smoothness. In addition, by utilizing Fast Fourier Transform (FFT), we propose an efficient ADMM algorithm with a solid convergence guarantee for solving the resulting optimization problem. Finally, a series of experiments on both simulations and real applications are carried out to demonstrate the general validity of the proposed 3DCTV-RPCA model. Copyright © 2022, The Authors. All rights reserved.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

GSLB: The Graph Structure learning Benchmark

arXiv

引用

arXiv 2023年

作者： Li, Zhixun Wang, Liang Sun, Xin Luo, Yifan Zhu, Yanqiao Chen, Dingshuo Luo, Yingtao Zhou, Xiangxin Liu, Qiang Wu, Shu Yu, Jeffrey Xu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Center for Research on Intelligent Perception Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Department of Automation University of Science and Technology of China China School of Cyberspace Security Beijing University of Posts and Telecommunications China Department of Computer Science University of California Los Angeles United States Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University United States

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Optimal Probabilistic Classification in Active Class Selection

Optimal Probabilistic Classification in Active Class Selecti...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Mirko Bunse Dorina Weichert Alexander Kister Katharina Morik Artificial Intelligence Group TU Dortmund University Germany Fraunhofer Institute for Intelligent Analysis and Information Systems Germany Fraunhofer Center for Machine Learning Germany

ISBN: (数字)9781728183169

ISBN: (纸本)9781728183176

The goal of active class selection (ACS) is to optimize the class proportions in newly acquired data; a classifier trained from that data should exhibit maximum performance during its deployment. This paper provides an information-theoretic examination of the problem, resulting in an upper bound of the classifier's error. This upper bound shows that the more data is acquired, the better is the performance of the class proportions that occur during deployment; other class proportions can outperform these natural proportions in the beginning of data acquisition, but natural proportions certainly yield optimal probabilistic classifiers in the limit. Put differently-and perhaps surprisingly-the more data is acquired, the less beneficial are ACS strategies. Our bound further reveals that the degree to which non-natural class proportions are eligible depends on the correlation between the features and the class label. Experiments on standard ACS data sets quantify these effects and also show that the conclusions drawn from our analysis take over to non-probabilistic classifiers.

关键词： Training Upper bound Training data Probabilistic logic Rendering (computer graphics) Standards Physics

来源：评论

学校读者我要写书评

暂无评论

Optimization of high precision manufacturing by Monte Carlo tree search

arXiv

引用

arXiv 2021年

作者： Weichert, Dorina Horchler, Felix Kister, Alexander Trost, Marcus Hartung, Johannes Risse, Stefan Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Schloss Birlinghoven Sankt Augustin53757 Germany Fraunhofer Center for Machine Learning Institute of Computer Science Bonn University Bonn53115 Germany Fraunhofer Institue for Applied Optics and Precision Engineering IOF Jena07745 Germany

Monte Carlo Tree Search (MCTS) has shown its strength for a lot of deterministic and stochastic examples, but literature lacks reports of applications to real world industrial processes. Common reasons for this are that there is no efficient simulator of the process available or there exist problems in applying MCTS to the complex rules of the process. In this paper, we apply MCTS for optimizing a high-precision manufacturing process that has stochastic and partially observable outcomes. We make use of an expert-knowledge-based simulator and adapt the MCTS default policy to deal with the manufacturing process. Copyright © 2021, The Authors. All rights reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Characteristics of Monte Carlo Dropout in Wide Neural Networks

arXiv

引用

arXiv 2020年

作者： Sicking, Joachim Akila, Maram Wirtz, Tim Houben, Sebastian Fischer, Asja Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Sankt Augustin Germany Fraunhofer Center for Machine Learning Faculty of Mathematics Ruhr-University Bochum Bochum Germany

