检索结果-内蒙古大学图书馆

Laplacian-Based Dimensionality Reduction Including Spectral Clustering, Laplacian Eigenmap, Locality Preserving Projection, Graph Embedding, and Diffusion Map: Tutorial and Survey

学校读者我要写书评

暂无评论

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 for nonlinear dimensionality and feature extraction methods which are based on the Laplacian of graph of data. We first introduce adjacency matrix, definition of Laplacian matrix, and the interpretation of Laplacian. Then, we cover the cuts of graph and spectral clustering which applies clustering in a subspace of data. Different optimization variants of Laplacian eigenmap and its out-of-sample extension are explained. Thereafter, we introduce the locality preserving projection and its kernel variant as linear special cases of Laplacian eigenmap. Versions of graph embedding are then explained which are generalized versions of Laplacian eigenmap and locality preserving projection. Finally, diffusion map is introduced which is a method based on Laplacian of data and random walks on the data graph. Copyright © 2021, The Authors. All rights reserved.

关键词： Surveys

Unified Framework for Spectral Dimensionality Reduction, Maximum Variance Unfolding, and Kernel learning By Semidefinite Programming: Tutorial and Survey

学校读者我要写书评

暂无评论

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 unification of spectral dimensionality reduction methods, kernel learning by Semidefinite Programming (SDP), Maximum Variance Unfolding (MVU) or Semidefinite Embedding (SDE), and its variants. We first explain how the spectral dimensionality reduction methods can be unified as kernel Principal Component Analysis (PCA) with different kernels. This unification can be interpreted as eigenfunction learning or representation of kernel in terms of distance matrix. Then, since the spectral methods are unified as kernel PCA, we say let us learn the best kernel for unfolding the manifold of data to its maximum variance. We first briefly introduce kernel learning by SDP for the transduction task. Then, we explain MVU in detail. Various versions of supervised MVU using nearest neighbors graph, by class-wise unfolding, by Fisher criterion, and by colored MVU are explained. We also explain out-of-sample extension of MVU using eigenfunctions and kernel mapping. Finally, we introduce other variants of MVU including action respecting embedding, relaxed MVU, and landmark MVU for big data. Copyright © 2021, The Authors. All rights reserved.

关键词： Surveys

Could machine learning be used to approximate optimal building retrofit solutions with the use of easily accessible building data? 32

学校读者我要写书评

暂无评论

Could machine learning be used to approximate optimal buildi...

32nd International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems, ECOS 2019

作者： Thrampoulidis, Emmanouil Mavromatidis, Georgios Lucchi, Aurelien Orehounig, Kristina Laboratory for Urban Energy Systems Empa Duebendorf Switzerland ETH Zurich Switzerland Institute for Machine Learning Data analytics lab ETH Zurich Switzerland

ISBN: (纸本)9788361506515

Building retrofit is of greatest importance to reduce the environmental footprint of the building stock. It typically refers to two types of interventions: the first pertaining to interventions on the building envelope, for instance by enhancing the thermal insulation of a building’s walls, and the second to energy system replacements. The latter includes not only the installation of a more efficient heating system, with the necessary capacity to meet the building's heat demands, but also the integration of renewable energy technologies and energy storage. Thus, there is a huge array of retrofit measure combinations to select from with different economic and environmental impacts. Even though there are tools and methodologies to handle the complex problem of deriving optimal retrofit solutions, they typically require increased level of expertise and highly heterogeneous building data, which are usually not available or challenging to obtain. As a result, building owners can find themselves in a quandary about how to further proceed with retrofitting their buildings. In this paper, we answer the question whether a machine-learning algorithm could be used as a surrogate model that can: (a) mimic the functionality of the retrofit process, and (b) derive near-optimal solutions with the use of building features that can be easily extracted, such as the building's ground floor area or age. To answer this question an artificial neural network-based model is trained with data collected from the case study of the city of Zurich. Results show that the proposed approach can approximate very well some dimensions of the building retrofit, such as the retrofit costs (R2 ≅ 0.971) and the energy system selection (f1 score ≅ 0.894), while for others, such as the electricity storage capacity (R2 ≅ 0.505), there is still room for improvement. Such surrogate retrofit models can be more easily shared with building owners, and can contribute towards accelerating the adoption of retrofit

关键词： Multiobjective optimization

Problems and Prospectives of Big data Storage and Processing Standartization

学校读者我要写书评

暂无评论

Problems and Prospectives of Big Data Storage and Processing...

IEEE Region 8 International Conference on Computational Technologies in Electrical and Electronics Engineering, SIBIRCON

作者： Evgeniy N. Pavlovskiy Stream Data Analytics and Machine Learning lab Novosibirsk State University Novosibirsk Russia

In the paper, we analyze the problem of standardization in the domain of storage and processing of big data in the application to the Internet of things. We highlight the underlying problems of big data; analyze the scientific, technological and economic barriers to the development of big data. We offer perspective research directions in the domain of development of standards of data representation.

关键词： Big data Internet of Things Standards Task analysis Neural networks data structures

Reducing over-smoothness in speech synthesis using Generative Adversarial Networks

学校读者我要写书评

暂无评论

Reducing over-smoothness in speech synthesis using Generativ...

