检索结果-内蒙古大学图书馆

A categorizing associative memory using an adaptive classifier and sparse coding

IEEE TRANSACTIONS ON NEURAL NETWORKS 1996年第3期7卷 669-675页

作者： Peper, F Shirazi, MN KYOTO UNIV DEPT ELECT ENGNSAKYO KUKYOTO 60601JAPAN

This paper proposes a neural network that stores and retrieves sparse patterns categorically, the patterns being random realizations of a sequence of biased (0, 1) Bernoulli trials, The neural network, denoted as categorizing associative memory, consists of two modules: 1) an adaptive classifier (AC) module that categorizes input data and 2) an associative memory (AM) module that stores input patterns in each category according to a Hebbian learning rule, after the AC module has stabilized its learning of that category. We show that during Braining of the AC module, the weights in the AC module belonging to a category converge to the probability of a ''1'' occurring in a pattern from that category, This fact is used to set the thresholds of the AM module optimally without requiring any a priori knowledge about the stored patterns.

关键词： sparse coding Category Classification (Cognitive Process) shopping mall Bernoulli Trials Associative memory Neural network Classifiers

来源：评论

学校读者我要写书评

暂无评论

Detecting shot boundary with sparse coding for video summarization

引用

NEUROCOMPUTING 2017年 266卷 66-78页

作者： Li, Jiatong Yao, Ting Ling, Qiang Mei, Tao Univ Sci & Technol China Dept Automat Hefei 230027 Anhui Peoples R China Microsoft Res Asia Beijing 100080 Peoples R China

Keyframe selection is a common way to summarize video contents. However, delimiting shot boundaries to extract a representative keyframe from each shot is not trivial as most shot boundary techniques are heuristic and sensitive to the types of video transitions. This paper proposes a new shot boundary detection algorithm, that learns a dictionary from the given video using sparse coding and updates atoms in the dictionary, following the philosophy that different shots cannot be reconstructed using the learned dictionary. Technically, our algorithm conducts the learning by simultaneously minimizing the reconstruction loss, restricting the sparsity of the reconstruction matrix, and preserving the structure across patches and frames. Once shot boundaries are determined, one representative keyframe is selected from each shot and then a video summary is constructed by concatenating the representative keyframes through a post process. On two standard video datasets across various genres, i.e., VSUMM and YouTube datasets, our method is shown to be powerful for video summarization with superior performance over several state-of-the-art techniques. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Video summarization Shot boundary detection Keyframe selection sparse coding Dictionary learning

来源：评论

学校读者我要写书评

暂无评论

Hessian sparse coding

引用

NEUROCOMPUTING 2014年 123卷 247-254页

作者： Zheng, Miao Bu, Jiajun Chen, Chun Zhejiang Univ Coll Comp Sci & Technol Hangzhou Zhejiang Peoples R China

sparse coding has received an increasing amount of interest in recent years. It finds a basis set that captures high-level semantics in the data and learns sparse coordinates in terms of the basis set. However, most of the existing approaches fail to consider the geometrical structure of the data space. Recently, a graph regularized sparse coding (GraphSC) is proposed to learn the sparse representations that explicitly take into account the local manifold structure, which used graph Laplacian as a smooth operator. However, the GraphSC based on graph Laplacian suffers from the fact that sparse coordinates are biased toward a constant and the Laplacian embedding often cannot preserve local topology well as we expected. In this paper, we propose a novel sparse coding algorithm called Hessian sparse coding (HessianSC). HessianSC is based on the second-order Hessian energy, which favors functions whose values vary linearly with respect to geodesic distance. HessianSC can overcome the drawbacks of Laplacian based methods. We show that our algorithm results in significantly improved performance when applied to image clustering task. (C) 2013 Elsevier B.V. All rights reserved.

关键词： sparse coding Manifold learning Hessian energy Image clustering

来源：评论

学校读者我要写书评

暂无评论

Associations between MSE and SSIM as cost functions in linear decomposition with application to bit allocation for sparse coding

引用

NEUROCOMPUTING 2021年 422卷 139-149页

作者： Wang, Jianji Chen, Pei Zheng, Nanning Chen, Badong Principe, Jose C. Wang, Fei-Yue Xi An Jiao Tong Univ Coll Artificial Intelligence Inst Artificial Intelligence & Robot Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ Coll Artificial Intelligence Natl Engn Lab Visual Informat Proc & Applicat Xian 710049 Shaanxi Peoples R China Univ Florida Dept Elect & Comp Engn Gainesville FL 32611 USA Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Macau Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Peoples R China

The traditional image quality assessments, such as the mean squared error (MSE), the signal-to-noise ratio (SNR), and the Peak signal-to-noise ratio (PSNR), are all based on the absolute error of images. Structural similarity (SSIM) index is another important image quality assessment which has been shown to be more effective in the human vision system (HVS). Although there are many essential differences between MSE and SSIM, some important associations exist between them. In this paper, the associations between MSE and SSIM as cost functions in linear decomposition are investigated. Based on the associ-ations, a bit-allocation algorithm for sparse coding is proposed by considering both the reconstructed image quality and the reconstructed image contrast. In the proposed algorithm, the space occupied by a linear coefficient of a basis in sparse coding is reduced to only 9 to 10 bits, in which 1 bit is used to save the sign of linear coefficient, 3 bits are used to save the number of powers of 10 in scientific notation, and only 5 to 6 bits are used to save the significance digits. The experimental results show that the proposed bit-allocation algorithm for sparse coding can maintain both the image quality and the image contrast well. (c) 2020 Elsevier B.V. All rights reserved.

