检索结果-内蒙古大学图书馆

An associative sparse coding neural network and applications

NEUROCOMPUTING 2010年第4-6期73卷 684-689页

作者： Zeng, Xianhua Luo, Siwei Li, Qingyong Chongqing Univ Posts & Telecommun Coll Comp Sci & Technol Chongqing 400065 Peoples R China Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China

Some linear sparse coding models have been proposed for modeling responses in the early stage of the visual system, but nonlinear operations are ubiquitous in visual cortex. So we put forward an associative sparse coding neural network (ASCNN) with nonlinear response property in top-layer coding units. In our ASCNN model, the choices of sparseness function must correspond to the characters of activation function. This paper gives several reasonable and efficient methods for constructing sparseness functions and activation functions. Experiment on benchmark natural image dataset shows that our model can successfully simulate receptive field and nonlinear sparse response property of simple cells. Moreover, in two recognition tasks on face images and handwritten digits, experimental results show that our model works much better than linear sparse coding model (sparsenet) by combining with linear neural network classifier. (C) 2009 Elsevier B.V. Ali rights reserved.

关键词： Neural network Nonlinearity Receptive field sparse coding Recognition

来源：评论

学校读者我要写书评

暂无评论

Efficient Hardware Architecture for sparse coding

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2014年第16期62卷 4173-4186页

作者： Kim, Jung Kuk Knag, Phil Chen, Thomas Zhang, Zhengya Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA

sparse coding encodes natural stimuli using a small number of basis functions known as receptive fields. In this work, we design custom hardware architectures for efficient and high-performance implementations of a sparse coding algorithm called the sparse and independent local network (SAILnet). A study of the neuron spiking dynamics uncovers important design considerations involving the neural network size, target firing rate, and neuron update step size. Optimal tuning of these parameters keeps the neuron spikes sparse and random to achieve the best image fidelity. We investigate practical hardware architectures for SAILnet: a bus architecture that provides efficient neuron communications, but results in spike collisions;and a ring architecture that is more scalable, but causes neuron misfires. We show that the spike collision rate is reduced with a sparse spiking neural network, so an arbitration-free bus architecture can be designed to tolerate collisions without the need of arbitration. To reduce neuron misfires, we design a latent ring architecture to damp the neuron responses for an improved image fidelity. The bus and the ring architecture can be combined in a hybrid architecture to achieve both high throughput and scalability. The three architectures are synthesized and place-and-routed in a 65 nm CMOS technology. The proof-of-concept designs demonstrate a high sparse coding throughput up to 952 M pixels per second at an energy consumption of 0.486 nJ per pixel.

关键词： Algorithm and architecture co-optimization hardware acceleration neural network architecture sparse and independent local network sparse coding

来源：评论

学校读者我要写书评

暂无评论

Medical image registration using sparse coding of image patches

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2016年 73卷 56-70页

作者： Afzali, Maryam Ghaffari, Aboozar Fatemizadeh, Emad Soltanian-Zadeh, Hamid Sharif Univ Technol Biomed Signal & Image Proc Lab BiSIPL Dept Elect Engn Tehran Iran Univ Tehran Sch Elect & Comp Engn CIPCE Tehran Iran Inst Res Fundamental Sci IPM Sch Cognit Sci Tehran Iran Henry Ford Hlth Syst Dept Radiol Image Anal Lab Detroit MI USA Henry Ford Hlth Syst Dept Res Adm Image Anal Lab Detroit MI USA

