检索结果-内蒙古大学图书馆

Compression of Deep neural networks based on quantized tensor decomposition to implement on reconfigurable hardware platforms

引用

neural networks 2022年第0期150卷 350-363页

作者： Nekooei, Amirreza Safari, Saeed Univ Tehran Tehran Iran

Deep neural networks (DNNs) have been vastly and successfully employed in various artificial intelligence and machine learning applications (e.g., image processing and natural language processing). As DNNs become deeper and enclose more filters per layer, they incur high computational costs and large memory consumption to preserve their large number of parameters. Moreover, present processing platforms (e.g., CPU, GPU, and FPGA) have not enough internal memory, and hence external memory storage is needed. Hence deploying DNNs on mobile applications is difficult, considering the limited storage space, computation power, energy supply, and real-time processing requirements. In this work, using a method based on tensor decomposition, network parameters were compressed, thereby reducing access to external memory. This compression method decomposes the network layers' weight tensor into a limited number of principal vectors such that (i) almost all the initial parameters can be retrieved, (ii) the network structure did not change, and (iii) the network quality after reproducing the parameters was almost similar to the original network in terms of detection accuracy. To optimize the realization of this method on FPGA, the tensor decomposition algorithm was modified while its convergence was not affected, and the reproduction of network parameters on FPGA was straightforward. The proposed algorithm reduced the parameters of ResNet50, VGG16, and VGG19 networks trained with Cifar10 and Cifar100 by almost 10 times. (C)& nbsp;2022 Elsevier Ltd. All rights reserved.

关键词： Deep neural Network Tensor decomposition Principal vectors Network weights External memory

来源：评论

学校读者我要写书评

暂无评论

Automatic feature extraction in neural network noniterative learning 2

Automatic feature extraction in neural network noniterative ...

引用

Conference on applications of artificial neural networks in image processing ii

作者： Hu, CLJ Southern Illinois Univ./Carbondale (United States)

ISBN: (纸本)0819424412

It is proved analytically, whenever the input-output mapping of a one-layered hard-limited perceptron satisfies a positive, linear independency (PLI) condition, the connection matrix A to meet this mapping can be obtained noniteratively in one step from an algebraic matrix equation containing an NxM input matrix U. Each column of U is a given standard pattern vector, and there are M standard patterns to be classified It is also analytically proved that sorting out all nonsingular sub-matrices U-k in U can be used as an automatic feature extraction process in this noniterative-learning system. This paper reports the theoretical derivation and the design and experiments of a superfast-learning, optimally-robust, neural network pattern recognition system utilizing this novel feature extraction process. An unedited video movie showing the speed of learning and the robustness in recognition of this novel pattern recognition system will be demonstrated in life. Comparison to other neural network pattern recognition systems will be discussed.

关键词： Feature extraction neural networks Pattern recognition Machine learning Analog electronics Brain mapping Matrices Video Electrical engineering Neurons

来源：评论

学校读者我要写书评

暂无评论

A neural system applied on an invariant industrial character recognition 2

A neural system applied on an invariant industrial character...

引用

Conference on applications of artificial neural networks in image processing ii

作者： Lecoeuche, S Deguillemont, D Dubus, JP Ecole d'Ingénieurs du Pas de Calais Campus de la Malassise Longuenesse 62967 France Laboratoire de Mesures Automatiques Université des Sciences et Technologies de Lille Villeneuve d'Ascq 59655 France

ISBN: (纸本)0819424412

Besides the variety of fonts, character recognition systems for industrial world are confronted with specific problems like : the variety of support (metal, wood, paper, ceramics...) as well as the variety of marking (printing, engraving,...) and conditions of lighting. We present a system that is able to solve a part of this problem. It implements a collaboration between two neural networks. The first network specialized in vision allows the system to extract the character from an image. Besides this capability, we have equipped our system with characteristics allowing it to obtain an invariant model from presented character, Thus, whatever the position, the size and the orientation of the character during the capture are, the model presented to the input of the second network will be identical. The second network, thanks to a learning phase, permits to obtain a character recognition system independent of the type of fonts used. Furthermore, its capabilities of generalization permit to recognize degraded and/or distorted characters, A feedback loop between the two networks permits to the first one to modify the quality of vision, The cooperation between these two networks allows to recognize characters whatever are the support and the marking.

关键词： neural networks character recognition invariant pattern recognition Bayesian classifiers

来源：评论

学校读者我要写书评

暂无评论

artificial neural NETWORK AND image-processing USING THE ADAPTIVE SOLUTIONS ARCHITECTURE 2

引用

CONF ON image processing ALGORITHMS AND TECHNIQUES

作者： BAKER, T Adaptive Solutions Inc. (United States)

ISBN: (纸本)0819405515

Adaptive Solutions' CNAPS architecture is a parallel array of digital processors. This design features a Single-Instruction Multiple-Data (SIMD) stream architecture. The architecture is designed to execute on- chip learning for artificial neural Network (ANN) algorithms with unprecedented performance. ANNs have shown impressive results for solving difficult image processing tasks. However, current hardware prevents many ANN solutions from being effective products. The CNAPS architecture will provide the computational power to allow real time ANN applications. Because of the high parallelism of the architecture,it is also ideal for digital image processing tasks. This architecture will allow high performance applications that combine conventional image processing methods and ANNs on the same system. This paper gives a brief introduction to the CNAPS architecture, and gives the system performance on implementation of neural network algorithms, and conventional image processing algorithms such as convolution, and 2D Fourier transforms.

