检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Ghojogh, Benyamin Ghodsi, Ali Karray, Fakhri Crowley, Mark Department of Electrical and Computer Engineering Machine Learning Laboratory University of Waterloo WaterlooON Canada Department of Statistics and Actuarial Science David R. Cheriton School of Computer Science Data Analytics Laboratory University of Waterloo WaterlooON Canada Department of Electrical and Computer Engineering Centre for Pattern Analysis and Machine Intelligence University of Waterloo WaterlooON Canada

This is a tutorial and survey paper on factor analysis, probabilistic Principal Component analysis (PCA), variational inference, and Variational Autoencoder (VAE). These methods, which are tightly related, are dimensionality reduction and generative models. They assume that every data point is generated from or caused by a lowdimensional latent factor. By learning the parameters of distribution of latent space, the corresponding low-dimensional factors are found for the sake of dimensionality reduction. For their stochastic and generative behaviour, these models can also be used for generation of new data points in the data space. In this paper, we first start with variational inference where we derive the Evidence Lower Bound (ELBO) and Expectation Maximization (EM) for learning the parameters. Then, we introduce factor analysis, derive its joint and marginal distributions, and work out its EM steps. Probabilistic PCA is then explained, as a special case of factor analysis, and its closed-form solutions are derived. Finally, VAE is explained where the encoder, decoder and sampling from the latent space are introduced. Training VAE using both EM and backpropagation are explained. Copyright © 2021, The Authors. All rights reserved.

关键词： Maximum principle

来源：评论

学校读者我要写书评

暂无评论

Multidimensional scaling, Sammon mapping, and Isomap: Tutorial and survey

arXiv

引用

arXiv 2020年

Multidimensional Scaling (MDS) is one of the first fundamental manifold learning methods. It can be categorized into several methods, i.e., classical MDS, kernel classical MDS, metric MDS, and non-metric MDS. Sammon mapping and Isomap can be considered as special cases of metric MDS and kernel classical MDS, respectively. In this tutorial and survey paper, we review the theory of MDS, Sammon mapping, and Isomap in detail. We explain all the mentioned categories of MDS. Then, Sammon mapping, Isomap, and kernel Isomap are explained. Out-of-sample embedding for MDS and Isomap using eigenfunctions and kernel mapping are introduced. Then, Nystrom approximation and its use in landmark MDS and landmark Isomap are introduced for big data embedding. We also provide some simulations for illustrating the embedding by these methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Locally linear embedding and its variants: Tutorial and survey

arXiv

引用

arXiv 2020年

作者： Ghojogh, Benyamin Ghodsi, Ali Karray, Fakhri Crowley, Mark Department of Electrical and Computer Engineering Machine Learning Laboratory University of Waterloo WaterlooON Canada Department of Statistics and Actuarial Science & David R. Cheriton School of Computer Science Data Analytics Laboratory University of Waterloo WaterlooON Canada Department of Electrical and Computer Engineering Centre for Pattern Analysis and Machine Intelligence University of Waterloo WaterlooON Canada

This is a tutorial and survey paper for Locally Linear Embedding (LLE) and its variants. The idea of LLE is fitting the local structure of manifold in the embedding space. In this paper, we first cover LLE, kernel LLE, inverse LLE, and feature fusion with LLE. Then, we cover out-of-sample embedding using linear reconstruction, eigenfunctions, and kernel mapping. Incremental LLE is explained for embedding streaming data. Landmark LLE methods using the Nystrom approximation and locally linear landmarks are explained for big data embedding. We introduce the methods for parameter selection of number of neighbors using residual variance, Procrustes statistics, preservation neighborhood error, and local neighborhood selection. Afterwards, Supervised LLE (SLLE), enhanced SLLE, SLLE projection, probabilistic SLLE, supervised guided LLE (using Hilbert-Schmidt independence criterion), and semi-supervised LLE are explained for supervised and semi-supervised embedding. Robust LLE methods using least squares problem and penalty functions are also introduced for embedding in the presence of outliers and noise. Then, we introduce fusion of LLE with other manifold learning methods including Isomap (i.e., ISOLLE), principal component analysis, Fisher discriminant analysis, discriminant LLE, and Isotop. Finally, we explain weighted LLE in which the distances, reconstruction weights, or the embeddings are adjusted for better embedding;we cover weighted LLE for deformed distributed data, weighted LLE using probability of occurrence, SLLE by adjusting weights, modified LLE, and iterative LLE. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Spectral, Probabilistic, and Deep Metric learning: Tutorial and Survey

