检索结果-内蒙古大学图书馆

Mastering TensorFlow 1.x: Advanced machine learning and deep learning concepts using TensorFlow 1.x and Keras

2018年

作者： Armando Fandango

ISBN: (数字)9781788297004

ISBN: (纸本)9781788292061

Build, scale, and deploy deep neural network models using the star libraries in Python About This Book • Delve into advanced machine learning and deep learning use cases using Tensorflow and Keras • Build, deploy, and scale end-to-end deep neural network models in a production environment • Learn to deploy TensorFlow on mobile, and distributed TensorFlow on GPU, Clusters, and Kubernetes Who This Book Is For This book is for data scientists, machine learning engineers, artificial intelligence engineers, and for all TensorFlow users who wish to upgrade their TensorFlow knowledge and work on various machine learning and deep learning problems. If you are looking for an easy-to-follow guide that underlines the intricacies and complex use cases of machine learning, you will find this book extremely useful. Some basic understanding of TensorFlow is required to get the most out of the book. What You Will Learn • Master advanced concepts of deep learning such as transfer learning, reinforcement learning, generative models and more, using TensorFlow and Keras • Perform supervised (classification and regression) and unsupervised (clustering) learning to solve machine learning tasks • Build end-to-end deep learning (CNN, RNN, and autoencoders) models with TensorFlow • Scale and deploy production models with distributed and high-performance computing on GPU and clusters • Build TensorFlow models to work with multilayer perceptrons using Keras, TFLearn, and R • Learn the functionalities of smart apps by building and deploying TensorFlow models on iOS and Android devices • Supercharge TensorFlow with distributed training and deployment on Kubernetes and TensorFlow Clusters In Detail TensorFlow is the most popular numerical computation library built from the ground up for distributed, cloud, and mobile environments. TensorFlow represents the data as tensors and the computation as graphs. This book is a comprehensive guide that lets you explore the advanced features of T

关键词： TensorFlow 1.x keras CNN RNN NLP machine learning deep learning Generative Network GAN Reinforcement Learning Ensemble Learning Transfer Learning TensorBoard autoencoder LSTM GRU TFLearn

来源：评论

学校读者我要写书评

暂无评论

SEGMENTAL AUDIO WORD2VEC: REPRESENTING UTTERANCES AS SEQUENCES OF VECTORS WITH APPLICATIONS IN SPOKEN TERM DETECTION

SEGMENTAL AUDIO WORD2VEC: REPRESENTING UTTERANCES AS SEQUENC...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Wang, Yu-Hsuan Lee, Hung-yi Lee, Lin-shan Natl Taiwan Univ Coll Elect Engn & Comp Sci Taipei Taiwan

ISBN: (纸本)9781538646588

While Word2Vec represents words (in text) as vectors carrying semantic information, audio Word2Vec was shown to be able to represent signal segments of spoken words as vectors carrying phonetic structure information. Audio Word2Vec can be trained in an unsupervised way from an unlabeled corpus, except the word boundaries are needed. In this paper, we extend audio Word2Vec from word-level to utterance-level by proposing a new segmental audio Word2Vec, in which unsupervised spoken word boundary segmentation and audio Word2Vec are jointly learned and mutually enhanced, so an utterance can be directly represented as a sequence of vectors carrying phonetic structure information. This is achieved by a segmental sequence-to-sequence autoencoder (SSAE), in which a segmentation gate trained with reinforcement learning is inserted in the encoder. Experiments on English, Czech, French and German show very good performance in both unsupervised spoken word segmentation and spoken term detection applications (significantly better than frame-based DTW).

关键词： recurrent neural network autoencoder reinforcement learning policy gradient

来源：评论

学校读者我要写书评

暂无评论

RELEVANCE FEEDBACK AND SPARSITY HANDLING METHODS FOR TEMPORAL DATA

RELEVANCE FEEDBACK AND SPARSITY HANDLING METHODS FOR TEMPORA...

引用

作者： Bahaeddin ERAVCI Bilkent University

学位级别：博士

Data with temporal ordering arises in many natural and digital processes with an increasing importance and immense number of applications. This study provides solutions to data mining problems in analyzing time series both in standalone and sparse networked cases. We initially develop a methodology for browsing time series repositories by forming new time series queries based on user annotations. The result set for each query is formed using diverse selection methods to increase the effectiveness of the relevance feedback (RF) mechanism. In addition to RF, a unique aspect of time series data is considered and representation feedback methods are proposed to converge to the outperforming representation type among various transformations based on user annotations as opposed to manual selection. These methods are based on partitioning of the result set according to representation performance and a weighting approach which amplifies different features from multiple representations. We subsequently propose the utilization of autoencoders to summarize the time series into a data-aware sparse representation to both decrease computation load and increase the accuracy. Experiments on a large variety of real data sets prove that the proposed methods improve the accuracy significantly and data-aware representations have recorded similar performances while reducing the data and computational load. As a more demanding case, the time series dataset may be incomplete needing interpolation approaches to apply data mining techniques. In this regard, we analyze a sparse time series data with an underlying time varying network. We develop a methodology to generate a road network time series dataset using noisy and sparse vehicle trajectories and evaluate the result using time varying shortest path solutions.