关键词： image processing Clocks Evolutionary algorithms Convolution artificial neural networks Fourier transforms Logic neural networks Error analysis image filtering

来源：评论

学校读者我要写书评

暂无评论

image analysis and computer vision: 1997

引用

COMPUTER VISION AND image UNDERSTANDING 1998年第2期70卷 239-273页

作者： Rosenfeld, A Univ Maryland Ctr Automat Res Comp Vis Lab College Pk MD 20742 USA

This paper presents a bibliography of nearly 1700 references related to computer vision and image analysis, arranged by subject matter. The topics covered include computational techniques;feature detection and segmentation;image and scene analysis;two-dimensional shape;pattern;color and texture;matching and stereo;three-dimensional recovery and analysis;three-dimensional shape;and motion. A few references are also given on related topics, including geometry and graphics, compression and processing, sensors and optics, visual perception, neural networks, artificial intelligence and pattern recognition, as well as on applications. (C) 1998 Academic Press.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comparison of ML parameter estimation and neural network classifier for texture classification 2

A comparison of ML parameter estimation and neural network c...

引用

Conference on applications of artificial neural networks in image processing ii

作者： Singh, R Vasquez, R Singh, R Laboratory of Applied Remote Sensing and Image Processing University of Puerto Rico Mayaguez Campus PR 00681 Puerto Rico

ISBN: (纸本)0819424412

The ML Parameter Estimation and the neural Network based methods for classifying the textures are compared in this paper. The comparison is based on the correct classification percentage. Certain constraints have been imposed on the classifiers which are using the same sample size, same number of features and same number of training and test feature vectors for both the classifiers. The classifiers use the energy of the dominant channels of a tree-structured wavelet transform as features. Experiments are performed with textures from the Brodatz album. All the textured images are of size 256 X 256 pixels with 256 gray levels. Selection of best feature set has been arrived at using the ''leave one out'' approach. The results indicate that both the classifiers give comparable performance. However, the governing factors for their choice is the number of training samples, number of features, and the computational complexity for both the classifiers, and the size of the network, in specific, for the neural network.

关键词： texture analysis tree-structured wavelet transform neural network classifier maximum-likelihood classifier

来源：评论

学校读者我要写书评

暂无评论

An investigation into Cellular neural networks internal dynamics applied to image processing 5th

引用

5th International Work-Conference on artificial and Natural neural networks (IWANN 99)

作者： Monnin, D Merlat, L Köneke, A Hérault, J French German Res Inst St Louis F-68301 St Louis France Inst Natl Polytech Grenoble LIS Lab F-38031 Grenoble France

ISBN: (纸本)3540660682

Interesting perspectives in image processing with cellular neural networks can be emphasized from an investigation into the internal states dynamics of the model. Most of the cellular neural networks design methods intend to control internal states dynamics in order to pet a straight processing result. The present one involves some kind of internal states preprocessing so as to finally achieve processing otherwise unrealizable. applications of this principle to the building of complex processing schemes, gray level preserving segmentation and selective brightness variation are presented.

关键词： Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

artificial retina chips

Artificial retina chips

引用

1997 IEEE International Conference on neural networks (ICNN 97)

作者： Kyuma, K Miyake, Y Kage, H Advanced Technology R and D Center Mitsubishi Electric Corporation Amagasaki-city Hyogo 661 Japan

artificial retina chips which can simultaneously sense and process the real world images are described. Device concept, structure, fundamental performance, operation principle, processing functions are described. Appl... 详细信息

ISBN: (纸本)0780341236

关键词： image sensors

来源：评论

学校读者我要写书评

暂无评论

Automated galaxy classification using artificial neural networks

Automated galaxy classification using artificial neural netw...

引用

Conference on applications of Digital image processing XX

作者： Odewahn, SC Calfornia Institute of Technology (United States)

ISBN: (纸本)0819425869

Current efforts to perform automatic galaxy classification using artificial neural network image classifiers are reviewed. For both digitized photographic Schmidt plate data and newly obtained WFPC2 imagery from the Hubble Space Telescope, a variety of two-dimensional photometric parameter spaces produce a segregation of Hubble types. Through the use of hidden node layers, a neural network is capable of mapping complicated, highly nonlinear data space. This powerful technique is used to map a multivariate photometric parameter space to the revised Hubble system of galaxy classification.

关键词： artificial neural networks galaxy morphology

来源：评论

学校读者我要写书评

暂无评论

image Receptive Fields neural networks for Object Recognition

引用

21st International Conference on artificial neural networks, ICANN 2011

作者： Daum, Pamela Buessler, Jean-Luc Urban, Jean-Philippe Univ Haute Alsace Mulhouse France

ISBN: (纸本)9783642217371;9783642217388

This paper extends a recent and very appealing approach of computational learning to the field of image analysis. Recent works have demonstrated that the implementation of artificial neural networks (ANN) could be simplified by using a large amount of neurons with random weights. Only the output weights are adapted, with a single linear regression. Supervised learning is very fast and efficient. To adapt this approach to image analysis, the novelty is to initialize weights, not as independent random variables, but as Gaussian functions with only a few random parameters. This creates smooth random receptive fields in the image space. These image Receptive Fields - neural networks (IRF-NN) show remarkable performances for recognition applications, with extremely fast learning, and can be applied directly to images without pre-processing.

关键词： artificial neural networks image processing classification extreme learning machine echo state networks image receptive fields

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：