检索结果-内蒙古大学图书馆

2022 learning, Knowledge, Data, Analysis, LWDA 2022 - workshops: Special Interest Group on Knowledge Management (FGWM), Knowledge Discovery, Data Mining, and machine learning (FGKD) and Special Interest Group on Database Systems (FGDB)

作者： Seiffarth, Florian Horváth, Tamás Wrobel, Stefan Dept. of Computer Science University of Bonn Bonn Germany Fraunhofer IAIS Schloss Birlinghoven Sankt Augustin Germany Fraunhofer Center for Machine Learning Sankt Augustin Germany

We study a recently introduced adaptation of Tukey depth to graphs and discuss its algorithmic properties and potential applications to mining and learning with graphs. In particular, since it is NP-hard to compute the Tukey depth of a node, as a first contribution we provide a simple heuristic based on maximal closed set separation in graphs and show empirically on different graph datasets that its approximation error is small. Our second contribution is concerned with geodesic core-periphery decompositions of graphs. We show empirically that the geodesic core of a graph consists of those nodes that have a high Tukey depth. This information allows for a parameterized deterministic definition of the geodesic core of a graph. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 international (CC BY 4.0).

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Meta-learning for Medical Image Segmentation Uncertainty Quantification 7th

Meta-learning for Medical Image Segmentation Uncertainty Qua...

引用

7th international Brain Lesion workshop (BrainLes)

作者： Cetindag, Sabri Can Yergin, Mert Alis, Deniz Oksuz, Ilkay Istanbul Tech Univ Dept Comp Engn Istanbul Turkey Hevi AI Istanbul Turkey Acibadem Mehmet Ali Aydinlar Univ Sch Med Radiol Dept Istanbul Turkey Kings Coll London Sch Biomed Engn & Imaging Sci London England

ISBN: (纸本)9783031090028;9783031090011

Inter-rater and intra-rater variability is a major challenge in medical image segmentation. Inconsistencies of manual segmentations between different experts can challenge development of deterministic automated medical image analysis tools. QUBIQ 2021 is a challenge to enable the successful development of automated machine learning tools, when there are inconsistencies between the labels of different annotators. In this paper, we propose to use meta-learning for quantifying uncertainty in biomedical image quantification. We first train a segmentation network for each expert separately with extensive data augmentation using the nnUnet framework. Then, a meta learner model based on a conventional U-net architecture is trained using the average of all annotators as ground truth, and output of all models that have been trained for each radiologist as input. We compared our results of meta-learning with ensemble methods for various image segmentation tasks and illustrate improved performance.

关键词： Uncertainty quantification Medical image segmentation Meta-learning

来源：评论

学校读者我要写书评

暂无评论

Data Frequency Coverage Impact on AI Performance

Data Frequency Coverage Impact on AI Performance

引用

IEEE international Conference on Software Testing Verification and Validation workshop, ICSTW

作者： Erin Lanus Brian Lee Jaganmohan Chandrasekaran Laura J. Freeman M S Raunak Raghu N. Kacker D. Richard Kuhn National Security Institute Virginia Tech Arlington VA USA Sanghani Center for Artificial Intelligence & Data Analytics Virginia Tech Arlington VA USA Information Technology Lab National Institute of Standards and Technology MD USA

ISBN: (数字)9798331534677

ISBN: (纸本)9798331534684

Artificial Intelligence (AI) models use statistical learning over data to solve complex problems for which straightforward rules or algorithms may be difficult or impossible to design; however, a side effect is that models that are complex enough to sufficiently represent the function may be uninterpretable. Combinatorial testing, a black-box approach arising from software testing, has been applied to test AI models. A key differentiator between traditional software and AI is that many traditional software faults are deterministic, requiring a failureinducing combination of inputs to appear only once in the test set for it to be discovered. On the other hand, AI models learn statistically by reinforcing weights through repeated appearances in the training dataset, and the frequency of input combinations plays a significant role in influencing the model’s behavior. Thus, a single occurrence of a combination of feature values may not be sufficient to influence the model’s behavior. Consequently, measures like simple combinatorial coverage that are applicable to software testing do not capture the frequency with which interactions are covered in the AI model’s input space. This work develops methods to characterize the data frequency coverage of feature interactions in training datasets and analyze the impact of imbalance, or skew, in the combinatorial frequency coverage of the training data on model performance. We demonstrate our methods with experiments on an open-source dataset using several classical machine learning algorithms. This pilot study makes three observations: performance may increase or decrease with data skew, feature importance methods do not predict skew impact, and adding more data may not mitigate skew effects.