关键词： Time Series Relevance Feedback Diversity autoencoder Sparsity Time-Varying Graphs

来源：评论

学校读者我要写书评

暂无评论

Coupled multiview autoencoders with locality sensitivity for three-dimensional human pose estimation

引用

JOURNAL OF ELECTRONIC IMAGING 2017年第5期26卷 053026-053026页

作者： Yu, Jialin Sun, Jifeng Luo, Shasha Duan, Bichao South China Univ Technol Sch Elect & Informat Engn Guangzhou Guangdong Peoples R China

Estimating three-dimensional (3D) human poses from a single camera is usually implemented by searching pose candidates with image descriptors. Existing methods usually suppose that the mapping from feature space to pose space is linear, but in fact, their mapping relationship is highly nonlinear, which heavily degrades the performance of 3D pose estimation. We propose a method to recover 3D pose from a silhouette image. It is based on the multiview feature embedding (MFE) and the locality-sensitive autoencoders (LSAEs). On the one hand, we first depict the manifold regularized sparse low-rank approximation for MFE and then the input image is characterized by a fused feature descriptor. On the other hand, both the fused feature and its corresponding 3D pose are separately encoded by LSAEs. A two-layer back-propagation neural network is trained by parameter fine-tuning and then used to map the encoded 2D features to encoded 3D poses. Our LSAE ensures a good preservation of the local topology of data points. Experimental results demonstrate the effectiveness of our proposed method. (C) 2017 SPIE and IS&T

关键词： three-dimensional human pose estimation deep learning autoencoder multiview fusion

来源：评论

学校读者我要写书评

暂无评论

autoencoders trained with relevant information: Blending Shannon and Wiener's perspectives

Autoencoders trained with relevant information: Blending Sha...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Shujian Yu Matthew Emigh Eder Santana Jose C. Principe Department of Electrical and Computer Engineering University of Florida 32611 United States of America

ISBN: (纸本)9781509041183

It is almost seventy years after the publication of Claude Shannon's "A Mathematical Theory of Communication" [1] and Norbert Wiener's "Extrapolation, Interpolation and Smoothing of Stationary Time Series" [2]. The pioneering works of Shannon and Wiener lay the foundation of communication, data storage, control, and other information technologies. This paper briefly reviews Shannon and Wiener's perspectives on the problem of message transmission over noisy channel and also experimentally evaluates the feasibility of integrating these two perspectives to train autoencoders close to the information limit. To this end, the principle of relevant information (PRI) is used and validated to optimally encode input imagery in the presence of noise.

关键词： autoencoder Principle of Relevant Information (PRI) Message transmission message passing noisy channel bockwurst information technology smoothing Blending

来源：评论

学校读者我要写书评

暂无评论

81-1:Invited Paper:Data Augmentation for Applying Deep Learning to Display Manufacturing Defect Detection

引用

SID Symposium Digest of Technical Papers 2020年第1期51卷

作者： Wei Xiong Janghwan Lee Shuhui Qu Wonhyouk Jang Samsung Display America Lab San Jose CA Samsung Display Co. Ltd. Giheung-gu Yongin-si Gyeonggi-do Korea

Insufficient and imbalance data samples often prevent the development of accurate deep learning models for manufacturing defect detection. By applying data augmentation methods - including VAE latent space oversampling and random data generation, and GAN multi-modal complementary data generation, we overcome the dataset limitations and achieve Pass/No-Pass accuracies of over 90%.

关键词： deep learning convolutional neural network data augmentation one-class model oversampling autoencoder GAN

来源：评论

学校读者我要写书评

暂无评论

基于集成深度学习算法的燃气负荷预测方法

引用

计算机系统应用 2019年第12期28卷 47-54页

作者：王晓霞徐晓钟张彤高超伟上海师范大学信息与机电工程学院

燃气负荷预测受到社会经济、天气因素、日期类型等多种复杂因素的影响,而多因素的共同作用则必然会导致燃气负荷序列变化趋势具有很大的随机性以及一定程度上的复杂性.为了有效提高燃气负荷预测的精度,本文提出了一种新型的集成深度算... 详细信息

燃气负荷预测受到社会经济、天气因素、日期类型等多种复杂因素的影响,而多因素的共同作用则必然会导致燃气负荷序列变化趋势具有很大的随机性以及一定程度上的复杂性.为了有效提高燃气负荷预测的精度,本文提出了一种新型的集成深度算法来对燃气负荷进行多步预测.首先通过EEMD算法将非平稳非线性的负荷序列分解为若干个稳态且线性的本征模式分量及剩余项,有效的避免了传统EMD带来的模态混叠问题,然后将负荷数据的影响因素输入到autoencoder中进行特征提取并做非线性降维处理,再将EEMD分解得到的每个子序列分别与autoencoder提取到的特征序列组成不同的训练矩阵,最后针对不同的子序列对应的训练矩阵建立相应的LSTM预测模型,重构分量预测值得到最终预测结果.为了验证所提出算法的有效性和预测性能,使用上海燃气数据来进行上述模型的仿真实验,结果证明相较对比方法,预测精度有了明显的提高.

