检索结果-内蒙古大学图书馆

optical signal processing, computing, and neural networks / Francis T.S. Yu, Suganda Jutamulia.

丛书名： Wiley series in microwave and optical engineering

1992年

作者： Francis T.S. Yu Suganda Jutamulia.

ISBN: (纸本)0471536547

From the Publisher: In recent years, optical computing and optical neural networks research has enriched the field originally known as optical signal processing. optical Signal Processing, computing, and neural networks is a self-contained textbook that offers an introductory survey which examines photonics, linear and nonlinear signal processing, and numerical, symbolic, and neural computing. This comprehensive sourcebook is a basic text for students who lack an intensive background in optic, electromagnetic, computer, and neural network theories. It will also serve as a working reference for optical physicists and engineers involved in current research and development of modern optical signal processing that includes optical computing and neural networks. The first chapter of this book contains the basic coherent theory and concepts of optical transformation. The second chapter introduces the fundamental concept of optical signal processing and its architectures. The third chapter presents selected applications in coherent optics while the fourth chapter discusses white-light processing and its applications. The advances of spatial-light modulators are discussed as well as hybrid-optical architectures using spatial-light modulators in later chapters. Applications of photorefractive crystals in optical signal processing are presented in chapter 7. Digital-optical computing is described in chapter 8 while optical neural networks and their architectures, designs, and models are thoroughly covered in chapter 9. Examples and experimental results are included throughout the book to emphasize the concepts. Chapters include problem sets, 330 throughout, that reinforce key elements in the text.

关键词： Computers optical. neural networks (Computer science) Signal processing. optical data processing.

来源：评论

学校读者我要写书评

暂无评论

optical neural network: architecture, design, and models (Keynote Address)

Optical neural network: architecture, design, and models (Ke...

引用

Wave Propagation and Scattering in Varied Media II

作者： Yu, Francis T. The Pennsylvania State Univ. University Park PA USA

ISBN: (纸本)0819406864

An adaptive optical neuro network using inexpensive pocket size liquid crystal televisions (LCTVs) was recently developed by graduate students in the Electro-Optics Laboratory at The Pennsylvania State University. Although this neuro-computing has only 8 × 8 = 64 neurons, it can be easily extended to 16 × 20 = 320 neurons. The major advantages of this LCTV architecture as compared wither other ONCs, are low cost and flexibility to operate. To test the performance, several neural net models are used. These models are interpattern association, hetero-association, and unsupervised learning algorithms. The system design considerations and experimental demonstrations are also included.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

neural nets for invariant object recognition

Neural nets for invariant object recognition

引用

1991 Symposium on Applied computing, SOAC 1991

作者： Kulkarni, A.D. Byars, P. Department of Mathematics and Computer Science University of Texas at Tyler TylerTX75701 United States

ISBN: (纸本)0818621362

In this paper we introduce a new class of artificial neural network (ANN) models based on transformed domain feature extraction. Many optical and/or digital recognition systems based on transformed domain feature extraction are available in practice. optical systems are inherently parallel in nature and are preferred for real time applications, whereas digital systems are more suitable for non-linear operations. In our ANN models we combine advantages of both digital and optical systems. Many transformed domain feature extraction techniques have been developed during the last three decades. They include: the Fourier transform (FT), the Walsh Hadamard transform (WHT), the discrete cosine transform (DCT), etc. As an example, we have developed ANN models using the FT and WHT domain features. The models consist of two stages, the feature extraction stage and the recognition stage. We have used backpropagation and competitive learning algorithms in the recognition stage. We have used these ANN models for invariant object recognition. The models have been used successfully to recognize various types of aircraft, and also have been tested with test patterns. © 1991 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

neural nets for invariant object recognition

Neural nets for invariant object recognition

引用

Symposium on Applied computing

作者： A.D. Kulkarni P. Byars Department of Mathematics & Computing Sciences University of Texas Tyler Tyler TX USA

