检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Bungert, Leon Raab, René Roith, Tim Schwinn, Leo Tenbrinck, Daniel Department Mathematics Friedrich-Alexander University Erlangen-Nürnberg Cauerstraße 11 Erlangen91058 Germany Machine Learning and Data Analytics Lab Friedrich-Alexander University Erlangen-Nürnberg Carl-Thiersch-Straße 2b Erlangen91052 Germany

Despite the large success of deep neural networks (DNN) in recent years, most neural networks still lack mathematical guarantees in terms of stability. For instance, DNNs are vulnerable to small or even imperceptible input perturbations, so called adversarial examples, that can cause false predictions. This instability can have severe consequences in applications which influence the health and safety of humans, e.g., biomedical imaging or autonomous driving. While bounding the Lipschitz constant of a neural network improves stability, most methods rely on restricting the Lipschitz constants of each layer which gives a poor bound for the actual Lipschitz constant. In this paper we investigate a variational regularization method named CLIP for controlling the Lipschitz constant of a neural network, which can easily be integrated into the training procedure. We mathematically analyze the proposed model, in particular discussing the impact of the chosen regularization parameter on the output of the network. Finally, we numerically evaluate our method on both a nonlinear regression problem and the MNIST and Fashion-MNIST classification databases, and compare our results with a weight regularization *** Codes 65K10, 68T07 Copyright © 2021, The Authors. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Structure of Attention in a Transformer Language Model

arXiv

引用

arXiv 2019年

作者： Vig, Jesse Belinkov, Yonatan Palo Alto Research Center Machine Learning and Data Science Group Interaction and Analytics Lab Palo AltoCA United States Harvard John A. Paulson School of Engineering and Applied Sciences MIT Computer Science and Artificial Intelligence Laboratory CambridgeMA United States

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the GPT-2 small pretrained model. We visualize attention for individual instances and analyze the interaction between attention and syntax over a large corpus. We find that attention targets different parts of speech at different layer depths within the model, and that attention aligns with dependency relations most strongly in the middle layers. We also find that the deepest layers of the model capture the most distant relationships. Finally, we extract exemplar sentences that reveal highly specific patterns targeted by particular attention heads. Copyright © 2019, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Assessing Personality Traits of Team Athletes in Virtual Reality

Assessing Personality Traits of Team Athletes in Virtual Rea...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Markus Wirth Stefan Gradl Wolfgang A. Mehringer Richard Kulpa Hannes Rupprecht Dino Poimann Annemarie F. Laudanski Bjoern M. Eskofier Machine Learning & Data Analytics Univ. of Erlangen-Nürnberg (FAU) Erlangen Germany MM2S Lab University Rennes 2 Rennes France FC Red Bull Salzburg Academy Salzburg Austria Department of Kinesiology University of Waterloo Waterloo Ontario Canada

ISBN: (数字)9781728165325

ISBN: (纸本)9781728165332

Assessment of personality traits is highly relevant in team sports in order to analyze the performance of an athlete under pressure when in competitive situations, for team-strategic decisions, to optimize command transmission, and ultimately to understand top-level performers. It further facilitates the development and application of personalized exercises, coaching to improve performance in competition, and can be considered a valuable criterion for talent scouting and development. The current state of the art method to assess personality traits in sports relies on validated questionnaires. However, these often provide non-sport-specific, subjective self-reported information and lack the ability to measure how these characteristics are reflected in context-based *** developed a virtual reality (VR) tool for the assessment of personality traits in team sports, in our case for soccer. An evaluation of this tool within a study with 24 subjects yielded a benchmark of its immersion through user experience and provided an objective description of athletes’ personalities based on performance indicators extracted from activity-tracking. Within the tool, we implemented two realistic virtual soccer environments to assess the motivational orientation of soccer players (i.e. action- and state-orientation) which we discerned from the gold standard *** show that user experience and presence of the implemented virtual environments scored significantly higher compared to benchmark measurements. Additionally, a significant difference between the two groups of action and state-oriented athletes could be observed. Measures of failure rate, pass accuracy, number of perceived opponents, and achieved bonus goals are parameters that differ significantly among the two athlete groups. These findings show that VR technology is applicable for the assessment of athletes’ motivational orientation and thus demonstrate the feasibility of virtual environments as func

关键词： Training Task analysis Tools Decision making Games Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Prediction of Stress Coping Capabilities from Nightly Heart Rate Patterns using machine learning

Prediction of Stress Coping Capabilities from Nightly Heart ...