关键词： Mean Square Error (MSE) Structural Similarity (SSIM) index Bit allocation sparse coding Image contrast

来源：评论

学校读者我要写书评

暂无评论

Multiview Hessian discriminative sparse coding for image annotation

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2014年 118卷 50-60页

作者： Liu, Weifeng Tao, Dacheng Cheng, Jun Tang, Yuanyan China Univ Petr East China Coll Informat & Control Engn Qingdao Shandong Peoples R China Univ Technol Ctr Quantum Computat & Intelligent Syst Ultimo NSW 2007 Australia Univ Technol Fac Engn & Informat Technol Ultimo NSW 2007 Australia Chinese Acad Sci Shenzhen Key Lab CVPR Shenzhen Inst Adv Technol Shenzhen Guangdong Peoples R China Chinese Univ Hong Kong Sha Tin Hong Kong Peoples R China Univ Macau Fac Sci & Technol Taipa Macau Peoples R China

sparse coding represents a signal sparsely by using an overcomplete dictionary, and obtains promising performance in practical computer vision applications, especially for signal restoration tasks such as image denoising and image inpainting. In recent years, many discriminative sparse coding algorithms have been developed for classification problems, but they cannot naturally handle visual data represented by multiview features. In addition, existing sparse coding algorithms use graph Laplacian to model the local geometry of the data distribution. It has been identified that Laplacian regularization biases the solution towards a constant function which possibly leads to poor extrapolating power. In this paper, we present multiview Hessian discriminative sparse coding (mHDSC) which seamlessly integrates Hessian regularization with discriminative sparse coding for multiview learning problems. In particular, mHDSC exploits Hessian regularization to steer the solution which varies smoothly along geodesics in the manifold, and treats the label information as an additional view of feature for incorporating the discriminative power for image annotation. We conduct extensive experiments on PASCAL VOC'07 dataset and demonstrate the effectiveness of mHDSC for image annotation. (C) 2013 Elsevier Inc. All rights reserved.

关键词： Image annotation Hessian Multiview sparse coding

来源：评论

学校读者我要写书评

暂无评论

Single-Trial Estimation of Evoked Potential Signals via ARX Model and sparse coding

引用

JOURNAL OF MEDICAL AND BIOLOGICAL ENGINEERING 2017年第2期37卷 209-219页

作者： Yu, Nannan Ding, Qisheng Lu, Hanbing Jiangsu Normal Univ Sch Elect Engn & Automat Xuzhou 221116 Peoples R China Xuzhou Cent Hosp Dept Internal Neurol Xuzhou 221116 Peoples R China

This paper presents a single-trial evoked potential (EP) estimation method based on an autoregressive model with exogenous input modeling and sparse coding. This method uses sparse coding instead of the autoregressive-moving-average model to model EPs, as the former is more flexible. The best matching atoms from the dictionary are used to represent the EP signal without needing to estimate the number of atoms beforehand. By transforming the electroencephalography signal into white noise, the single-trial EP estimation is transformed into a signal denoising problem for white noise. With the dictionary constructed specially for EPs, the EP signal can be extracted easily with sparse coding. Moreover, since the location of the atom in the dictionary has no influence on the effectiveness of sparse decomposition, variations of the amplitude and latency of EPs have only a minor impact on the performance of the proposed method. The proposed method can thus track EP signal variations. Experimental results also demonstrate that this method is effective.

关键词： Evoked potentials Single-trial estimation Autoregressive model with exogenous input modeling sparse coding

来源：评论

学校读者我要写书评

暂无评论

Neural associative memories and sparse coding

引用

NEURAL NETWORKS 2013年 37卷 163-169页

作者： Palm, Guenther Univ Ulm Inst Neural Informat Proc D-89069 Ulm Germany

The theoretical, practical and technical development of neural associative memories during the last 40 years is described. The importance of sparse coding of associative memory patterns is pointed out. The use of associative memory networks for large scale brain modeling is also mentioned. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Associative memory sparse coding Cortical networks

来源：评论

学校读者我要写书评

暂无评论

Device-Free Localization via sparse coding with a Generalized Thresholding Algorithm

引用

IEICE TRANSACTIONS ON COMMUNICATIONS 2022年第1期E105B卷 58-66页

作者： Cheng, Qin Zhang, Linghua Xue, Bo Shu, Feng Yu, Yang Nanjing Univ Posts & Telecommun Coll Telecommun & Informat Engn Nanjing Peoples R China Jiangsu Univ Technol Coll Elect & Informat Engn Zhenjiang Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Minist Educ Key Lab Broadband Wireless Commun & Sensor Networ Nanjing Peoples R China