Monte Carlo (MC) dropout is one of the state-of-the-art approaches for uncertainty estimation in neural networks (NNs). It has been interpreted as approximately performing Bayesian inference. Based on previous work on the approximation of Gaussian processes by wide and deep neural networks with random weights, we study the limiting distribution of wide untrained NNs under dropout more rigorously and prove that they as well converge to Gaussian processes for fixed sets of weights and biases. We sketch an argument that this property might also hold for infinitely wide feed-forward networks that are trained with (full-batch) gradient descent. The theory is contrasted by an empirical analysis in which we find correlations and non-Gaussian behaviour for the pre-activations of finite width NNs. We therefore investigate how (strongly) correlated pre-activations can induce non-Gaussian behavior in NNs with strongly correlated weights. Copyright © 2020, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

sbi reloaded: a toolkit for simulation-based inference workflows

arXiv

引用

arXiv 2024年

作者： Boelts, Jan Deistler, Michael Gloeckler, Manuel Tejero-Cantero, Álvaro Lueckmann, Jan-Matthis Moss, Guy Steinbach, Peter Moreau, Thomas Muratore, Fabio Linhart, Julia Durkan, Conor Vetter, Julius Miller, Benjamin Kurt Herold, Maternus Ziaeemehr, Abolfazl Pals, Matthijs Gruner, Theo Bischoff, Sebastian Krouglova, Anastasia N. Gao, Richard Lappalainen, Janne K. Mucsányi, Bálint Pei, Felix Schulz, Auguste Stefanidi, Zinovia Rodrigues, Pedro L.C. Schröder, Cornelius Zaid, Faried Abu Beck, Jonas Kapoor, Jaivardhan Greenberg, David S. Gonçalves, Pedro J. Macke, Jakob H. Machine Learning in Science University of Tübingen Germany Tübingen AI Center Germany TransferLab AppliedAI Institute for Europe Germany ML Colab Cluster ML in Science University of Tübingen Germany Google Research United States Helmholtz-Zentrum Dresden-Rossendorf Germany Université Paris-Saclay INRIA CEA Palaiseau France Robert Bosch GmbH Germany School of Informatics University of Edinburgh United Kingdom University of Amsterdam Netherlands Research and Innovation Center BMW Group Germany Institute for Applied Mathematics and Scientific Computing University of the Bundeswehr Munich Germany Aix Marseille INSERM INS France TU Darmstadt Hessian.AI Germany University Hospital Tübingen M3 Research Center Germany Faculty of Science KU Leuven B-3000 Belgium Imec Belgium Methods of Machine Learning University of Tübingen Germany Neuroscience Institute Carnegie Mellon University United States Université Grenoble Alpes INRIA CNRS Grenoble INP LJK France Hertie Institute for AI in Brain Health University of Tübingen Germany Institute of Coastal Systems - Analysis and Modeling Helmholtz AI Germany Departments of Computer Science Electrical Engineering KU Leuven Belgium Department Empirical Inference Max Planck Institute for Intelligent Systems Tübingen Germany

Scientists and engineers use simulators to model empirically observed phenomena. However, tuning the parameters of a simulator to ensure its outputs match observed data presents a significant challenge. Simulation-based inference (SBI) addresses this by enabling Bayesian inference for simulators, identifying parameters that match observed data and align with prior knowledge. Unlike traditional Bayesian inference, SBI only needs access to simulations from the model and does not require evaluations of the likelihood-function. In addition, SBI algorithms do not require gradients through the simulator, allow for massive parallelization of simulations, and can perform inference for different observations without further simulations or training, thereby amortizing inference. Over the past years, we have developed, maintained, and extended sbi, a PyTorch-based package4 that implements Bayesian SBI algorithms based on neural networks. The sbi toolkit implements a wide range of inference methods, neural network architectures, sampling methods, and diagnostic tools. In addition, it provides well-tested default settings but also offers flexibility to fully customize every step of the simulation-based inference workflow. Taken together, the sbi toolkit enables scientists and engineers to apply state-of-the-art SBI methods to black-box simulators, opening up new possibilities for aligning simulations with empirically observed data. © 2024, CC BY-SA.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Predicting Motor Excitability in TMS using EEG-Features: A machine learning Approach

