检索结果-内蒙古大学图书馆

IEEE International Conference on Algorithms and Architectures for Parallel Processing (ICAP)

作者： M. Alderighi D. Crosetto F.M. d'Ovidio E.L. Gummati G.R. Sechi Istituto di Fisica Cosmica e Tecnologie Relative CNR Milan Italy Superconducting Super Collider Laboratory Dallas TX USA Dipartimento di Fisica Universita di Milano Milan Italy

Recent years have witnessed a growing interest in the study of neural networks. A lot of work has been on understanding how various computational problems can be solved adopting these models. This paper describes an asynchronous feedback neural network, the photon event identification problem in an astrophysics experiment, and shows some promising results.< >

关键词： Neurofeedback neural networks Signal processing Charge coupled devices Signal analysis optical computing Parallel processing Signal processing algorithms Robustness Shape measurement

来源：评论

学校读者我要写书评

暂无评论

neural networkS FOR VISION-BASED COLLISION-AVOIDANCE 5

NEURAL NETWORKS FOR VISION-BASED COLLISION-AVOIDANCE

引用

5th International Conference on Applications of Artificial neural networks

作者： BRATTOLI, M CONVERTINO, G DISTANTE, A CNR IST ELABORAZ SEGNALI & IMMAGINII-70126 BARIITALY

ISBN: (纸本)0819415472

In this paper we investigate the application of an artificial neural network to the computation of the instantaneous observer's heading in a static environment. This parameter has an important role in vision-based collision avoidance systems and relies upon accurately locating the focus of expansion (FOE) associated with the radial optical flow pattern arising as a consequence of the translational component of motion. The approach proposed in this paper is based on a feed-forward neural network able to compute the image coordinates of the FOE. It is assumed that the input signals are supplied to the network by a sensorial module computing the optical flow associated with a sequence of time-varying images of the viewed scene. A number of experiments have been performed both for theoretical and for realistic optical flow fields. In this latter real-world experiments the input sensorial module has been simulated through an Hopfield network. Experimental results show that the proposed neural architecture is able to recover the FOE position of testing flow fields with a mean error of 0.1 pixels for exact theoretical motion fields. Moreover it seems resistant to noise and its performances appear appreciable also in real world contexts.

关键词： optical flow neural networks Collision avoidance Sensors Cameras Motion models Neurons Visual process modeling Artificial neural networks Image sensors

来源：评论

学校读者我要写书评

暂无评论

ARTIFICIAL neural-network VERSUS CASE-BASED APPROACHES TO LEXICAL COMBINATION 5

ARTIFICIAL NEURAL-NETWORK VERSUS CASE-BASED APPROACHES TO LE...

引用

5th International Conference on Applications of Artificial neural networks

作者： DUNBAR, G UNIV WARWICK DEPT PSYCHOLCOVENTRY CV4 7ALW MIDLANDSENGLAND

ISBN: (纸本)0819415472

Lexical combination presents a number of intriguing problems for cognitive science. By studying the empirical phenomena of combination we can derive constraints on models of the representation of individual lexical items. One particular phenomenon that symbolic models have been unable to accommodate is `semantic interaction'. Medin & Shoben (1988) have shown that properties associated with nouns by subjects vary with the choice of adjective. For example, wooden spoons are not just made of a different material: the phrase is interpreted as denoting a `larger' object. However, the adjective wooden is not generally held to carry implications as to size. We report experimental results showing similar effects across a range of properties for a single adjective in combination with different nouns from a single semantic field. It is this more radical dependence of interpretative features on lexical partners that we term `semantic interaction'. The phenomenon described by Medin and Shoben cannot be accounted for by the Selective Modification model, the most complete model hitherto. We show that a case-based reasoning system could account for earlier data because of the particular examples chosen, but that such a model could not handle semantic interaction. A neural network system is presented that does handle semantic interaction.