引用

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Linda Vorberg Siri Pflueger Robert Richer Katharina M. Jaeger Arne Küderle Nicolas Rohleder Bjoern M. Eskofier Department Artificial Intelligence in Biomedical Engineering (AIBE) Machine Learning and Data Analytics Lab (MaD Lab) Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany Chair of Health Psychology Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany

Stress is related to short- and long-term alterations in stress systems, including the hypothalamic-pituitary-adrenal (HPA) axis and the sympathetic nervous system (SNS). While it is well established that stress experienced during the day can affect sleep quality, less is known about how it affects stress systems during the night. We assume that stress coping strategies can have an impact on how stress carries over into the night and that individuals with bad coping mechanisms show elevated activation of stress systems during sleep. For that reason, we recorded the heart rate (HR) and heart rate variability (HRV) of 21 healthy participants on two consecutive nights during sleep and the first hour after awakening and extracted cortisol and alpha-amylase from saliva samples collected in the first hour after awakening. Stress coping capabilities were assessed using self-reports. We performed backward stepwise multiple regression models to analyze the relationship between HR(V) and stress coping and trained different machine learning-based regression algorithms to predict positive (SVF Pos ) and negative (SVF Neg ) stress coping capabilities, respectively. Our results show that individuals with higher SVF Neg scores showed higher SNS activity during the night, whereas higher SVF Pos scores indicated lower SNS activity. SVF Pos was predicted with a mean absolute error (MAE) of 1.51 ± 0.73 and SVF Neg with an MAE of 2.79 ± 1.53. Our findings indicate an association between nightly HR(V) and the individual’s capability of coping with stress. This provides further information about how stress influences sleep and might be used for tailored intervention and feedback on successful stress coping.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Correction to: Wearable gait analysis systems: ready to be used by medical practitioners in geriatric wards?

引用

European geriatric medicine 2022年第4期13卷 825-826页

作者： Malte Ollenschläger Felix Kluge Matthias Müller-Schulz Rupert Püllen Claudia Möller Jochen Klucken Bjoern M Eskofier Machine Learning and Data Analytics Lab Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Carl-Thiersch-Str. 2b 91052 Erlangen Germany. malte.ollenschlaeger@fau.de. Machine Learning and Data Analytics Lab Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Carl-Thiersch-Str. 2b 91052 Erlangen Germany. AGAPLESION DIAKONIEKLINIKUM HAMBURG Hamburg Germany. AGAPLESION MARKUS KRANKENHAUS Frankfurt am Main Germany. AGAPLESION gAG Frankfurt am Main Germany. Centre Hospitalier de Luxembourg Luxembourg Institute of Health University of Luxembourg Esch-sur-Alzette Luxembourg.

来源：评论

学校读者我要写书评

暂无评论

VoStress – Voice-based Detection of Acute Psychosocial Stress

VoStress – Voice-based Detection of Acute Psychosocial Stre...

引用

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Marie Oesten Robert Richer Luca Abel Nicolas Rohleder Bjoern M. Eskofier Department Artificial Intelligence in Biomedical Engineering (AIBE) Machine Learning and Data Analytics Lab (MaD Lab) Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany Chair of Health Psychology Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany

Current stress assessment methods include self-reports and biomarkers which are evaluated in often complex, laboratory procedures. Due to that investigating new indicators for acute stress is crucial for the development of automatic stress detection systems. A promising extension might be provided by investigating speech, which has been shown to be affected by negative emotions and threatening situations. For that reason, we extracted verbal acoustics from audio data collected during a study where N=21 participants underwent the Trier Social Stress Test (TSST), the gold standard for laboratory stress induction, and a stress-free control condition (friendly-TSST) while concurrently collecting cortisol via saliva samples to assess the biological response to stress. Our results show that acute stress leads to significant (p < 0.05) alterations of acoustic features. A stepwise backward multiple linear regression model explained 58.8 % of the variance of the maximum cortisol increase. In addition to that, we performed classification experiments that distinguished stress from non-stress situations with an accuracy of 80.0 ± 12.7 %. While further research is needed to validate our approach, we are convinced that the information extracted from speech can be a valuable indicator for automatic stress detection systems and can even predict the biological response to stress situations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NC-ALG: Graph-Based Active learning Under Noisy Crowd