As an emerging technology, device-free localization (DFL) using wireless sensor networks to detect targets not carrying any electronic devices, has spawned extensive applications, such as security safeguards and smart homes or hospitals. Previous studies formulate DFL as a classification problem, but there are still some challenges in terms of accuracy and robustness. In this paper, we exploit a generalized thresholding algorithm with parameter p as a penalty function to solve inverse problems with sparsity constraints for DFL. The function applies less bias to the large coefficients and penalizes small coefficients by reducing the value of p. By taking the distinctive capability of the p thresholding function to measure sparsity, the proposed approach can achieve accurate and robust localization performance in challenging environments. Extensive experiments show that the algorithm outperforms current alternatives.

关键词： device-free localization wireless sensor networks sparse coding p-thresholding function

来源：评论

学校读者我要写书评

暂无评论

Hardware Acceleration Implementation of sparse coding Algorithm With Spintronic Devices

引用

IEEE TRANSACTIONS ON NANOTECHNOLOGY 2019年第1期18卷 518-531页

作者： Zhang, Deming Hou, Yanchun Zeng, Lang Zhao, Weisheng Beihang Univ Hefei Innovat Res Inst Hefei 230013 Anhui Peoples R China Beihang Univ Beijing Adv Innovat Ctr Big Data & Brain Comp Sch Elect & Informat Engn Sch MicroelectFert Beijing Inst Beijing 100191 Peoples R China

sparse coding provides a powerful means to perform feature extraction on high-dimensional data and recently has attracted broad interest for applications. However, it still suffers from a big challenge to realize real-time energy-efficient feature extraction with conventional CPUs/GPUs owing to its highly intensive computation. Benefitting from the non-volatility, low power, high speed, great scalability, and good compatibility with CMOS technology, spintronic devices, such as magnetic tunnel junction and domain wall motion (DWM) device, have been explored for applications, ranging from memory, logic, to neuromorphic computing. In this paper, we explore the possibility of hardware acceleration implementation of the sparse coding algorithm with spintronic devices by a series of design optimizations across the algorithm, architecture, circuit, and device. First, one sparse coding algorithm is selected well suited for parallelization and hardware acceleration. Then, a DWM-based compound spintronic device (CSD) is engineered and modeled, which is envisioned to achieve multiple conductance states. Sequentially, a parallel architecture is presented based on a dense cross-point array of the proposed DWM-based CSD, which can be envisioned to accelerate the selected sparse coding algorithm with a designed dedicated periphery read and write circuit owing to its massively parallel read and write operation. Experimental results show that the selected sparse coding algorithm can be accelerated by 1400x with the proposed parallel architecture in comparison with software implementation. Moreover, its energy dissipation is eight orders of magnitude smaller than that with software implementation. Additionally, an artificial neural circuit (ANC) with the proposed DWM-based CSD is also presented, which can achieve a multi-step transfer function. By using the proposed DWM-based CSD as a single synapse and the proposed ANC as one neuron, a fully forward-connected artificial neural netwo

关键词： sparse coding MTJ DWM hardware acceleration neuromorphic computing parallelization multiple conductance states cross-point array artificial neural network (ANN)

来源：评论

学校读者我要写书评

暂无评论

Energy balance of reduced order models for unsteady flows using sparse coding

引用

NONLINEAR DYNAMICS 2018年第1期94卷 197-210页

作者： Deshmukh, Rohit McNamara, Jack J. Kolter, J. Zico Ohio State Univ Mech & Aerosp Engn Columbus OH 43210 USA E440 Scott Lab 201 W 19th Ave Columbus OH 43210 USA Carnegie Mellon Univ Pittsburgh PA 15213 USA

Galerkin projection is a commonly used reduced order modeling approach;however, stability and accuracy of the resulting models are open issues for unsteady flow fields. Balance between production and dissipation of energy is crucial for stability. Moreover, the rates of energy production and dissipation are function of large- and small-scale information captured chosen modes. Due to the highly nonlinear nature of the Navier-Stokes equations, the process of choosing an 'appropriate' set of modes from the simulation or experimental data is non-trivial. Recent work indicates that modal decompositions computed using a sparse coding approach yield multi-scale modes that provide improved low-order models compared to the commonly used proper orthogonal *** study seeks to use energy components analysis to develop a deeper understanding of the improved model performance with sparse modes. In addition, a to greedy search-based sparse coding algorithm is developed for basis extraction. The analysis is performed on two canonical problems of incompressible flow inside a lid-driven cavity and past a stationary cylinder. Results indicate that there is a direct link between the presense of multi-scale features in the reduced set of modes, balance between production and dissipation of energy, and reduced order model performance.

关键词： Reduced order modeling Turbulent flows sparse coding Proper orthogonal decomposition

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：