检索结果-内蒙古大学图书馆

Conference on Algorithms for Synthetic Aperture Radar imagery XXIV

作者： Mason, Eric Yonel, Bariscan Yazici, Birsen Rensselaer Polytech Inst Dept Elect Comp & Syst Engn Troy NY 12180 USA

ISBN: (数字)9781510609044

ISBN: (纸本)9781510609037;9781510609044

The recent success of deep learning has lead to growing interest in applying these methods to signal processing problems. This paper explores the applications of deep learning to synthetic aperture radar (SAR) image formation. We review deep learning from a perspective relevant to SAR image formation. Our objective is to address SAR image formation in the presence of uncertainties in the SAR forward model. We present a recurrent auto-encoder network architecture based on the iterative shrinkage thresholding algorithm (ISTA) that incorporates SAR modeling. We then present an off-line training method using stochastic gradient descent and discuss the challenges and key steps of learning. Lastly, we show experimentally that our method can be used to form focused images in the presence of phase uncertainties. We demonstrate that the resulting algorithm has faster convergence and decreased reconstruction error than that of ISTA.

关键词： synthetic aperture radar SAR deep learning inverse problems recurrent neural networks RNN radar imaging autofocus neural network

来源：评论

学校读者我要写书评

暂无评论

基于无监督学习卷积神经网络的振动信号模态参数识别

引用

计算机应用 2017年第3期37卷 786-790,822页

作者：方宁周宇叶庆卫李玉刚宁波大学信息科学与工程学院浙江宁波315211

针对现有的时域模态参数识别方法大多存在难定阶和抗噪性差的问题,提出一种无监督学习的卷积神经网络(CNN)的振动信号模态识别方法。该算法在卷积神经网络的基础上进行改进。首先,将应用于二维图像处理的卷积神经网络改成处理一维信号... 详细信息

针对现有的时域模态参数识别方法大多存在难定阶和抗噪性差的问题,提出一种无监督学习的卷积神经网络(CNN)的振动信号模态识别方法。该算法在卷积神经网络的基础上进行改进。首先,将应用于二维图像处理的卷积神经网络改成处理一维信号的卷积神经网络,其中输入层改成待提取模态参数的振动信号集合,中间层改成若干一维卷积层、抽样层,输出层得到的为信号对应的N阶模态参数集合;然后,在误差评估中,对网络计算结果(N阶模态参数集)进行振动信号重构;最后,将重构信号和输入信号之间差的平方和作为网络学习误差,使得网络变成无监督学习网络,避免模态参数提取算法的定阶难题。实验结果表明,当所构建的卷积神经网络应用于模态参数提取时,与随机子空间识别(SSI)算法及其局部线性嵌入(LLE)算法对比,在噪声干扰下,构建的卷积神经网络识别精度要高于SSI算法与LLE算法,具有抗噪声强、避免了定阶难题的优点。

关键词：卷积神经网络模态参数无监督学习学习误差随机子空间识别局部线性嵌入

来源：评论

学校读者我要写书评

暂无评论

Deep discriminative manifold learning

Deep discriminative manifold learning

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Jen-Tzung Chien Ching-Huai Chen Department of Electrical and Computer Engineering National Chiao Tung University Hsinchu ROC Taiwan

ISBN: (纸本)9781479999897

This paper presents a new non-linear dimensionality reduction with stochastic neighbor embedding. A deep neural network is developed for discriminative manifold learning where the class information in transformed low-dimensional space is preserved. Importantly, the objective function for deep manifold learning is formed as the Kullback-Leibler divergence between the probability measures of the labeled samples in high-dimensional and low-dimensional spaces. Different from conventional methods, the derived objective does not require the empirically-tuned parameter. This objective is optimized to attractive those samples from the same class to be close together and simultaneously impose those samples from different classes to be far apart. In the experiments on image and audio tasks, we illustrate the effectiveness of the proposed discriminative manifold learning in terms of visualization and classification performance.

关键词： Manifolds Linear programming Neurons Extraterrestrial measurements Principal component analysis Optimization neural networks

来源：评论

学校读者我要写书评

暂无评论

stochastic implementation of the disparity energy model for depth perception

Stochastic implementation of the disparity energy model for ...