关键词： Training Hands machine learning algorithms statistical learning Software algorithms Training data Data models Frequency measurement Software measurement Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

FEW-SHOT learning VIA DEPENDENCY MAXIMIZATION AND INSTANCE DISCRIMINANT ANALYSIS 31

FEW-SHOT LEARNING VIA DEPENDENCY MAXIMIZATION AND INSTANCE D...

引用

IEEE 31st international workshop on machine learning for Signal Processing (MLSP)

作者： Hou, Zejiang Kung, Sun-Yuan Princeton Univ Princeton NJ 08544 USA

ISBN: (纸本)9781728163383

We study the few-shot learning (FSL) problem, where a model learns to recognize new objects with extremely few labeled training data per category. Most of previous FSL approaches resort to the meta-learning paradigm, where the model accumulates inductive bias through learning many training tasks so as to solve a new unseen few-shot task. In contrast, we propose a simple approach to exploit unlabeled data accompanying the few-shot task for improving few-shot performance. firstly, we propose a Dependency Maximization method based on the Hilbert-Schmidt norm of the cross-covariance operator, which maximizes the statistical dependency between the embedded feature of those unlabeled data and their label predictions, together with the supervised loss over the support set. We then use the obtained model to infer the pseudo-labels for those unlabeled data. Furthermore, we propose an Instance Discriminant Analysis to evaluate the credibility of each pseudo-labeled example and select the most faithful ones into an augmented support set to retrain the model as in the first step. We iterate the above process until the pseudo-labels for the unlabeled data become stable. Following the standard transductive and semi-supervised FSL setting, our experiments show that the proposed method outperforms previous state-of-the-art methods on four widely used benchmarks, including mini-ImageNet, tiered-ImageNet, CUB, and CIFARFS.

关键词： few-shot learning dependency maximization semi-supervised cross-domain

来源：评论

学校读者我要写书评

暂无评论

Blind Processing methods for Quantum Channels: Identification, Equalization and Source Separation

Blind Processing Methods for Quantum Channels: Identificatio...

引用

IEEE workshop on machine learning for Signal Processing

作者： Yannick Deville Alain Deville Université de Toulouse UPS CNRS CNE IRAP Toulouse France Aix-Marseille Université CNRS IM2NP UMR 7334 Marseille France

System identification, system inversion and its multiple-signal extension to source separation, including non-blind and blind (i.e. unsupervised) configurations, are major topics in classical, i.e. nonquantum, signal processing. Their application fields especially include communications, where they are often referred to as (possibly blind and MIMO) channel identification / estimation and channel equalization. Some of their configurations have also been extended to quantum channels. In this paper, we focus on such channels and on the most challenging configurations, namely blind and multiplequbit ones, hence with main emphasis on source separation. In this framework, two classes of methods were previously proposed for two-qubit configurations and a specific type of channels. We here first define their extensions to any number of qubits and general channels. For that configuration too, we then propose a third class of methods and we analyze its relationships with the previous two. This leads us to provide new general insight into the connections between the unentanglement of a pure quantum state and the statistical independence of associated measurement components.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel ensemble-based statistical approach to estimate daily wildfire-specific PM2.5 in California (2006-2020)

引用

ENVIRONMENT international 2023年 171卷 107719页

作者： Aguilera, Rosana Luo, Nana Basu, Rupa Wu, Jun Clemesha, Rachel Gershunov, Alexander Benmarhnia, Tarik Univ Calif San Diego Scripps Inst Oceanog La Jolla CA USA Calif Environm Protect Agcy Off Environm Hlth Hazard Assessment Oakland CA USA Univ Calif Irvine Dept Environm & Occupat Hlth Program Publ Hlth Irvine CA USA Univ Calif San Diego Scripps Inst Oceanog 9500 Gilman Dr 0230 La Jolla CA 92093 USA

