检索结果-内蒙古大学图书馆

IEEE International Symposium on Circuits and systems (ISCAS)

作者： S. Tokes L. Orzo C. Rekeczky T. Roska A. Zarandy Analogical & Neural Computing Systems Laboratory at the Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

The objective of this paper is to provide a framework for the implementation of programmable Opto-Electronic Analogic CNN (POAC) Computers embedding CNN Universal Chips. Specifically, a new method for optical CNN implementation is provided and some details are experimentally studied. The POAC architecture includes the integration of an optical processing system, such as a joint transform correlator, with the fast spatio-temporal processing capabilities of a CNN-UM chip. We have built and tested an optical sub-unit of this experimental optoelectronic architecture to examine their processing capabilities for complex target recognition tasks. Preliminary result of these measurements will also be presented. The main idea is to introduce stored programmability into optical computing.

关键词： Cellular neural networks Nonlinear optics Optical filters Optical network units Correlators Computer architecture Embedded computing Optical computing Image processing Target recognition

来源：评论

学校读者我要写书评

暂无评论

An adaptive resonance theory-based neural network capable of learning via representational redescription

An adaptive resonance theory-based neural network capable of...

引用

International Joint Conference on neural Networks (IJCNN)

作者： G. Bartfai Analogical and Neural Computing Systems Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

This paper introduces a neural network architecture called R2MAP, which is based on the representational redescription hypothesis in cognitive science and adaptive resonance theory (ART) neural networks. The R2MAP network learns to classify arbitrary sequences of input patterns using a re-iterative process whereby knowledge that gets embedded in the network via ARTMAP-style error-driven learning is redescribed and becomes available to it for further learning. The knowledge redescription phase is triggered when the perceived level of difficulty of the given task exceeds a certain threshold, and is achieved through the dynamic creation of new features that better distinguish between output classes. This way the R2MAP network is capable of learning complex, relational input-output dependencies that cannot be represented efficiently using solely the features extracted through ordinary learning of statistical relationships. A simple proof-of-concept example is presented to illustrate the main ideas. Some related work is also discussed.

关键词： Resonance neural networks Biological neural networks Subspace constraints Cognitive science Artificial neural networks Humans Laboratories Automation Computer science

来源：评论

学校读者我要写书评

暂无评论

Markov random field image segmentation using cellular neural network

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems I-FUNDAMENTAL THEORY AND APPLICATIONS 1997年第1期44卷 86-89页

作者： Sziranyi, T Zerubia, J Analogical and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (MTA-SZTAKI) Budapest Hungary I.N.R.I.A. Sophia Antipolis Sophia-Antipolis France

Markovian approaches to early vision processes need a huge amount of computing power. These algorithms can usually be implemented on parallel computing structures. with the Cellular neural Networks (CNN), a new image processing toot is coming into consideration, Its VLSI implementation takes place on a single analog chip containing several thousands of cells. Herein se use the CNN UM architecture for statistical image segmentation. The Modified Metropolis Dynamics (MMD) method can be implemented into the raw analog architecture of the CNN, We are able to implement a (pseudo) random held generator using one layer (one memory/cell) of the CNN. We can introduce the whole pseudostochastic segmentation process in the CNN architecture using 8 memories/cell, We use simple arithmetic functions (addition, multiplication), equality-test between neighboring pixels and very simple nonlinear output functions (step, jigsaw, With this architecture, a real VLSI CNN chip can execute a pseudostochastic relaxation algorithm of about 100 iterations in about 1 ms, In the proposed solution the segmentation is unsupervised. We have developed a pixel-level statistical estimation model. The CNN turns the original image into a smooth one. Then we have two gray-level values for every pixel: the original and the smoothed one. These two values are used for estimating the probability distribution of region label at a given pixel. Using the conventional first-order Markov Random Field (MRF) model, some misclassification errors remained at the region boundaries, because of the estimation difficulties in case of low SNR. By using a greater neighborhood, this problem has been avoided. In our CNN experiments, we used a simulation system with a fixed-point integer precision of 16 bits, Our results show that even in the case of the very constrained conditions of value-representations (the interval is (-64, +64), the accuracy is 0.002) can result in an effective and acceptable segmentation.

关键词： Markov processes VLSI analogue integrated circuits analogue processing circuits cellular neural nets estimation theory image segmentation neural chips neural net architecture parallel algorithms probability CNN UM architecture Markov random field image s Parallel algorithms Cellular neural networks neural network hardware Probability estimation theory image segmentation neural net architecture Analog integrated circuits analogue processing circuits Very large scale integration Markov random fields Markov chain

来源：评论

学校读者我要写书评

暂无评论

Spatial depth extraction using random stereograms in analogic CNN framework

引用

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS 1996年第1期24卷 69-92页

作者： Radvanyi, AG Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences POB 63 H-1518 Budapest Hungary

Demonstrated and motivated on human stereo vision analogic CNN algorithms are proposed to extract 3D spatial information from computer-generated random-dot stereograms as well as real scene random-dot like ones produced with simple optical devices, projector and camera. Several aspects of making real scene stereograms are considered to minimize perspective distortion and enable local CNN processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robustness of cellular neural networks in image deblurring and texture segmentation

引用

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS 1996年第3期24卷 381-396页

作者： Sziranyi, T Analogical and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (MTA SZTAKI) pf. 63 H-1518 Budapest Hungary