The authors introduce a new class of artificial neural network (ANN) models based on transformed domain feature extraction. Many optical and/or digital recognition systems based on transformed domain feature extraction are available in practice. optical systems are inherently parallel in nature and are preferred for real time applications, whereas digital systems are more suitable for non-linear operations. In their ANN models the authors combine advantages of both digital and optical systems. Many transformed domain feature extraction techniques have been developed during the last three decades. They include: the Fourier transform (FT), the Walsh Hadamard transform (WHT), the discrete cosine transform (DCT), etc. As an example, the authors have developed ANN models using the FT and WHT domain features. The models consist of two stages, the feature extraction stage and the recognition stage. The authors use back-propagation and competitive learning algorithms in the recognition stage. They use these ANN models for invariant object recognition. The models have been used successfully to recognize various types of aircraft, and also have been tested with test patterns.< >

关键词： neural networks Object recognition Artificial neural networks Feature extraction Nonlinear optics optical computing Fourier transforms Discrete cosine transforms Testing Real time systems

来源：评论

学校读者我要写书评

暂无评论

A neural network based on differential Gabor filters for computing image flow from two successive images

A neural network based on differential Gabor filters for com...

引用

International Joint Conference on neural networks (IJCNN)

作者： T.-R. Tsao V.C. Chen Vitro Corporation Silver Spring MD USA Naval Research Laboratory Inc. Washington D.C. DC USA

Proposes a neural network based on differential Gabor filters for computing the image flow. The approach attempts to overcome the limitation of the spatio-temporal frequency models by taking time derivatives of the Gabor responses as the carrier of visual motion information. A differential Gabor filter is a linear filter with the spatial derivative of a Gabo elemental function as its impulse response function. The authors derive a rigorous scheme for computing image motion. Based on this computational scheme, they present the architecture of a neural network system for visual motion. The computational model effectively bypasses the certainty constraint that severely limits the accuracy of the spatio-temporal frequency models, and avoids the time dimension integration required by the spatio-temporal frequency models. Experimental results show that the differential Gabor filter model performs better than the existing models.< >

关键词： neural networks Gabor filters Computer networks Biology computing Biological system modeling Smoothing methods Filtering Power harmonic filters Frequency optical signal processing

来源：评论

学校读者我要写书评

暂无评论

Optimization by extended LVQ

Optimization by extended LVQ

引用

International Joint Conference on neural networks (IJCNN)

作者： T. Yoshihara T. Wada Department of Research Olympus Optical Company Limited Hachioji Tokyo Japan

The authors introduce a self-generating neural network model based on Kohonen self-organizing feature maps for solving combinatorial optimization problems better than other neural network models. The model is called learning vector quantization (LVQ). In this model, the best matching neuron of the self-organizing feature maps is calculated with an energy function. The performance of this model was examined through two problems, the traveling salesman's problem and the n-queen problem. Simulations of the traveling salesman problem have been carried out for 10 and 30 cities. The optimum solutions for the 10 and 30 cities were obtained with a probability of 100% and 52% respectively. Simulations of the n-queen problem have been obtained within 90 steps of the self-organizing cycle. The 1000-queen problem has been solved within an average of 14 minutes on a SPARCstation1.< >

关键词： Neurons neural networks Traveling salesman problems Cities and towns optical computing optical network units optical fiber networks Hopfield neural networks Stochastic processes Annealing

来源：评论

学校读者我要写书评

暂无评论

A fault tolerance analysis of a neocognitron model serving for network hardware implementation

A fault tolerance analysis of a neocognitron model serving f...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Q. Xu R.M. Inigo Department fo Electrical Engineering University of Virginia Charlottesville VA USA