arXiv

引用

arXiv 2022年

This is a tutorial and survey paper on metric learning. Algorithms are divided into spectral, probabilistic, and deep metric learning. We first start with the definition of distance metric, Mahalanobis distance, and generalized Mahalanobis distance. In spectral methods, we start with methods using scatters of data, including the first spectral metric learning, relevant methods to Fisher discriminant analysis, Relevant Component analysis (RCA), Discriminant Component analysis (DCA), and the Fisher-HSIC method. Then, large-margin metric learning, imbalanced metric learning, locally linear metric adaptation, and adversarial metric learning are covered. We also explain several kernel spectral methods for metric learning in the feature space. We also introduce geometric metric learning methods on the Riemannian manifolds. In probabilistic methods, we start with collapsing classes in both input and feature spaces and then explain the neighborhood component analysis methods, Bayesian metric learning, information theoretic methods, and empirical risk minimization in metric learning. In deep learning methods, we first introduce reconstruction autoencoders and supervised loss functions for metric learning. Then, Siamese networks and its various loss functions, triplet mining, and triplet sampling are explained. Deep discriminant analysis methods, based on Fisher discriminant analysis, are also reviewed. Finally, we introduce multi-modal deep metric learning, geometric metric learning by neural networks, and few-shot metric learning. Copyright © 2022, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Support System for Choosing an Individual Educational Trajectory at Vasyl’ Stus Donetsk National University

Support System for Choosing an Individual Educational Trajec...

引用

International Scientific-Practical Conference Problems of Infocommunications Science and Technology

作者： Pavlo Chaikovskyi Oleh Vietrov Artem Baiev Yana Teletska Maksym Strutovskyi Educational and Practical Laboratory of Information Security Vasyl' Stus Donetsk National University Vinnytsia Ukraine Department of Applied Mathematics Vasyl' Stus Donetsk National University Vinnytsia Ukraine Interdepartmental Laboratory of Machine Learning and Intelligent Data Analysis Vasyl' Stus Donetsk National University Vinnytsia Ukraine

Members of Interdepartmental laboratory of machine learning and intelligent data analysis Vasyl' Stus Donetsk national university are developing a software that helps students choose minors and other additional subjects, as well as proper tooling for teachers and staff. Described process of development, its specifics and addressed direction and possible technologies that may serve the scaling of the system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Developing a Strategy for the Digital Transformation of an Educational Organization Based on Cloud Technology

Developing a Strategy for the Digital Transformation of an E...

引用

Information Systems Theory and Practice (ISTP), Seminar on

作者： Alexander V. Olifirov Krystina A. Makoveichuk Sergei A. Petrenko Department of Economics and Finance V.I Vernadsky Crimean Federal University Yalta Russia Department of Data Analysis and Machine Learning Financial University under the Government of the Russian Federation Moscow Russia Department of Information Security Saint Petersburg Electrotechnical University “LETI” Saint Petersburg Russia

The article examines the theory and practical implementation of a digital transformation strategy. It was found that the main stages of formation of the digital transformation strategy of the organization are determined by: the use of digital services, individualization of a particular instance of the service, the involvement of the end consumer in the process, customer support throughout the life cycle of the service. Six main stages of implementation of the strategy of digital transformation of the educational process based on the use of cloud technology were formed. Opportunities and threats to the use of cloud technology in the educational space were identified. The experience of using the cloud service “1C: Fresh” in the formation of more than one hundred information bases in the training of specialists in the field of economics and finance was obtained. It was shown that the use of cloud technologies with the provision of students with access to the cloud service of 1C in the educational space of the university simulates the production activities of future specialists in real time. In this case, up-to-date and daily updated for the current legislation programs are used, functionality, cybersecurity and a high degree of data security are maintained at the proper level.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Portable tracker for neurophysiological research of sport shooting

Portable tracker for neurophysiological research of sport sh...