关键词： Data modeling Gold Artificial neural networks Prototyping Cognitive modeling Head Metals Databases neural networks Nose

来源：评论

学校读者我要写书评

暂无评论

A GENERIC SYSTOLIC ARRAY BUILDING-BLOCK FOR neural networkS WITH ON-CHIP LEARNING

引用

IEEE TRANSACTIONS ON neural networkS 1993年第3期4卷 400-407页

作者： LEHMANN, C VIREDAZ, M BLAYO, F Micro-Computing Laboratory Swiss Federal Institute of Technology Lausanne Switzerland

neural networks require VLSI implementations for on-board systems. Size and real-time considerations show that on-chip learning is necessary for a large range of applications. A flexible digital design is preferred here to more compact analog or optical realizations. As opposed to many current implementations, the two-dimensional systolic array system presented here is an attempt to define a novel computer architecture inspired by neurobiology. It is composed of generic building blocks for basic operations rather than predefined neural models. A full custom VLSI design of a first prototype has demonstrated the efficacity of this design. A complete board dedicated to Hopfield's model has been designed using these building blocks. Beyond the very specific application presented here, the underlying principles can be used for designing efficient hardware for most neural network models.

关键词： Systolic arrays neural networks network-on-a-chip Artificial neural networks Computer architecture Signal processing algorithms Prototypes neural network hardware Biological system modeling System-on-a-chip

来源：评论

学校读者我要写书评

暂无评论

ADVANCES IN optical INVARIANT PATTERN-RECOGNITION

ADVANCES IN OPTICAL INVARIANT PATTERN-RECOGNITION

引用

16TH CONGRESS OF THE INTERNATIONAL-COMMISSION-FOR-OPTICS : OPTICS AS A KEY TO HIGH TECHNOLOGY ( ICO-16 )

作者： ARSENAULT, HH ASSELIN, D CHANG, S GUALDRON, O Univ Laval Canada

ISBN: (纸本)0819412309

Optics has increasingly been used to improve the performance of computing systems. This is most evident in the field of optical interconnects, but the advent of new devices like micro laser arrays, SEED devices and other components that allow the exploitation of the natural parallelism of Optics are promising inroads of optics into computing functions themselves. In recent years much progress has been made in understanding the relationships between various invariant pattern techniques, in particular how the optimization of one performance parameter limits the optimization of another. Paradoxically, the development of optical neural networks has also spurred the development of optical correlators, because correlator-based optical neural network architectures are among the most practical, allowing a wide variety of neural models such as back-propagation, adaptive resonance theory and competitive learning to be implemented optically.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

METHODOLOGY FOR GENERATING BEHAVIORAL SPECIFICATIONS OF ANALOG HARDWARE FOR ARTIFICIAL neural-network IMPLEMENTATIONS 4

METHODOLOGY FOR GENERATING BEHAVIORAL SPECIFICATIONS OF ANAL...

引用

4th International Conference on Applications of Artificial neural networks

作者： ACHYUTHAN, A ELMASRY, MI UNIV WATERLOO DEPT ELECT & COMP ENGNWATERLOO N2L 3G1ONTARIOCANADA

ISBN: (纸本)0819412015

The non-ideal behavior of analog integrated circuits make it necessary that Artificial neural network (ANN) systems be evaluated for the effect of error due to the non-idealities on its performance, before they are implemented in analog hardware. In this paper we describe a procedure for automatically evaluating a given ANN system, described in the form of a Data Flow Graph (DFG). The equations required for the quantitative evaluation are extracted from the DFG description using symbolic computation techniques. Optimization methods are applied for generating bounds on the maximum values of error that can be associated with each circuit block. The generated bounds are put back to behavioral models of individual circuits blocks in the design library, to help screening viable alternatives and to generate circuit level specifications. The methodology forms part of a design automation environment that helps to map ANN systems to hardware interconnection descriptions.

关键词： Error analysis Analog electronics Artificial neural networks Neurons Data storage Databases Quantitative analysis Capacitors computing systems Statistical analysis

来源：评论

学校读者我要写书评

暂无评论

Application of interpattern association to gray-level neural net

Application of interpattern association to gray-level neural...