NC-ALG: Graph-Based Active Learning Under Noisy Crowd

引用

International Conference on data Engineering

作者： Wentao Zhang Yexin Wang Zhenbang You Yang Li Gang Cao Zhi Yang Bin Cui Center for Machine Learning Research Peking University Institute of Advanced Algorithms Research Shanghai National Engineering Labratory for Big Data Analytics and Applications Key Lab of High Confidence Software Technologies Peking University Department of Data Platform TEG Tencent Inc. Beijing Academy of Artificial Intelligence Institute of Computational Social Science Peking University Qingdao

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of existing GNN-based Active learning (AL) methods, they assume that the annotated labels are always correct, which is contradictory to the error-prone labeling process in a practical crowdsourcing environment. Besides, due to this impractical assumption, existing works only focus on optimizing the node selection in AL but neglect optimizing the labeling process. Therefore, we present NC-ALG, the first GNN-based AL framework that optimizes both the node selection and node labeling process under a noisy crowd. For node selection, NC-ALG introduces a new measurement to model influence reliability and an effective influence maximization objective to select nodes. For node labeling, NC-ALG significantly reduces the labeling cost by considering the model-predicted labels and the labels of mirror nodes. To the best of our knowledge, this is the first attempt to consider GNN-based AL under the practical noisy crowd. Empirical studies on public datasets demonstrate that NC-ALG significantly outperforms existing methods in terms labeling efficiency. Notably, it only takes NC-ALG one-third of the labeling budget that the competitive baseline GRAIN needs to achieve an accuracy of 70.7 % on PubMed.

关键词： Crowdsourcing Costs Noise Predictive models Graph neural networks Labeling Noise measurement

来源：评论

学校读者我要写书评

暂无评论

XPASC: Measuring Generalization in Weak Supervision by Explainability and Association

arXiv

引用

arXiv 2022年

作者： März, Luisa Asgari, Ehsaneddin Braune, Fabienne Zimmermann, Franziska Roth, Benjamin Research Group Data Mining and Machine Learning Faculty of Computer Science University of Vienna Vienna Austria Faculty of Philological and Cultural Studies University of Vienna Vienna Austria AI Innovation & Pre-Development Data:Lab Volkswagen AG Munich Germany UniVie Docotoral School Computer Science Vienna Austria CAPE Analytics Mountain ViewCA United States

Weak supervision is leveraged in a wide range of domains and tasks due to its ability to create massive amounts of labeled data, requiring only little manual effort. Standard approaches use labeling functions to specify signals that are relevant for the labeling. It has been conjectured that weakly supervised models over-rely on those signals and as a result suffer from overfitting. To verify this assumption, we introduce a novel method, XPASC (eXPlainability-Association SCore), for measuring the generalization of a model trained with a weakly supervised dataset. Considering the occurrences of features, classes and labeling functions in a dataset, XPASC takes into account the relevance of each feature for the predictions (explainability) of the model as well as the connection of the feature with the class and the labeling function (association), respectively. The explainability is measured using occlusion in this work. The association in XPASC can be measured in two variants: XPASC-CHI SQUARE measures associations relative to their statistical significance, while XPASC-PPMI measures association strength more generally. We use XPASC to analyze KNOWMAN, an adversarial architecture intended to control the degree of generalization from the labeling functions and thus to mitigate the problem of overfitting. On one hand, we show that KNOWMAN is able to control the degree of generalization through a hyperparameter. On the other hand, results and qualitative analysis show that generalization and performance do not relate one-to-one, and that the highest degree of generalization does not necessarily imply the best performance. Therefore methods that allow for controlling the amount of generalization can achieve the right degree of benign overfitting. Our contributions in this study are i) the XPASC score to measure generalization in weakly-supervised models, ii) evaluation of XPASC across datasets and models and iii) the release of the XPASC implementation. © 2022, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Retrieval of sun-induced plant fluorescence in the O2-A absorption band from DESIS imagery