IEEE Region 8 International Conference on Computational Technologies in Electrical and Electronics Engineering, SIBIRCON

作者： Leyuan Sheng Evgeniy N. Pavlovskiy Novosibirsk State University Novosibirsk Russia Stream Data Analytics and Machine Learning laboratory Novosibirsk State University Novosibirsk Russia

Speech synthesis is widely used in many practical applications. In recent years, speech synthesis technology has developed rapidly. However, one of the reasons why synthetic speech is unnatural is that it often has over-smoothness. In order to improve the naturalness of synthetic speech, we first extract the mel-spectrogram of speech and convert it into a real image, then take the over-smooth mel-spectrogram image as input, and use image-to-image translation Generative Adversarial Networks(GANs) framework to generate a more realistic mel-spectrogram. Finally, the results show that this method greatly reduces the over-smoothness of synthesized speech and is more close to the mel-spectrogram of real speech.

关键词： Generative adversarial networks Speech synthesis Spectrogram Generators Hidden Markov models Training

ICDAR 2021 competition on on-line signature verification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Tolosana, Ruben Vera-Rodriguez, Ruben Gonzalez-Garcia, Carlos Fierrez, Julian Rengifo, Santiago Morales, Aythami Ortega-Garcia, Javier Ruiz-Garcia, Juan Carlos Romero-Tapiador, Sergio Jiang, Jiajia Lai, Songxuan Jin, Lianwen Zhu, Yecheng Galbally, Javier Diaz, Moises Ferrer, Miguel Angel Gomez-Barrero, Marta Hodashinsky, Ilya Sarin, Konstantin Slezkin, Artem Bardamova, Marina Svetlakov, Mikhail Saleem, Mohammad Szücs, Cintia Lia Kovari, Bence Pulsmeyer, Falk Wehbi, Mohamad Zanca, Dario Ahmad, Sumaiya Mishra, Sarthak Jabin, Suraiya Biometrics and Data Pattern Analytics Lab UAM Spain South China University of Technology China Guangdong Artificial Intelligence and Digital Economy Laboratory China European Commission Joint Research Centre Italy Universidad del Atlantico Medio Spain Universidad de las Palmas de Gran Canaria Spain Hochschule Ansbach Germany Tomsk State University of Control Systems and Radioelectronics Russia Budapest University of Technology and Economics Hungary Machine Learning and Data Analytics Lab FAU Germany Jamia Millia Islamia India

This paper describes the experimental framework and results of the ICDAR 2021 Competition on On-Line Signature Verification (SVC 2021). The goal of SVC 2021 is to evaluate the limits of on-line signature verification systems on popular scenarios (office/mobile) and writing inputs (stylus/finger) through large-scale public databases. Three different tasks are considered in the competition, simulating realistic scenarios as both random and skilled forgeries are simultaneously considered on each task. The results obtained in SVC 2021 prove the high potential of deep learning methods. In particular, the best on-line signature verification system of SVC 2021 obtained Equal Error Rate (EER) values of 3.33% (Task 1), 7.41% (Task 2), and 6.04% (Task 3). SVC 2021 will be established as an on-going competition12, where researchers can easily benchmark their systems against the state of the art in an open common platform using large-scale public databases such as DeepSignDB13 and SVC2021_EvalDB14, and standard experimental protocols. © 2021, CC BY-NC-ND.

关键词： Deep learning

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

学校读者我要写书评

暂无评论

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

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

Simple unsupervised keyphrase extraction using sentence embeddings 22

学校读者我要写书评

暂无评论

Simple unsupervised keyphrase extraction using sentence embe...

22nd Conference on Computational Natural Language learning, CoNLL 2018

作者： Bennani-Smires, Kamil Musat, Claudiu Hossmann, Andreaa Baeriswyl, Michael Jaggi, Martin Data Analytics and AI Swisscom AG Switzerland Machine Learning and Optimization Laboratory EPFL Switzerland

ISBN: (纸本)9781948087728

Keyphrase extraction is the task of automatically selecting a small set of phrases that best describe a given free text document. Supervised keyphrase extraction requires large amounts of labeled training data and generalizes very poorly outside the domain of the training data. At the same time, unsupervised systems have poor accuracy, and often do not generalize well, as they require the input document to belong to a larger corpus also given as input. Addressing these drawbacks, in this paper, we tackle keyphrase extraction from single documents with EmbedRank: a novel unsupervised method, that leverages sentence embeddings. EmbedRank achieves higher F-scores than graph-based state of the art systems on standard datasets and is suitable for real-time processing of large amounts of Web data. With EmbedRank, we also explicitly increase coverage and diversity among the selected keyphrases by introducing an embedding-based maximal marginal relevance (MMR) for new phrases. A user study including over 200 votes showed that, although reducing the phrases’ semantic overlap leads to no gains in F-score, our high diversity selection is preferred by humans. © 2018 Association for Computational Linguistics.

关键词： Embeddings

Stochastic Neighbor Embedding with Gaussian and Student-t Distributions: Tutorial and Survey

学校读者我要写书评

暂无评论

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

Stochastic Neighbor Embedding (SNE) is a manifold learning and dimensionality reduction method with a probabilistic approach. In SNE, every point is consider to be the neighbor of all other points with some probability and this probability is tried to be preserved in the embedding space. SNE considers Gaussian distribution for the probability in both the input and embedding spaces. However, t-SNE uses the Student-t and Gaussian distributions in these spaces, respectively. In this tutorial and survey paper, we explain SNE, symmetric SNE, t-SNE (or Cauchy-SNE), and t-SNE with general degrees of freedom. We also cover the out-of-sample extension and acceleration for these methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Gaussian distribution