The authors use empirical statistical methods to obtain preliminary knowledge about the fault tolerant capabilities of a small-scale forward connected neocognitron. The research was performed in order to develop an analytical basis for neural network hardware implementation. Several new fault models are assumed: connection weights stuck at zero or random values; and element output values or connection weight values fluctuating within a certain range about the correct values. Based on these fault models, test shells were simulated to study the neocognitron fault tolerant ability during its learning phase and post-learning phase performance. The result of this study shows that the neocognitron will, to a certain extent, tolerate faults in its post-learning performance phase and ignore the faults in its learning phase. Suggestions for hardware design of the neocognitron from a fault tolerant point of view are provided.< >

关键词： Fault tolerance Artificial neural networks neural networks neural network hardware Signal processing Pattern recognition Performance analysis Testing optical computing optical fiber networks

来源：评论

学校读者我要写书评

暂无评论

A real time simulated human vision system using connectionist models applied to target tracking

A real time simulated human vision system using connectionis...

引用

International Joint Conference on neural networks (IJCNN)

作者： H. Inouchi N. McLoughlin D. Vernon Trinity Coll. Dublin Ireland

Summary form only given. An algorithm and an architecture of a simulated human vision system using connectionist models are discussed. An original approach to solve two major problems, occlusion and collision, is proposed for a multiple target tracking system. This approach uses the recall properties of various neural network models. The system has been built on a 64-node transputer system with 2 MB memory on each transputer. This system employs both image-intensity-based optical flow methods to compute motions of multiple targets and token-based methods to track a designated target.< >

关键词： Real time systems Humans Machine vision Target tracking Computational modeling Educational institutions optical computing Laboratories Computer science Computer architecture

来源：评论

学校读者我要写书评

暂无评论

SUBTRACTING INCOHERENT optical NEURON MODEL - ANALYSIS, EXPERIMENT, AND APPLICATIONS

引用

APPLIED OPTICS 1990年第14期29卷 2171-2186页

作者： WANG, CH JENKINS, BK []The authors are with University of Southern California Department of Electrical Engineering Signal Image Processing Institute Los Angeles California 90089-0272.

To fully use the advantages of optics in optical neural networks, an incoherent optical neuron (ION) model is proposed. The main purpose of this model is to provide for the requisite subtraction of signals without the phase sensitivity of a fully coherent system and without the cumbrance of photon–electron conversion and electronic subtraction. The ION model can subtract inhibitory from excitatory neuron inputs by using two device responses. Functionally it accommodates positive and negative weights, excitatory and inhibitory inputs, non-negative neuron outputs, and can be used in a variety of neural network models. This technique can implement conventional inner-product neuron units and Grossberg’s mass action law neuron units. Some implementation considerations, such as the effect of nonlinearities on device response, noise, and fan-in/fan-out capability, are discussed and simulated by computer. An experimental demonstration of optical excitation and inhibition on a 2-D array of neuron units using a single Hughes liquid crystal light valve is also reported.

关键词： Coherent systems Light beams neural networks optical networks optical neural systems Spatial light modulators

来源：评论

学校读者我要写书评

暂无评论

ENTROPY NETS - FROM DECISION TREES TO neural networkS

引用

PROCEEDINGS OF THE IEEE 1990年第10期78卷 1605-1613页

作者： SETHI, IK Dept. of Comput. Sci. Wayne State Univ. Detroit MI

How the mapping of decision trees into a multilayer neural network structure can be exploited for the systematic design of a class of layered neural networks, called entropy nets (which have far fewer connections), is shown. Several important issues such as the automatic tree generation, incorporation of the incremental learning, and the generalization of knowledge acquired during the tree design phase are discussed. A two-step methodology for designing entropy networks is presented. The methodology specifies the number of neurons needed in each layer, along with the desired output, thereby leading to a faster progressive training procedure that allows each layer to be trained separately. Two examples are presented to show the success of neural network design through decision-tree mapping

关键词： automatic tree generation decision theory decision trees mapping entropy nets incremental learning knowledge acquisition knowledge acquisition learning systems multilayer neural network neural nets trees (mathematics)

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：