arXiv

引用

arXiv 2024年

作者： Buffat, Jim Pato, Miguel Alonso, Kevin Auer, Stefan Carmona, Emiliano Maier, Stefan Müller, Rupert Rademske, Patrick Rascher, Uwe Scharr, Hanno Forschungszentrum Jülich GmbH Institute of Bio- and Geosciences IBG-2: Plant Sciences Jülich Germany Oberpfaffenhofen Germany Largo Galileo Galilei Frascati00044 Italy Forschungszentrum Jülich GmbH Institute of Advanced Simulations IAS-8: Data Analytics and Machine Learning Jülich Germany

We provide the first method allowing to retrieve spaceborne SIF maps at 30 m ground resolution with a strong correlation (r2 = 0.6) to high-quality airborne estimates of sun-induced fluorescence (SIF). SIF estimates can provide explanatory information for many tasks related to agricultural management and physiological studies. While SIF products from airborne platforms are accurate and spatially well resolved, the data acquisition of such products remains science-oriented and limited to temporally constrained campaigns. Spaceborne SIF products on the other hand are available globally with often sufficient revisit times. However, the spatial resolution of spaceborne SIF products is too small for agricultural applications. In view of ESA’s upcoming FLEX mission we develop a method for SIF retrieval in the O2-A band of hyperspectral DESIS imagery to provide first insights for spaceborne SIF retrieval at high spatial resolution. To this end, we train a simulation-based self-supervised network with a novel perturbation based regularizer and test performance improvements under additional supervised regularization of atmospheric variable prediction. In a validation study with corresponding HyPlant derived SIF estimates at 740 nm we find that our model reaches a mean absolute difference of 0.78 mW nm−1 sr−1 m−2 © 2024, CC BY.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

VulnerVAN: A Vulnerable Network Generation Tool

VulnerVAN: A Vulnerable Network Generation Tool

引用

MILCOM, Military Communications Conference

作者： Sridhar Venkatesan Jason A. Youzwak Shridatt Sugrim Cho-Yu J. Chiang Alexander Poylisher Matthew Witkowski Gary Walther Michelle Wolberg Ritu Chadha E. Allison Newcomb Blaine Hoffman Norbou Buchler Machine Learning and Data Analytics Research Perspecta Labs Inc. Basking Ridge NJ USA Computational and Information Science Directorate U.S. CCDC Army Research Laboratory Aberdeen MD USA Human Research and Engineering Directorate U.S. CCDC Army Research Laboratory

ISBN: (数字)9781728142807

ISBN: (纸本)9781728142814

Cyber training, security testing, and research and development activities are vital to improve the security posture of a network. Currently, many institutions use cyber security testbeds to conduct these activities in an isolated virtual environment. One of the important requirements for such an environment is to provide organizers (or experimenters) with a library of vulnerable network scenarios and capabilities to mount attacks against them. However, the task of preparing a vulnerable network scenario in current testbed environments is costly in time and labor, requires significant support from the testbed staff. To this end, we present a toolset called VulnerVAN that creates a vulnerable network scenario to realize an attack sequence. In this paper, we discuss the design of VulnerVAn - our proof-of-concept implementation on CyberVAN - and present a new high-level attack specification language that enables users to chain attack steps into an attack sequence. For a given attack sequence and network scenario, VulnerVAN identifies all possible attack paths through the network that can realize the attack sequence, and provides instructions to configure machines on an attack path selected by the user. VulnerVAn also provides an attack blueprint that can guide a Red team or an automated attacker to execute the attack sequence. To demonstrate VulnerVAN's capability, we consider the use-case of a typical data exfiltration attack sequence conducted by APTs and study the performance of VulnerVAn in mapping the attack sequence to different networks.

关键词： data security Training Specification languages Virtual environments

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：