Though fine particulate matter (PM2.5) has decreased in the United States (U.S.) in the past two decades, the increasing frequency, duration, and severity of wildfires significantly (though episodically) impairs air quality in wildfire-prone regions and beyond. Increasing PM2.5 concentrations derived from wildfire smoke and associated impacts on public health require dedicated epidemiological studies. Main sources of PM2.5 data are provided by government-operated monitors sparsely located across U.S., leaving several regions and potentially vulnerable populations unmonitored. Current approaches to estimate PM2.5 concentrations in unmonitored areas often rely on big data, such as satellite-derived aerosol properties and meteorological variables, apply computationally -intensive deterministic modeling, and do not distinguish wildfire-specific PM2.5 from other sources of emis-sions such as traffic and industrial sources. Furthermore, modelling wildfire-specific PM2.5 presents a challenge since measurements of the smoke contribution to PM2.5 pollution are not available. Here, we aim to use statistical methods to isolate wildfire-specific PM2.5 from other sources of emissions. Our study presents an ensemble model that optimally combines multiple machine learning algorithms (including gradient boosting machine, random forest and deep learning), and a large set of explanatory variables to, first, estimate daily PM2.5 concentrations at the ZIP code level, a relevant spatiotemporal resolution for epidemiological studies. Subsequently, we propose a novel implementation of an imputation approach to estimate the wildfire-specific PM2.5 concentrations that could be applied geographical regions in the US or worldwide. Our ensemble model achieved comparable results to previous machine learning studies for PM2.5 prediction while avoiding processing larger, computationally intensive datasets. Our study is the first to apply a suite of statistical models using readily available datas

关键词： Air pollution Wildfire PM2 5 Human health machine learning

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Multiple Sclerosis Using Genomic Expression

Automatic Detection of Multiple Sclerosis Using Genomic Expr...

引用

workshop held at the 12th international Conference on Model and Data Engineering, MEDI 2023

作者： Ahmed, Abdullah DH. Hadhoud, Marwa M. A. Ghoneim, Vidan F. Biomedical Engineering Department Faculty of Engineering Helwan University Cairo Egypt

ISBN: (纸本)9783031557286

This study leverages microarray data together with statistical and machine learning techniques to investigate the best set of biomarkers in diagnosing multiple sclerosis (MS). In this work to build an automated system to detect MS two phases are approached. The first phase which is of emphasis is to reduce the dimension of features space and select the most discriminative set of features;biomarkers for MS diagnosis. Principal Component Analysis (PCA) was used as a dimension reduction method. Meanwhile, various feature selection methods were used (Fisher score, chi-square, relief, and MRMR). The second phase of this work is the classification phase, where the output of the first phase were assessed. This phase comprises three different classifiers: LDA, SVM, and KNN. Relief feature selection method achieved 100% accuracy with KNN, using 38 differentially expressed genes (DEGs). Out of this set of these DEGs, Key biomarker genes were identified by studying the gene annotation for all. The genes MIF, PTGES3, CYLD, and JAK1 are realized to be associated with immune and neurological functions. Which is of great relevance to MS. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Dimension Reduction machine learning Microarray Technology statistical techniques

来源：评论

学校读者我要写书评

暂无评论

Balancing Effectiveness and Flakiness of Non-deterministic machine learning Tests

Balancing Effectiveness and Flakiness of Non-Deterministic M...

引用

international Conference on Software Engineering (ICSE)

作者： Chunqiu Steven Xia Saikat Dutta Sasa Misailovic Darko Marinov Lingming Zhang University of Illinois Urbana-Champaign

Testing machine learning (ML) projects is challenging due to inherent non-determinism of various ML algorithms and the lack of reliable ways to compute reference results. Developers typically rely on their intuition when writing tests to check whether ML algorithms produce accurate results. However, this approach leads to conservative choices in selecting assertion bounds for comparing actual and expected results in test assertions. Because developers want to avoid false positive failures in tests, they often set the bounds to be too loose, potentially leading to missing critical bugs. We present FASER - the first systematic approach for balancing the trade-off between the fault-detection effectiveness and flakiness of non-deterministic tests by computing optimal assertion bounds. FASER frames this trade-off as an optimization problem between these competing objectives by varying the assertion bound. FASER leverages 1) statistical methods to estimate the flakiness rate, and 2) mutation testing to estimate the fault-detection effectiveness. We evaluate FASER on 87 non-deterministic tests collected from 22 popular ML projects. FASER finds that 23 out of 87 studied tests have conservative bounds and proposes tighter assertion bounds that maximizes the fault-detection effectiveness of the tests while limiting flakiness. We have sent 19 pull requests to developers, each fixing one test, out of which 14 pull requests have already been accepted.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Isolated Sign Recognition using ASL Datasets with Consistent Text-based Gloss Labeling and Curriculum learning 7

