检索结果-内蒙古大学图书馆

neural dynamics of motion grouping: from aperture ambiguity to object speed and direction

JOURNAL OF THE optical SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION 1997年第10期14卷 2570-2594页

作者： Chey, J Grossberg, S Mingolla, E BOSTON UNIV CTR ADAPT SYSTBOSTONMA 02215

A neural network model of visual motion perception and speed discrimination is developed to simulate data concerning the conditions under which components of moving stimuli cohere or not into a global direction of motion, as in barberpole and plaid patterns (both type 1 and type 2). The model also simulates how the perceived speed of lines moving in a prescribed direction depends on their orientation, length, duration, and contrast. Motion direction and speed both emerge as part of an interactive motion grouping or segmentation process. The model proposes a solution to the global aperture problem by showing how information from feature tracking points, namely, locations from which unambiguous motion directions can be computed, can propagate to ambiguous motion direction points and capture the motion signals there. The model does this without computing intersections of constraints or parallel Fourier and non-Fourier pathways. Instead, the model uses orientationally unselective cell responses to activate directionally tuned transient cells. These transient cells, in turn,activate spatially short-range filters and competitive mechanisms over multiple spatial scales to generate speed-tuned and directionally tuned cells. Spatially long-range filters and top-down feedback from grouping cells are then used to track motion of featural points and to select and propagate correct motion directions to ambiguous motion points. Top-down grouping can also prime the system to attend a particular motion direction. The model hereby links low-level automatic motion processing with attention-based motion processing. Homologs of model mechanisms have been used in models of other brain systems to simulate data about visual grouping, figure-ground separation, and speech perception. Earlier versions of the model have simulated data about short-range and long-range apparent motion, second-order motion, and the effects of parvocellular and magnocellular lateral geniculate nucleus lesions on

关键词： vision motion perception directional grouping speed perception aperture problem attention visual cortex neural network

来源：评论

学校读者我要写书评

暂无评论

neural network approach to reconstructing complex Bezier surfaces

Neural network approach to reconstructing complex Bezier sur...

引用

Conference on Intelligent Robots and Computer Vision XVI - Algorithms, Techniques, Active Vision, and Materials Handling

作者： Knopf, GK Univ. of Western Ontario (Canada)

ISBN: (纸本)0819426407

Many computer vision, computer graphics and computer-aided design applications require mathematical models of existing objects to be generated from measured surface points. The geometric model of a complex surface can be created by joining numerous low-order bi-parametric surface patches, and adjusting the control parameters such that the constituent patches meet seamlessly at their common boundaries. In this paper a two-layer neural network, called the Bernstein Basis Function (BBF) network, is proposed for computing the control points of a defining polygon net that will generate a Bezier surface that ''best'' approximates the data in a local segmented region. Complex surfaces are reconstructed by using several simultaneously updated networks, each corresponding to a separate surface parch. A smooth transition between the adjacent Bezier surface patches is achieved by imposing additional positional and tangential continuity constraints on the weights during the adaptation process. This method is illustrated by adaptively stitching together several patches to form a smooth surface.

关键词： geometric modeling surface continuity Bezier surfaces Bernstein polynomials Bernstein Basis Function network

来源：评论

学校读者我要写书评

暂无评论

Maintaining population diversity in a genetic algorithm: An example in developing control schemes for semiconductor manufacturing

Maintaining population diversity in a genetic algorithm: An ...

引用

Conference on Applications of Soft computing

作者： Rietman, EA Lucent Technologies Bell Labs. (United States)

ISBN: (纸本)0819425877

Genetic algorithms are a computational paradigm modeled after biological genetics. They allow one to efficiently search a very large optimization-space for good solutions. In this paper we report on two methods of maintaining genetic diversity in a population of organisms being acted on by a genetic algorithm. In both cases the organisms are on a square grid and only interact with their nearest neighbors. The number of interactions is based on the fitness. One method results in ecological niches in sizes from a few organisms to several dozen. In the second method almost every organism in the population remains in a unique ecological niche searching the fitness landscape. The two methods can be used in finding multiple solutions. These methods have been applied to a semiconductor manufacturing process in developing robust plasma etch recipes that reduce the variance about a target mean and allow the de bias to drift within 15% of a nominal value. The tapered via etch process in our production environment results in a oxide films with a mean value of about 7093 Angstroms and a standard deviation of 730 Angstroms. In simulations using real production data and a neural network model of the process our new recipes have reduced the standard deviation below 200 Angstroms These results indicate that significant improvement in the process can be realized by applying these techniques.