引用

Saratov Fall Meeting 2021: Computational Biophysics and Nanobiophotonics

作者： Antipov, V.M. Badarin, A.A. Grubov, V.V. Kazantsev, V.B. Hramov, A.E. Neuroscience and Cognivite Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Universitetskaya Str. 1 Innopolis 420500 Russia Laboratory of Advanced Methods for High-Dimensional Data Analysis Lobachevsky State University of Nizhni Novgorod 23 Gagarin ave. Nizhny Novgorod603950 Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University A. Nevskogo ul. 14 Kaliningrad236016 Russia Neurotechnology Deparment Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod603022 Russia

ISBN: (数字)9781510653702

ISBN: (纸本)9781510653696

In this work we present the development process of a wireless portable module. It is developed to record various characteristics during sport shooting, such as automatic detection of the moment of shot and barrel movement during aiming, taking into account the peculiarities of its use in neurophysiological research. We propose an approach allowing to synchronize devices in a wireless local network with high accuracy (synchronization accuracy was 2 ms), as well as a method of logging the recorded data at a sampling rate of up to 2 kHz on an onboard flash drive. © 2022 SPIE.

关键词： Neurophysiology

来源：评论

学校读者我要写书评

暂无评论

RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement

RecycleNet: Latent Feature Recycling Leads to Iterative Deci...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Gregor Koehler Tassilo Wald Constantin Ulrich David Zimmerer Paul F. Jaeger Jörg K. H. Franke Simon Kohl Fabian Isensee Klaus H. Maier-Hein Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Information and Data Science School for Health Karlsruhe/Heidelberg Germany Helmholtz Imaging DKFZ National Center for Tumor Diseases (NCT) NCT Heidelberg a Partnership Between DKFZ University Medical Center Heidelberg Interactive Machine Learning Group DKFZ Machine Learning Lab University of Freiburg Freiburg Germany Latent Labs (***) London UK Applied Computer Vision Lab DKFZ Pattern Analysis and Learning Group Heidelberg University Hospital Heidelberg Germany

Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we can not only form a decision on the spot, but also ponder, revisiting an initial guess from different angles, distilling relevant information, arriving at a better decision. Here, we propose RecycleNet, a latent feature recycling method, instilling the pondering capability for neural networks to refine initial decisions over a number of recycling steps, where outputs are fed back into earlier network layers in an iterative fashion. This approach makes minimal assumptions about the neural network architecture and thus can be implemented in a wide variety of contexts. Using medical image segmentation as the evaluation environment, we show that latent feature recycling enables the network to iteratively refine initial predictions even beyond the iterations seen during training, converging towards an improved decision. We evaluate this across a variety of segmentation benchmarks and show consistent improvements even compared with top-performing segmentation methods. This allows trading increased computation time for improved performance, which can be beneficial, especially for safety-critical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using ERPs for assessing the (sub) conscious perception of noise

Using ERPs for assessing the (sub) conscious perception of n...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Anne K. Porbadnigk Jan-N. Antons Benjamin Blankertz Matthias S. Treder Robert Schleicher Sebastian Möller Gabriel Curio Machine Learning Laboratory Berlin Institute of Technology Berlin Germany Quality and Usability Lab Telekom Laboratories Berlin Germany Intelligent Data Analysis Group Fraunhofer FIRST Berlin Germany Department of Neurology and Clinical Neurophysiology Charite Berlin Germany Department of Neurology Clinical Neurophysiology Charite Berlin Germany

In this paper, we investigate the use of event-related potentials (ERPs) as a quantitative measure for quality assessment of disturbed audio signals. For this purpose, we ran an EEG study (N=11) using an oddball paradigm, during which subjects were presented with the phoneme /a/, superimposed with varying degrees of signal-correlated noise. Based on this data set, we address the question to which degree the degradation of the auditory stimuli is reflected on a neural level, even if the disturbance is below the threshold of conscious perception. For those stimuli that are consciously recognized as being disturbed, we suggest the use of the amplitude and latency of the P300 component for assessing the level of disturbance. For disturbed stimuli for which the noise is not perceived consciously, we show for two subjects that a classifier based on shrinkage LDA can be applied successfully to single out stimuli, for which the noise was presumably processed subconsciously.

关键词： Noise Presses Electroencephalography Training Degradation Noise measurement Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Correction to: Potential cyber threats of adversarial attacks on autonomous driving models

引用

Journal of Computer Virology and Hacking Techniques 2023年第2期20卷 315-315页

作者： Boltachev, Eldar Department of Data Analysis and Machine Learning Financial University Under the Government of the Russian Federation Moscow Russia

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：