引用

Clinical Neurophysiology 2024年 159卷 e47-e48页

作者： Haxel, L. Belardinelli, P. Macke, J.H. Ziemann, U. Hertie Institute for Clinical Brain Research University of Tübingen Germany Department of Neurology & Stroke University of Tübingen Germany Machine Learning in Science Excellence Cluster Machine Learning University of Tübingen Germany Tübingen AI Center University of Tübingen Germany CiMeC Center for Mind and Brain Sciences University of Trento Italy Max Planck Institute for Intelligent Systems Tübingen Germany Department of Neurology & Stroke and Hertie Institute for Clinical Brain Research Eberhard Karls University Tübingen Germany

来源：评论

学校读者我要写书评

暂无评论

Convolutional Capsule-Based Network for Person Re-identification 15th

Convolutional Capsule-Based Network for Person Re-identifica...

引用

15th International Conference on intelligent Computing, ICIC 2019

作者： Li, Andong Wu, Di Huang, De-Shuang Zhang, Lijun Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University Shanghai China Collaborative Innovation Center of Intelligent New Energy Vehicle Shanghai China School of Automotive Studies Tongji University Shanghai China

ISBN: (纸本)9783030267629

Person re-identification is yet a critical challenging task in video surveillance domain. It aims to match the same person across different cameras. Practically, pedestrian’s appearances may vary greatly due to the complex background. Most deep learning methods rely on convolutional neural network to extract the feature of the pedestrian. But most of them lose the crucial details of the pedestrian and are sensitive to the viewpoints of the camera. To remedy this problem, we propose using capsule network as the feature extractor and introduce an improved loss function for the network. The experiment results on the Market-1501 dataset show the effectiveness of the proposed method. © 2019, Springer Nature Switzerland AG.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Real-time gravitational-wave inference for binary neutron stars using machine learning

arXiv

引用

arXiv 2024年

作者： Dax, Maximilian Green, Stephen R. Gair, Jonathan Gupte, Nihar Pürrer, Michael Raymond, Vivien Wildberger, Jonas Macke, Jakob H. Buonanno, Alessandra Schölkopf, Bernhard Max Planck Institute for Intelligent Systems Max-Planck-Ring 4 Tübingen72076 Germany School of Mathematical Sciences University of Nottingham University Park NottinghamNG7 2RD United Kingdom Am Mühlenberg 1 Potsdam14476 Germany Department of Physics University of Maryland College ParkMD20742 United States Department of Physics University of Rhode Island East Hall KingstonRI02881 United States Center for Computational Research Carothers Library University of Rhode Island KingstonRI02881 United States Gravity Exploration Institute Cardiff University CardiffCF24 3AA United Kingdom ELLIS Institute Tübingen Maria-von-Linden-Straße 2 Tübingen72076 Germany Machine Learning in Science University of Tübingen & Tübingen AI Center Tübingen72076 Germany

Mergers of binary neutron stars (BNSs) emit signals in both the gravitational-wave (GW) and electromagnetic (EM) spectra. Famously, the 2017 multi-messenger observation of GW170817 [1, 2] led to scientific discoveries across cosmology [3], nuclear physics [4–6], and gravity [7]. Central to these results were the sky localization and distance obtained from GW data, which, in the case of GW170817, helped to identify the associated EM transient, AT 2017gfo [8], 11 hours after the GW signal. Fast analysis of GW data is critical for directing time-sensitive EM observations;however, due to challenges arising from the length and complexity of signals, it is often necessary to make approximations that sacrifice accuracy. Here, we present a machine learning framework that performs complete BNS inference in just one second without making any such approximations. Our approach enhances multi-messenger observations by providing (i) accurate localization even before the merger;(ii) improved localization precision by ∼ 30% compared to approximate low-latency methods;and (iii) detailed information on luminosity distance, inclination, and masses, which can be used to prioritize expensive telescope time. Additionally, the flexibility and reduced cost of our method open new opportunities for equation-of-state studies. Finally, we demonstrate that our method scales to extremely long signals, up to an hour in length, thus serving as a blueprint for data analysis for next-generation ground- and space-based detectors. Copyright © 2024, The Authors. All rights reserved.

关键词： Stars

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：