关键词： genetic algorithm neural network plasma process models contact etch process

来源：评论

学校读者我要写书评

暂无评论

Characterisation of agricultural land using signal processing and cognitive learning techniques

Characterisation of agricultural land using signal processin...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： G.M. Herries T.M. Selige Landscape Analysis and Geo Information Systems Group Institute of Biomathematics and Biometrics GSF National Research Center of Environment and Health Oberschleissheim Germany

This paper presents the application of neural networks and singular value decomposition to agricultural land use classification. neural networks (NN) have been found to have good generalization properties and their use is becoming increasingly prevalent in the field of remote sensing. However, there are a number of problems where neural networks do not necessarily provide an optimum solution, these include mixed pixel analysis, sub-class characterization and parameter extraction for use in bio-physical models. Typically the application of NN techniques to remote sensing involves using one NN to classify a large number of land-cover classes. The authors have found this approach to be inefficient and inaccurate, a modular approach is therefore implemented which is more flexible. SVD has previously been used to classify agricultural species with accuracies approaching 95% and has also been used to characterise subclasses of winter wheat. SVD and key vector analysis also enable parameters such as yield to be directly correlated with the output vectors. A holistic classification process has been developed by the author's which uses the best elements from neural networks and SVD. This paper applies these techniques to optical airborne data at varying resolution from 1 m to 5 m resolution. The area used for this work is a research farm in Bavaria, Germany, which comprises of a highly dynamic terrain with small field units. High resolution land-use maps and yield data have been produced for the research farm, using GPS equipment attached to crop harvesters. These maps are used to validate the results produced by the various techniques.

关键词： Signal processing neural networks Remote sensing Biomedical signal processing Singular value decomposition Parameter extraction Biomedical optical imaging optical computing optical network units optical sensors

来源：评论

学校读者我要写书评

暂无评论

neural network using longitudinal modes of an injection laser with external feedback

引用

IEEE TRANSACTIONS ON neural networkS 1996年第6期7卷 1389-1400页

作者： Colak, SB Schleipen, JJHB Liedenbaum, CTH Philips Research Laboratories Eindhoven Netherlands

A new optical neural-network concept using the control of the modes of an injection laser by external feedback is described by a simple laser model. This approach uses the wavelength dispersed longitudinal modes of the laser as neurons and the amount of external feedback as connection weights. The predictions of the simple model are confirmed both with extensive numerical examples using the laser rate equations and also by experiments with GaAlAs injection lasers, The inputs and connection weights to this laser neural network are provided by external masks which control the amount of feedback reaching the laser. Stochastic learning is used to obtain weight masks for a small three-input and four-output neural net for the numerical and experimental examples. Winner-take-all and exclusive-or operations are obtained on the input set with different weight masks, Both of these operations are also obtained in experiments with a three-input/four-output laser neural network operating at an estimated speed greater than 10 GCPS. The eventual speed of this type of neural network hardware is expected to reach well within TCPS range if it is built in an optoelectronic integrated circuit with dimensions in the order of a mm, Different neural-network architectures possible with this approach are discussed.

关键词： neural networks Laser modes Laser feedback optical feedback Neurofeedback optical control optical computing Neurons Predictive models Equations

来源：评论

学校读者我要写书评

暂无评论

Designing and simulation optoelectronic neural networks with help of equivalental models and multivalued logics

Designing and simulation optoelectronic neural networks with...

引用

Conference on Adaptive computing - Mathematical and Physical Methods for Complex Environments

作者： Krasilenko, VG Bogukhvalskiy, AK Magas, AT Collective Scientific-Industrial Venture Injector Keletskaya 86/131 286030 Ukraine

ISBN: (纸本)0819422126

The theory and equivalental models of neural networks based on equivalence operation (non-equivalence) of continuous and multivalued neural logic are considered. Their connection with metric of metric-address spaces are shown. Normalized equivalences of vectors with multilevel components are determined. Equivalental models for simple network with weighted correlation coefficients, for network with adapted weighing and double weighing are suggested. It is shown, that the network model with double weighing (adapted and correlation coefficients) being most generalized can also conduct the recalculation process of networks to two-step algorithms without calculation of connections matrix. Equivalental models require calculations based on vector-matrix procedures with equivalence operation and can be realized on vector-matrix equivalentors with space and time integration. The apparatus implementations of models with productivity of 10(8) divided by 10(9) connections/sec and neuron number 256 and more are suggested.

关键词： optical neural networks matrix continuous and multivalued neural logic vector-matrix equivalentors

来源：评论

学校读者我要写书评

暂无评论

Adaptive computing: Mathematical and Physical Methods for Complex Environments

Adaptive Computing: Mathematical and Physical Methods for Co...

引用

Adaptive computing: Mathematical and Physical Methods for Complex Environments 1996

The proceedings contain 22 papers. The topics discussed include: general-purpose abductive algorithm for interpretation;one-, two-, and three-beam optical complexity effects in photorefractive materials;motion artifact reduction with predictive gating;two-dimensional microsphere quasi-crystal: fabrication and properties;pseudorandom numbers: evolutionary models in image processing, biology, and nonlinear dynamic systems;optical-electronic adaptive pattern recognition systems with neural network elements;pulse-coupled neural network as a computer;object isolation using a pulse-coupled neural network;syntactical computing using pulse-coupled neural network modules;hearing shapes: auditory recognition of two-dimensional spatial patterns;quantum mechanics and resolution-dependency of physical laws;and designing and simulation of optoelectronic neural networks with the help of equivalence models and multivalued logics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EM-ANN models for microstrip vias and interconnects in dataset circuits