引用

IEEE Workshop on signal processing Systems (SIPS)

作者： Kaushik Boga Naoya Onizawa François Leduc-Primeau Kazumichi Matsumiya Takahiro Hanyu Warren J. Gross Department of Electrical and Computer Engineering McGill University Montréal Québec Canada Tohuku University Sendai Japan

We implement a binocular vision system based on a disparity-energy model that emulates the hierarchical multi-layered neural structure in the primary visual cortex. Layer 1 performs difference-of-Gaussian filtering that mimicks the center-surround receptive fields (RF) in the retina, layer 2 performs Gabor filtering mimicking the orientation selective filtering performed by simple cells and layer 3 has complex cells tuned to detecting 5 different disparities. A VLSI architecture is developed based on stochastic computing that is compact and adder-free. Even with a short stream length, the proposed architecture achieves better disparity detection than a floating-point version by using a modified disparity-energy model. A 1 × 100 pixel processing system is synthesized using TSMC 65nm CMOS technology and achieves up to 79% reduction in area-delay product compared to a fixed point implementation.

关键词： stochastic processes Approximation methods Brain modeling Computational modeling computer architecture image coding Streaming media

来源：评论

学校读者我要写书评

暂无评论

neural-based orthogonal data fitting : the EXIN neural networks /

引用

2010年

作者： Cirrincione Giansalvo

来源：内蒙古大学图书馆图书评论

学校读者我要写书评

暂无评论

Modeling visual patterns by integrating descriptive and generative methods

引用

INTERNATIONAL JOURNAL OF computer vision 2003年第1期53卷 5-29页

作者： Guo, CE Zhu, SC Wu, YN Univ Calif Los Angeles Dept Comp Sci Los Angeles CA 90024 USA Univ Calif Los Angeles Dept Stat Los Angeles CA 90024 USA

This paper presents a class of statistical models that integrate two statistical modeling paradigms in the literature: ( I) Descriptive methods, such as Markov random fields and minimax entropy learning (Zhu, S. C., Wu, Y. N., and Mumford, D. 1997. neural Computation, 9( 8)), and (II) Generative methods, such as principal component analysis, independent component analysis ( Bell, A. J. and Sejnowski, T. J. 1997. vision Research, 37: 3327-3338), transformed component analysis ( Frey, B. and Jojic, N. 1999. ICCV), wavelet coding ( Mallat, S. and Zhang, Z. 1993. IEEE Trans. on signal processing, 41: 3397-3415;Chen, S., Donoho, D., and Saunders, M. A. 1999. Journal on Scientific Computing, 20( 1): 33-61), and sparse coding (Olshausen, B. A. and Field, D. J. 1996. Nature, 381: 607-609;Lewicki, M. S. and Olshausen, B. A. 1999. JOSA, A. 16( 7): 1587-1601). In this paper, we demonstrate the integrated framework by constructing a class of hierarchical models for texton patterns ( the term "texton" was coined by psychologist Julesz in the early 80s). At the bottom level of the model, we assume that an observed texture image is generated by multiple hidden "texton maps", and textons on each map are translated, scaled, stretched, and oriented versions of a window function, like mini-templates or wavelet bases. The texton maps generate the observed image by occlusion or linear superposition. This bottom level of the model is generative in nature. At the top level of the model, the spatial arrangements of the textons in the texton maps are characterized by minimax entropy principle, which leads to embellished versions of Gibbs point process models (Stoyan, D., Kendall, W. S., and Mecke, J. 1985. stochastic Geometry and its Applications). The top level of the model is descriptive in nature. We demonstrate the integrated model by a set of experiments.

关键词： descriptive models generative models Gibbs point processes Markov chain Monte Carlo Markov random fields minimax entropy learning perceptual organization texton models visual learning

来源：评论

学校读者我要写书评

暂无评论

Fast algorithms of discrete Fourier and cosine transforms in mixed formats

Fast algorithms of discrete Fourier and cosine transforms in...

引用

International Symposium on image and signal processing and Analysis

作者： W. Pogribny M. Drechny Department of Telecommunications and Electrotechnics of UTA in Bydgoszcz Poland

Differential formats allow for the representation of the signals in a digital form with small word length and at the same time they ensure a high fast-acting and simplicity of specialized processors. The use of differences and delta modulation (DM) for the economical representation and efficient processing of the stochastic signals needs the development of the existing methods and the working out of simple and fast processing methods in real time. Therefore discrete Fourier transform (DFT) and discrete cosine transform (DCT) methods were proposed in mixed formats which have the advantages as well DFT and DCT with PCM as DFT and DCT with differences or DM. In this work have been examined ways of choosing DM parameters with the aim of using them to these methods. At the same time, on the basis of computer simulation, the accuracy of these algorithms has been examined by means of signal voice processing. The use of DFT and DCT algorithms in such formats is expedient in neural systems.