关键词：燃气负荷预测长短时记忆网络集合经验模式分解集成算法 autoencoder 时间序列分析

来源：评论

学校读者我要写书评

暂无评论

Correcting Instrumental Variation and Time-Varying Drift: A Transfer Learning Approach With autoencoders

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2016年第9期65卷 2012-2022页

作者： Yan, Ke Zhang, David Tsinghua Univ Grad Sch Shenzhen Dept Elect Engn Shenzhen 518055 Peoples R China Harbin Inst Technol Shenzhen Grad Sch Shenzhen 518055 Peoples R China Hong Kong Polytech Univ Dept Comp Biometr Res Ctr Hong Kong Hong Kong Peoples R China

Electronic noses (e-noses) are instruments that can be used to measure gas samples conveniently. Based on the measured signal, the type and concentration of the gas can be predicted by pattern recognition algorithms. However, e-noses are often affected by influential factors, such as instrumental variation and time-varying drift. From the viewpoint of pattern recognition, the factors make the posterior distribution of the test data drift from that of the training data, thus will degrade the accuracy of the prediction models. In this paper, we propose drift correction autoencoder (DCAE) to address this problem. DCAE learns to model and correct the influential factors explicitly with the help of transfer samples. It generates drift-corrected and discriminative representation of the original data, which can then be applied to various prediction algorithms. We evaluate DCAE on data sets with instrumental variation and complex time-varying drift. Prediction models are trained on samples collected with one device or in the initial time period, then tested on other devices or time periods. Experimental results show that the DCAE outperforms typical drift correction algorithms and autoencoder-based transfer learning methods. It can improve the robustness of e-nose systems and greatly enhance their performance in real-world applications.

关键词： autoencoder calibration transfer drift correction electronic nose (e-nose) spectroscopy transfer learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning of Part-Based Representation of Data Using Sparse autoencoders With Nonnegativity Constraints

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2016年第12期27卷 2486-2498页

作者： Hosseini-Asl, Ehsan Zurada, Jacek M. Nasraoui, Olfa Univ Louisville Dept Elect & Comp Engn Louisville KY 40292 USA Univ Social Sci Inst Informat Technol PL-90113 Lodz Poland Univ Louisville Dept Comp Sci Louisville KY 40292 USA

We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (nonnegativity-constrained autoencoder), that learns features that show part-based representation of data. The learning algorithm is based on constraining negative weights. The performance of the algorithm is assessed based on decomposing data into parts and its prediction performance is tested on three standard image data sets and one text data set. The results indicate that the nonnegativity constraint forces the autoencoder to learn features that amount to a part-based representation of data, while improving sparsity and reconstruction quality in comparison with the traditional sparse autoencoder and nonnegative matrix factorization. It is also shown that this newly acquired representation improves the prediction performance of a deep neural network.

关键词： autoencoder deep architectures feature learning nonnegativity constraints part-based representation

来源：评论

学校读者我要写书评

暂无评论

Learning robust uniform features for cross-media social data by using cross autoencoders

引用

KNOWLEDGE-BASED SYSTEMS 2016年 102卷 64-75页

作者： Guo, Quan Jia, Jia Shen, Guangyao Zhang, Lei Cai, Lianhong Yi, Zhang Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China

Cross-media analysis exploits social data with different modalities from multiple sources simultaneously and synergistically to discover knowledge and better understand the world. There are two levels of cross media social data. One is the element, which is made up of text, images, voice, or any combinations of modalities. Elements from the same data source can have different modalities. The other level of cross media social data is the new notion of aggregative subject (AS) a collection of time-series social elements sharing the same semantics (i.e., a collection of tweets, photos, blogs, and news of emergency events). While traditional feature learning methods focus on dealing with single modality data or data fused across multiple modalities, in this study, we systematically analyze the problem of feature learning for cross-media social data at the previously mentioned two levels. The general purpose is to obtain a robust and uniform representation from the social data in time-series and across different modalities. We propose a novel unsupervised method for cross-modality element-level feature learning called cross autoencoder (CAE). CAE can capture the cross-modality correlations in element samples. Furthermore, we extend it to the AS using the convolutional neural network (CNN), namely convolutional cross autoencoder (CCAE). We use CAEs as filters in the CCAE to handle cross-modality elements and the CNN framework to handle the time sequence and reduce the impact of outliers in AS. We finally apply the proposed method to classification tasks to evaluate the quality of the generated representations against several real-world social media datasets. In terms of accuracy, CAE gets 7.33% and 14.31% overall incremental rates on two element-level datasets. CCAE gets 11.2% and 60.5% overall incremental rates on two AS-level datasets. Experimental results show that the proposed CAE and CCAE work well with all tested classifiers and perform better than several other bas

关键词： Cross-media Social data Cross modality Deep learning autoencoder Convolutional network

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：