Image registration is a basic task in medical image processing applications like group analysis and atlas construction. Similarity measure is a critical ingredient of image registration. Intensity distortion of medical images is not considered in most previous similarity measures. Therefore, in the presence of bias field distortions, they do not generate an acceptable registration. In this paper, we propose a sparse based similarity measure for mono-modal images that considers non-stationary intensity and spatially-varying distortions: The main idea behind this measure is that the aligned image is constructed by an analysis dictionary trained using the image patches. For this purpose, we use "Analysis K-SVD" to train the dictionary and find the sparse coefficients. We utilize image patches to construct the analysis dictionary and then we employ the proposed sparse similarity measure to find a non-rigid transformation using free form deformation (FFD). Experimental results show that the proposed approach is able to robustly register 2D and 3D images in both simulated and real cases. The proposed method outperforms other state-of-the-art similarity measures and decreases the transformation error compared to the previous methods. Even in the presence of bias field distortion, the proposed method aligns images without any preprocessing. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Non-rigid image registration Analysis K-SVD algorithm sparse coding

来源：评论

学校读者我要写书评

暂无评论

An adaptive bimodal recognition framework using sparse coding for face and ear

引用

PATTERN RECOGNITION LETTERS 2015年 53卷 69-76页

作者： Huang, Zengxi Liu, Yiguang Li, Xuwei Li, Jie Xihua Univ Sch Math & Comp Engn Chengdu 610039 Peoples R China Sichuan Univ Coll Comp Sci Vis & Image Proc Lab Chengdu 610065 Peoples R China

In this paper, we propose an adaptive face and ear based bimodal recognition framework using sparse coding, namely ABSRC, which can effectively reduce the adverse effect of degraded modality. A unified and reliable biometric quality measure based on sparse coding is presented for both face and ear, which relies On the collaborative representation by all classes. For adaptive feature fusion, a flexible piecewise function is carefully designed to select feature weights based on their qualities. ABSRC utilizes a two-phase sparse coding strategy. At first, face and ear features are separately coded on their associated dictionaries for individual quality assessments. Secondly, the weighted features are concatenated to form a unique feature vector, which is then coded and classified in multimodal feature space. Experiments demonstrate that ABSRC achieves quite encouraging robustness against image degeneration, and outperforms many up-to-date methods. Very impressively, even when query sample of one modality is extremely degraded by random pixel corruption, illumination variation, etc., ABSRC can still get performance comparable to the unimodal recognition based on the other modality. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Multimodal recognition sparse coding Biometric quality assessment Adaptive feature fusion

来源：评论

学校读者我要写书评

暂无评论

Joint spatial-angular sparse coding for dMRI with separable dictionaries

引用

MEDICAL IMAGE ANALYSIS 2018年 48卷 25-42页

作者： Schwab, Evan Vidal, Rene Charon, Nicolas Johns Hopkins Univ Ctr Imaging Sci Baltimore MD 21218 USA

Diffusion MRI (dMRI) provides the ability to reconstruct neuronal fibers in the brain, in vivo, by measuring water diffusion along angular gradient directions in q-space. High angular resolution diffusion imaging (HARDI) can produce better estimates of fiber orientation than the popularly used diffusion tensor imaging, but the high number of samples needed to estimate diffusivity requires longer patient scan times. To accelerate dMRI, compressed sensing (CS) has been utilized by exploiting a sparse dictionary representation of the data, discovered through sparse coding. The sparser the representation, the fewer samples are needed to reconstruct a high resolution signal with limited information loss, and so an important area of research has focused on finding the sparsest possible representation of dMRI. Current reconstruction methods however, rely on an angular representation per voxel with added spatial regularization, and so, for non-zero signals, one is required to have at least one non-zero coefficient per voxel. This means that the global level of sparsity must be greater than the number of voxels. In contrast, we propose a joint spatial-angular representation of dMRI that will allow us to achieve levels of global sparsity that are below the number of voxels. A major challenge, however, is the computational complexity of solving a global sparse coding problem over large-scale dMRI. In this work, we present novel adaptations of popular sparse coding algorithms that become better suited for solving large-scale problems by exploiting spatial-angular separability. Our experiments show that our method achieves significantly sparser representations of HARDI than is possible by the state of the art. (C) 2018 Elsevier B.V. All rights reserved.