Isolated Sign Recognition using ASL Datasets with Consistent...

引用

7th workshop on Sign Language Translation and Avatar Technology: The Junction of the Visual and the Textual Challenges and Perspectives, SLTAT 2022

作者： Dafnis, Konstantinos M. Chroni, Evgenia Neidle, Carol Metaxas, Dimitris N. Rutgers University 110 Frelinghuysen Road PiscatawayNJ08854 United States Boston University Boston University Linguistics 621 Commonwealth Ave. BostonMA02215 United States

ISBN: (纸本)9791095546825

We present a new approach for isolated sign recognition, which combines a spatial-temporal Graph Convolution Network (GCN) architecture for modeling human skeleton keypoints with late fusion of both the forward and backward video streams, and we explore the use of curriculum learning. We employ a type of curriculum learning that dynamically estimates, during training, the order of difficulty of each input video for sign recognition;this involves learning a new family of data parameters that are dynamically updated during training. The research makes use of a large combined video dataset for American Sign Language (ASL), including data from both the American Sign Language Lexicon Video Dataset (ASLLVD) and the Word-Level American Sign Language (WLASL) dataset, with modified gloss labeling of the latter-to ensure 1-1 correspondence between gloss labels and distinct sign productions, as well as consistency in gloss labeling across the two datasets. This is the first time that these two datasets have been used in combination for isolated sign recognition research. We also compare the sign recognition performance on several different subsets of the combined dataset, varying in, e.g., the minimum number of samples per sign (and therefore also in the total number of sign classes and video examples). © European Language Resources Association (ELRA), licensed under CC-BY-NC 4.0.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

CML-IOT 2020: The Second workshop on Continual and Multimodal learning for Internet of Things 20

CML-IOT 2020: The Second Workshop on Continual and Multimoda...

引用

ACM international Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) / ACM international Symposium on Wearable Computers (ISWC)

作者： Xu, Susu Pan, Shijia Yu, Tong Qualcomm AI Res San Diego CA 92121 USA Univ Calif Merced CA USA Samsung Res Amer Mountain View CA USA

ISBN: (纸本)9781450380768

With the deployment of Internet of Things (IoT), large amount of sensors are connected into the Internet, providing large-amount, streaming, and multimodal data. These data have distinct statistical characteristics over time and sensing modalities, which are hardly captured by traditional learning methods. Continual and multimodal learning allows integration, adaptation, and generalization of the knowledge learned from experiential data collected with heterogeneity to new situations. Therefore, continual and multimodal learning is an important step to enable efficient ubiquitous computing on IoT devices. The major challenges to combine continual learning and multimodal learning with real-world data include 1) how to fuse and transfer knowledge between the multimodal data under constrained computational resources, 2) how to learn continually despite the missing, imbalanced or noisy data under constrained computational resources, 3) how to effectively reserve privacy and retain security when learning knowledge from streaming and multimodal data collected by multiple stakeholders, and 4) how to develop large-scale distributed learning systems to efficiently learn from continual and multimodal data. We organize this workshop to bring people working on different disciplines together to tackle these challenges in this topic. This workshop aims to explore the intersection and combination of continual machine learning and multimodal modeling with applications in the Internet of Things. The workshop welcomes works addressing these issues in different applications/domains as well as algorithmic and systematic approaches to leverage continual learning on multimodal data. We further seek to develop a community that systematically handles the streaming multimodal data widely available in real-world ubiquitous computing systems. In 2019, we held the first workshop on Continual and Multimodal learning for Internet of Things (https://***/) with Ubicomp 2019, London

关键词： Ubiquitous Computing Internet of Things Multimodal learning Continual learning

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：