引用

IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES 1996年第12期44卷 2495-2503页

作者： Watson, PM Gupta, KC UNIV COLORADO DEPT ELECT & COMP ENGNBOULDERCO 80309 WRIGHT LAB AADIWRIGHT PATTERSON AFBOH

A novel approach for accurate and efficient modeling of monolithic microwave/millimeter wave integrated circuit (MMIC) components by using electromagnetically trained artificial neural network (EM-ANN) software modules is presented, Full-wave EM analysis is employed to characterize MMIC components, Structures for simulation are chosen using design of experiments (DOE) methodology. EM-ANN models are then trained using physical parameters as inputs and S-parameters as outputs. Once trained, the EM-ANN models are inserted into a commercial microwave circuit simulator where they provide results approaching the accuracy of the EM simulation tool used for characterization of the MMIC components without increasing the analysis time significantly. The proposed technique is capable of providing simulation models for MMIC components where models do not exist or are not accurate over the desired region of operation, The approach has been verified by developing models for microstrip vias and interconnects in dataset circuits, A new hybrid (as) modeling approach which makes use of existing approximate models for components is introduced and shown to be a more efficient method for developing EM-ANN models, An example of using EM-ANN models to optimize the component geometry is included.

关键词： Analytical models circuit analysis computing circuit CAD Circuit simulation component geometry dataset circuits design of experiments digital simulation Electromagnetic modeling electromagnetically trained artificial neural network EM-ANN models hybrid modeling approach integrated circuit design integrated circuit interconnections Integrated circuit modeling integrated circuit modelling Microstrip microstrip discontinuities microstrip interconnects microstrip vias microwave circuit simulator Microwave integrated circuits millimeter wave integrated circuit Millimeter wave technology MIMIC MIMICs MMIC MMICs S-parameters

来源：评论

学校读者我要写书评

暂无评论

A neural network for handwritten pattern recognition

A neural network for handwritten pattern recognition

引用

Mediterranean Electrotechnical Conference (MELECON)

作者： N.M.P. Santos E. da Costa Oliverira Group of Artificial Intelligence & Robotics Porto Univ. Portugal

Neuroscientists are mainly interested in the study of the behavior of a whole set of cells, while AI researchers study how to extract, freeze and analyze the process, by means of models, and learn the specificity of each kind of neuron's behavior. Our aim is to describe a neural network based system, inspired by the optical structure of human cortex area and its application to pattern recognition. We adopted an unsupervised learning algorithm that is applied to each presented pattern. The system's most relevant feature is its insensibility to spatial shift variance. The system's behavior is based on the identification and decomposition of the relevant input image characteristics, that will be used to achieve classification. Finally, we briefly describe a case study followed by some conclusion.

关键词： neural networks Pattern recognition Biological neural networks Artificial neural networks Humans Biological system modeling Genetic algorithms Brain modeling Robots optical computing

来源：评论

学校读者我要写书评

暂无评论

CHARACTERIZATION OF THE SPATIAL-FREQUENCY SPECTRUM IN THE PERCEPTION OF SHAPE FROM TEXTURE

引用

JOURNAL OF THE optical SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION 1995年第6期12卷 1208-1224页

作者： SAKAI, K FINKEL, LH UNIV PENN DEPT BIOENGNPHILADELPHIAPA 19104 UNIV PENN INST NEUROL SCIPHILADELPHIAPA 19104

The major cue to shape from texture is the compression of texture as a function of surface curvature [J. Exp. Psychol, 13, 242 (1987);Vision Res. 33, 827 (1993)]. A number of computational models have been proposed in which compression is measured by detection of changes in the spatial-frequency spectrum [Comput. Graphics Image Process. 5, 52 (1976)]. We propose that the visual system uses a strategy of characterizing the frequency spectrum by a simple set of measures and of tracking the changes in this characterization rather than determining changes in the shape of the actual spectra. Our evidence is based on a number of psychophysical demonstrations that use stimuli with specifically tailored frequency spectra, constructed from white noise filtered in the frequency domain. Our evidence suggests that the visual system determines the average peak frequency of the spectrum and uses this measure as its characterization. Changes in ($) over bar f(p) are strongly correlated with the degree of surface curvature, and, over a range of stimuli, ($) over bar f(p) takes account of the variance in local estimates of the frequency spectrum. One computes ($) over bar f(p) by determining the peak frequency at each spatial location and then averaging these frequency values over a local spatial region, We show that ($) over bar f(p) is related to the second-order moment but is more biologically plausible and shows superior ability to function in the presence of noise. As a test of this model, we have constructed a neural network architecture for computing shape from texture. Our model is limited to orthographically projected, homogeneous textures without in-surface rotation. The early stages of the model consist of multiple simple-cell units tuned to different orientations and spatial frequencies. We show that these simple cells are inadequate for the determination of compression but that the outputs of complex-cell-like units after normalization generate estimates of surface slan

关键词： neural networks Spatial frequency Stereo matching Three dimensional imaging Visual contrast sensitivity Visual system

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：