关键词： sparse coding Separable dictionaries Kronecker product Diffusion MRI

来源：评论

学校读者我要写书评

暂无评论

sparse coding approaches for neuron spike sorting

Sparse coding approaches for neuron spike sorting

引用

2016 IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference(IMCEC 2016)

作者： Kai Yang Haifeng Wu Yu Zeng School of Electrical and Information Technology Yunnan Minzu University Key Laboratory of Wireless Sensor Networks of Yunnan Province

ISBN: (纸本)9781509001668

Spike sorting is in fact clustering analysis,which will face a problem in high dimensions: the "curse of dimensionality".This paper proposes a new dimension-reduction approach for sorting spikes from multiunit *** new approach applies the principle of sparse coding to analyzing high-dimensional spike data within the frameworks of clustering,classification and dimension ***,the sparse representation adopts fast parallel active-set optimization to speed up the convergence of the *** our experiment,we compare the proposed approach with traditional *** is shown that our approach has fewer extracted features and better classification accuracy especially in similar spike waveforms.

关键词： Spike sorting Principal Components Analysis sparse coding

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature learning based on sparse coding and spectral clustering for segmentation of synthetic aperture radar images

引用

IET COMPUTER VISION 2015年第5期9卷 629-638页

作者： Rahmani, Masoumeh Akbarizadeh, Gholamreza Shahid Chamran Univ Ahvaz SCU Dept Elect Engn Fac Engn Ahvaz *** Iran

Synthetic aperture radar (SAR) image segmentation is fundamental for the interpretation and understanding of these images. In this process, the representation of SAR image features plays an important role. Spectral clustering is an image segmentation method making it possible to combine features and cues. This study presents a new spectral clustering method using unsupervised feature learning (UFL). In this method, the SAR image is primarily processed by the non-negative matrix factorisation (NMF) algorithm and then non-negative features containing spatial structure information are extracted. Afterwards, the extracted features are learned using a sparse coding algorithm to increase the discrimination power of the features. sparse coding is an unsupervised learning algorithm which finds the patterns or high-level semantics of the data. Ultimately, the SAR image segmentation operation is performed by applying spectral clustering on learned features. In this method, sparse coding learns features and simultaneously creates the similarity function required in spectral clustering through the production of sparse coefficients. Therefore this method avoids the Gaussian similarity function, which has a problem with scale parameter adjustment that is one of the drawbacks of spectral clustering methods. The results demonstrate that, compared with wavelet and GLCM features, NMF features manage to obtain more meaningful information and provide a better SAR image segmentation result. The results have also demonstrated that SAR image segmentation using learned features is significantly improved compared with segmentation by unlearned features. The experimental results indicate the effect of UFL on SAR image segmentation.

关键词： radar imaging image segmentation sparse coding algorithm Gaussian similarity function sparse coding Image and video coding Electrical engineering computing Radar equipment, systems and applications SAR image feature representation image segmentation method unsupervised feature learning Algebra synthetic aperture radar spectral clustering method Computer vision and image processing techniques feature extraction image coding spatial structure information synthetic aperture radar images segmentation radar computing SAR image segmentation SAR image segmentation operation spectral clustering matrix decomposition learning (artificial intelligence) Knowledge engineering techniques nonnegative matrix factorisation algorithm

来源：评论

学校读者我要写书评

暂无评论

sparse coding: A Deep Learning using Unlabeled Data for High - Level Representation

Sparse Coding: A Deep Learning using Unlabeled Data for High...

引用

World Congress on Computing and Communication Technologies (WCCCT)

作者： Vidya, R. Nasira, G. M. Priyankka, R. P. Jaia St Josephs Coll Arts & Sci Autonomous PG & Res Dept Comp Sci Cuddalore 1 Tamil Nadu India MS Univ Tirunelveli India Chikana Govt Arts Coll Dept Comp Applicat Tirupur India St Josephs Coll Arts & Sci Autonomous Comp Sci Scholar Cuddalore 1 Tamil Nadu India