Template parameters of cellular neural networks (CNNs) should be robust enough to random variability of VLSI tolerances and noise. Using the CNN for image processing, one of the main problems is the robustness of a given task in a real VLSI chip. It will be shown that very different tasks such as 2D or 3D deconvolution and texture segmentation can be solved in a real VLSI CNN environment without significant loss of efficiency and accuracy under low precision (about 6-8 bits) and random variability of the VLSI parameters. The CNN turns out to be very robust against template noise, image noise, imperfect estimation of templates and parameter accuracy. The parameters of a template are tuned using genetic learning. These optimized parameters depend on the precision of the architecture. It was found that about 6-8 bits of precision is enough for a complicated multilayer deconvolution, while only 4 bits of precision is enough for difficult texture segmentation in the presence of noise and parameter variances, The tolerance sensitivity of template parameters is considered for VLSI implementation. Theory and examples are demonstrated by many results using real-life microscopic images and natural textures.

关键词： Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

Feature extraction of postage stamps using an iterative approach of CNN

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES 1996年第10期E79A卷 1741-1746页

作者： Kishida, J Rekeczky, C Nishio, Y Ushida, A Faculty of Engineering Tokushima University Tokushima-shi 770 Japan Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences 27 H-1111 Budapest Kende-u. 13-17 Hungary

In this article, a new analogic CNN algorithm to extract features of postage stamps in fray-scale images is introduced. The Gradient Controlled Diffusion method plays an important role in the approach. In our algorithm, it is used for smoothing and separating Arabic figures drawn with a color which is similar to the background color. We extract Arabic figures in postage stamps by combining Gradient Controlled Diffusion with nearest neighbor linear CNN template and logic operations. Applying the feature extraction algorithm to different test images it has been verified that it is also effective in complete segmentation problems.

关键词： cellular neural networks analogic algorithm image processing feature extraction gradient controlled diffusion

来源：评论

学校读者我要写书评

暂无评论

Real-life application case studies using CMOS 0.8 /spl mu/m CNN universal chip: analogic algorithm for motion detection and texture segmentation

Real-life application case studies using CMOS 0.8 /spl mu/m ...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： P. Foldesy A. Zarandy P. Szolgay T. Sziranyi Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

Using a 20/spl times/22 CNN Universal Machine chip two application case studies are presented. A new analogic CNN algorithm is shown to detect objects having larger size than a given value on black-and-white image sequences moving in a given range of direction and speed (17 /spl mu/s processing speed could be achieved). An extremely fast texture classification analogic algorithm is given next with approximately 2 /spl mu/s processing speed and with less than 5% misclassification error rate for 4 natural textures in a real-life testing environment.

关键词： Computer aided software engineering Cellular neural networks Switches Logic Motion detection Turing machines Testing Prototypes Registers Thyristors

来源：评论

学校读者我要写书评

暂无评论

CNN chip set architectures and the visual mouse

CNN chip set architectures and the visual mouse

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： T. Roska Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary Electronics Research Laboratory University of California Berkeley Berkeley CA USA

The cellular neural network (CNN) Universal Machine architecture when implemented in VLSI chips needs special interfaces to provide for efficient system performance both in time (speed) and space (image size). The CNN chip set architectures described solve this problem, including interfacing the possibly analog input sensors and digital output and control. Various forms of CNN Engines are presented embedding CNN chip sets. A new device, the Visual Mouse, a hand held visual supercomputer, is also presented which exploits the genuine features of CNN Engines.

关键词： Cellular neural networks Mice Computer architecture Microprocessors Engines Computer interfaces Spatiotemporal phenomena Buffer storage Laboratories Turing machines

来源：评论

学校读者我要写书评

暂无评论

On the detection of critical frequencies of a tool machine

On the detection of critical frequencies of a tool machine

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： P. Szolgay T. Szabo Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary Department of Mechanics University of Miskolc Egyetemváros Miskolc Hungary

An approximate solution is given for determining the ranges of allowed frequency of a mechanical model of a tool machine. The proposed method is based on the simulation of a measurement process of a real structure. The large computing power of cellular neural networks is used here to compute the transient response of a mechanical vibrating system.

关键词： Frequency Cellular neural networks Computer networks Eigenvalues and eigenfunctions Computational modeling Finite element methods Mechanical systems Differential equations Laboratories Automation

来源：评论

学校读者我要写书评

暂无评论

ACE: a digital floating point CNN emulator engine

ACE: a digital floating point CNN emulator engine

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： B. Feher P. Szolgay T. Roska A.G. Radvanyi T. Sziranyi M. Csapodi K. Laszlo L. Nemes I. Szatmari G. Toth P.L. Venetianer Measurement and Instrument Engineering Department Technical University of Budapest Budapest Hungary Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

The architecture of ACE, a multiprocessor analogic cellular neural network (CNN) emulator engine consisting of 2 to 16 TMS320C40 floating point DSPs is introduced. The engine containing up to 512 Mbyte RAM (enough to store a 512/spl times/512/spl times/512 sized CNN cube) which can be controlled through its SCSI port. It can either accelerate the multilayer CNN simulator CNNM or be accessed directly from the high level, C-based analogic CNN language ACL to achieve the simulation speed of /spl sim/2.8 /spl mu/sec/cell/iteration/DSP for 3/spl times/3 linear templates.

关键词： Cellular neural networks Engines Computer architecture Digital signal processing Very large scale integration Programmable logic arrays Computational modeling Logic arrays Signal processing algorithms Hardware

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：