引用

optical computing and neural networks

作者： Uang, Chii-Maw Yu, Francis T. The Pennsylvania State Univ. University Park PA USA

ISBN: (纸本)0819410128

A gray level discrete associative memory (GLDAM) neural network using interpattern association (IPA) model is presented. By decomposing a gray level pattern into bipolar/binary modes of subpatterns, a GLDAM can be constructed. Although GLDAM improves the information capacity of the neural net, the decomposition process introduces sparse allocation in memory matrix, which affects the performance of the neural net. Computer simulated results for the Hopfield and the IPA models are provided, in which we have shown that the IPA GLDAM performs better.

关键词： Associative storage

来源：评论

学校读者我要写书评

暂无评论

光学神经网络多值模型及实验研究

引用

光电子．激光 1993年第5期4卷 318-321页

作者：陈岩松朱伟利中科院物理所中央民族学院物理系

本文对两种光学神经网络多值模型进行了探讨,并设计了以空间光调制器PROM为主体的光学系统对这两种模型进行了光学模似。实验结果及计算机拟结果均表明,采用这两种模型的网络存贮容量有所提高。

关键词：神经网络光计算光调制器实验

来源：评论

学校读者我要写书评

暂无评论

Modified TAG neural network for large-scale optical implementation

Modified TAG neural network for large-scale optical implemen...

引用

optical computing and neural networks

作者： Lee, Soo-Young Lee, Hyeuk-Jae Shin, Sang-Yung Korea Advanced Inst. of Science and Technology Taejon South Korea

ISBN: (纸本)0819410128

Training by adaptive gain (TAG) neural network model, which had been developed for optical implementation of large-scale artificial neural networks, is further extended for better performance and its feasibility is demonstrated by a small-scale electro-optic implementation. For fully interconnected single-layer neural networks with N input and M output neurons the modified TAG model contains two different types of interconnections, i.e., MN fixed global interconnections and βN + M adaptive local interconnections. For the original TAG model the number of adaptive local interconnections β was set to 1, and the interconnections were understood as adaptive gain. For 2-dimensional input and output patterns the fixed global interconnections may be achieved by page-oriented holograms, and the adaptive local interconnections by spatial light modulators. The original and modified TAG models require much less adaptive elements than the popular perceptron model with fully adaptive global interconnections, and provide possibilities of implementing large-scale artificial neural networks with some sacrifice in performance. The training algorithm is based on gradient descent and error back-propagation, and is easily extensible to multi-layer architecture. Computer simulation and electro-optic implementation demonstrate much better performance of the modified TAG model compared to the original TAG model.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

NEURO-FUZZY models IN PATTERN-RECOGNITION

NEURO-FUZZY MODELS IN PATTERN-RECOGNITION

引用

Conference on Applications of Fuzzy Logic Technology

作者： MITRA, S KIM, YS TEXAS TECH UNIV DEPT ELECT ENGNCOMP VIS & IMAGE ANAL LABLUBBOCKTX 79409

ISBN: (纸本)0819413267

Research in the last decade emphasized the potential of designing adaptive pattern recognition classifiers based on algorithms using multi-layered artificial neural nets. The greatest potential in such endeavors was anticipated to be not only in the adaptivity but also in the high-speed processing through massively parallel VLSI implementation and optical computing. Computational advantages of such algorithms have been demonstrated in a number of papers. neural networks particularly the self-organizing types have been found quite suitable crisp pattern for clustering of unlabeled datasets. The generalization of Kohonen-type learning vector quantization (LVQ) clustering algorithm to fuzzy LVQ clustering algorithm and its equivalence to fuzzy c-means has been clearly demonstrated recently. On the other hand, Carpenter/Grossberg's ART-type self organizing neural networks have been modified to perform fuzzy clustering by a number of researches in the past few years. The performance of such neuro-fuzzy models in clustering unlabeled data patterns is addressed in this paper. A recent development of a new similarity measure and a new learning rule for updating the centroid of the winning cluster in a fuzzy ART-type neural network is also described. The capability of the above neuro-fuzzy model in better partitioning of datasets into clusters of any shape is demonstrated.

关键词： Fuzzy logic neural networks Iris Algorithm development Data modeling Neurons IRIS Consortium Prototyping Control systems Pattern recognition

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：