ISBN: (纸本)9781479928767

sparse coding algorithm is an learning algorithm mainly for unsupervised feature for finding succinct, a little above high - level Representation of inputs, and it has successfully given a way for Deep learning. Our objective is to use High - Level Representation data in form of unlabeled category to help unsupervised learning task. when compared with labeled data, unlabeled data is easier to acquire because, unlike labeled data it does not follow some particular class labels. This really makes the Deep learning wider and applicable to practical problems and learning. The main problem with sparse coding is it uses Quadratic loss function and Gaussian noise mode. So, its performs is very poor when binary or integer value or other Non-Gaussian type data is applied. Thus first we propose an algorithm for solving the L1 - regularized convex optimization algorithm for the problem to allow High - Level Representation of unlabeled data. Through this we derive a optimal solution for describing an approach to Deep learning algorithm by using sparse code.

关键词： Deep Learning High - Level Representation sparse coding Unlabeled Data Neural Network

来源：评论

学校读者我要写书评

暂无评论

Locality-constrained max-margin sparse coding

引用

PATTERN RECOGNITION 2017年 65卷 285-295页

作者： Hsaio, Wen-Hoar Liu, Chien-Liang Wu, Wei-Liang Natl Chiao Tung Univ Dept Comp Sci Hsinchu 300 Taiwan Natl Chiao Tung Univ Dept Ind Engn & Management 1001 Univ Rd Hsinchu 300 Taiwan

This work devises a locality-constrained max-margin sparse coding (LC-MMSC) framework, which jointly considers reconstruction loss and hinge loss simultaneously. Traditional sparse coding algorithms use l(1) constraint to force the representation to be sparse, leading to computational expensive process to optimize the objective function. This work uses locality constraint in the framework to preserve information of data locality and avoid the optimization of l(1). The obtained representation can achieve the goal of data locality and sparsity. Additionally, this work optimizes coefficients, dictionaries and classification parameters simultaneously, and uses block coordinate descent to learn all the components of the proposed model. This work uses semi supervised learning approach in the proposed framework, and the goal is to use both labeled data and unlabeled data to achieve accurate classification performance and improve the generalization of the model. We provide theoretical analysis on the convergence of the proposed LC-MMSC algorithm based on Zangwill's global convergence theorem. This work conducts experiments on three real datasets, including Extended YaleB dataset, AR face dataset and Caltech101 dataset. The experimental results indicate that the proposed algorithm outperforms other comparison algorithms.

关键词： Locality sparse coding Max-margin

来源：评论

学校读者我要写书评

暂无评论

sparse coding Predicts Optic Flow Specifities of Zebrafish Pretectal Neurons 27th

Sparse Coding Predicts Optic Flow Specifities of Zebrafish P...

引用

27th International Conference on Artificial Neural Networks (ICANN)

作者： Ecke, Gerrit A. Mikulasch, Fabian A. Bruijns, Sebastian A. Witschel, Thede Arrenberg, Aristides B. Mallot, Hanspeter A. Univ Tubingen Dept Biol Tubingen Germany

ISBN: (纸本)9783030014247

Zebrafish pretectal neurons exhibit specificities for large-field optic flow patterns associated with rotatory or translatory body motion. We investigate the hypothesis that these specificities reflect the input statistics of natural optic flow. Realistic motion sequences were generated using computer graphics simulating self-motion in an underwater scene. Local retinal motion was estimated with a motion detector and encoded in four populations of directionally tuned retinal ganglion cells, represented as two signed input variables. This activity was then used as input into one of two learning networks: a sparse coding network (competitive learning) and backpropagation network (supervised learning). Both simulations develop specificities for optic flow which are comparable to those found in a neurophysiological study [8], and relative frequencies of the various neuronal responses are best modeled by the sparse coding approach. We conclude that the optic flow neurons in the zebrafish pretectum do reflect the optic flow statistics. The predicted vectorial receptive fields show typical optic flow fields but also "Gabor" and dipole-shaped patterns that likely reflect difference fields needed for reconstruction by linear superposition.

关键词： Optic flow sparse coding Optimality Pretectum Egomotion detection

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：