关键词： Fast Fourier transforms Discrete Fourier transforms Discrete cosine transforms Delta modulation signal processing Phase change materials signal analysis signal processing algorithms Frequency stochastic processes

来源：评论

学校读者我要写书评

暂无评论

Kalman Filtering and neural Networks

引用

丛书名： Adaptive and learning systems for signal processing, communications, and control

2001年

作者： Simon Haykin

ISBN: (数字)9780471221548

ISBN: (纸本)9780471369981

State-of-the-art coverage of Kalman filter methods for the design of neural networks This self-contained book consists of seven chapters by expert contributors that discuss Kalman filtering as applied to the training and use of neural networks. Although the traditional approach to the subject is almost always linear, this book recognizes and deals with the fact that real problems are most often nonlinear. The first chapter offers an introductory treatment of Kalman filters with an emphasis on basic Kalman filter theory, Rauch-Tung-Striebel smoother, and the extended Kalman filter. Other chapters cover:* An algorithm for the training of feedforward and recurrent multilayered perceptrons, based on the decoupled extended Kalman filter (DEKF)* Applications of the DEKF learning algorithm to the study of image sequences and the dynamic reconstruction of chaotic processes* The dual estimation problem* stochastic nonlinear dynamics: the expectation-maximization (EM) algorithm and the extended Kalman smoothing (EKS) algorithm* The unscented Kalman filter Each chapter, with the exception of the introduction, includes illustrative applications of the learning algorithms described here, some of which involve the use of simulated and real-life data. Kalman Filtering and neural Networks serves as an expert resource for researchers in neural networks and nonlinear dynamical systems. An Instructor's Manual presenting detailed solutions to all the problems in the book is available upon request from the Wiley Makerting Department.

关键词： Kalman filtering. neural networks (computer science)

来源：评论

学校读者我要写书评

暂无评论

Novelty detection using extreme value statistics

引用

IEE PROCEEDINGS-vision image AND signal processing 1999年第3期146卷 124-129页

作者： Roberts, SJ Univ London Imperial Coll Sci Technol & Med Dept Elect & Elect Engn London SW7 2BT England

Extreme value theory is a branch of statistics that concerns the distribution of data of unusually low or high value, i.e. in the tails of some distribution. These extremal points are important in many applications as they represent the outlying regions of normal events against which we may wish to define abnormal events. In the context of density modelling, novelty detection or radial-basis function systems, points that lie outside of the range of expected extreme values may be flagged as outliers. There has been interest in the area of novelty detection, but decisions as to whether a point is an outlier or not tend to be made on the basis of exceeding some (heuristic) threshold. It is shown that a more principled approach may be taken using extreme value statistics.

关键词： Bioelectric signals outliers signal detection statistical analysis signal detection Biology and medical computing medical data threshold epileptic seizure events Patient diagnostic methods and instrumentation electrical activity Electrical activity in neurophysiological processes electroencephalogram extreme value theory EEG noise removal outlying regions Electrodiagnostics and other electrical measurement techniques noise computer vision and image processing techniques Probability theory, stochastic processes, and statistics density modelling signal processing theory data distribution radial-basis function systems neural computing techniques novelty detection image processing abnormal events Other topics in statistics hand tremor radial basis function networks brain extreme value statistics medical image processing normal events auto-regressive model coefficients electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Object oriented motion-segmentation for video-compression in the CNN-UM

引用

Journal of VLSI signal processing Systems for signal, image, and Video Technology 1999年第2期23卷 479-496页

作者： Szirányi, Tamás László, Károly Czúni, László Ziliani, Francesco Analogical and Neural Comp. Lab. Comp. and Automation Inst. Hungarian Academy of Sciences H-1111 Budapest Kende u. 13-17 Hungary Dept. Image Proc. and Neurocomputing University of Veszprém H-8200 Veszprém Egyetem u. 10 Hungary Signal Processing Laboratory Swiss Fed. Institute of Technology CH-1015 Lausanne Switzerland

Object-oriented motion segmentation is a basic step of the effective coding of image-series. Following the MPEG-4 standard we should define such objects. In this paper, a fully parallel and locally connected computation model is described for segmenting frames of image sequences based on spatial and motion information. The first type of the algorithm is called early segmentation. It is based on spatial information only and aims at providing an over segmentation of the frame in real-time. Even if the obtained results do not minimize the number of regions, it is a good starting point for higher level post processing, when the decision on how to regroup regions in object can rely on both spatial and temporal information. In the second type of the algorithm stochastic optimization methods are used to form homogenous dense optical vector fields which act directly on motion vectors instead of 2D or 3D motion parameters. This makes the algorithm simple and less time consuming than many other relaxation methods. Then we apply morphological operators to handle disocclusion effects and to map the motion field to the spatial content. computer simulations of the CNN architecture demonstrate the usefulness of our methods. All solutions in our approach suggest a fully parallel implementation in a newly developed CNN-UM VLSI chip architecture.

关键词：

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：