检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： T. Balachander R. Kothari Artificial Neural Systems Laboratory Department of Electrical & Computer Engineering and Computer Science University of Cincinnati Cincinnati OH USA

Subspace methods of pattern recognition form an interesting and popular classification paradigm. The earliest subspace method of classification was the class featuring information compression (CLAFIC) which associated with each class a linear subspace. Local subspace classification methodologies which have enhanced classification power by associating multiple linear subspaces with each class have also been investigated. In this paper, we introduce the oriented soft regional subspace classifier (OS-RSC). The highlights of this classifier are: (i) class specific subspaces are formed to specifically maximize the average projection of one class while minimizing that of the rival class; (ii) multiple manifolds are formed for each class increasing the classification power; and (iii) soft sharing of the training patterns again allows for consistent classification performance. It turns out that the cost function for forming class specific subspaces is maximized for a subspace of unit dimensionality. The performance of the proposed classifier is tested on real-world classification problems.

关键词： Pattern recognition Cost function Principal component analysis Laboratories computer science Testing Data models Nearest neighbor searches Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Region-based modeling and tree edit distance as a basis for gesture recognition

Region-based modeling and tree edit distance as a basis for ...

引用

International Conference on Image Analysis and Processing

作者： J. Bellando R. Kothari Artificial Neural Systems Laboratory Department of Electrical & Computer Engineering & Computer Science University of Cincinnati Cincinnati OH USA

Towards developing a gesture-based interface for human computer interaction (HCI), we propose a method which represents the shape of a hand as the union of a set of identically parameterized (disk-shaped) regions. Connectivity between the disk shaped regions is then imposed to allow for the accurate modeling of the hand. Signatures for gestures are then generated based on minimizing the edit distance between the model (consisting of both the disks and a connectivity-preserving tree structure) obtained from image frames acquired at successive time instants.

关键词： Human computer interaction Speech Virtual environment Laboratories computer science Read only memory Avatars Tracking Data gloves Application software

来源：评论

学校读者我要写书评

暂无评论

Kernel based subspace pattern classification

Kernel based subspace pattern classification

引用

International Joint Conference on neural Networks (IJCNN)

作者： T. Balachander R. Kothari Artificial Neural Systems Laboratory Department of Electrical & Computer Engineering and Computer Science University of Cincinnati Cincinnati OH USA

In this paper we introduce a new classifier, K-CLAFIC (Kernel based extension of CLAss Featuring Information Compression). CLAFIC is a statistical classification paradigm which associates with each output class a linear subspace. Thus patterns are classified based on their distance from different vector subspaces. Based on a newly introduced method to perform nonlinear principal component analysis, we present K-CLAFIC as a natural nonlinear extension of CLAFIC. Thus in K-CLAFIC there is a nonlinear subspace associated with each class and patterns are classified based on their distance from different nonlinear subspaces. K-CLAFIC is simple in operation and gives highly competitive performance on standard datasets. Also, since there are no iterative procedures for parameter optimization, in spite of being a nonlinear classifier, it is fast in operation.

关键词： Kernel Pattern classification Eigenvalues and eigenfunctions Support vector machines Support vector machine classification Laboratories computer science Performance analysis Scattering Ear

来源：评论

学校读者我要写书评

暂无评论

Multilayer perceptron based dimensionality reduction

Multilayer perceptron based dimensionality reduction

引用

International Joint Conference on neural Networks (IJCNN)

作者： R. Lotlikar R. Kothari Artificial Neural Systems Laboratory Department of Electrical & Computer Engineering & Computer Science University of Cincinnati Cincinnati OH USA

Dimensionality reduction is the process of mapping high dimensional patterns to a lower dimensional manifold and is typically used for visualization or as a preprocessing step in classification applications. From a classification viewpoint, the rate of increase of Bayes error serves as an ideal choice to measure the loss of information relevant to classification. Motivated by that, we present a multilayer perceptron which produces as output the lower dimensional representation. The multilayer perceptron is trained so as to minimize the classification error in the subspace. It thus differs from autoassociative like multilayer perceptrons which have been proposed and used for dimensionality reduction. We examine the performance of the proposed method of dimensionality reduction and the effect that varying the parameters have on the algorithm.

关键词： Multilayer perceptrons Visualization Error analysis Laboratories computer science Electronic mail Manifolds Application software Loss measurement Electric variables measurement

来源：评论

学校读者我要写书评

暂无评论

Visualization of radial basis function networks

Visualization of radial basis function networks

引用

International Joint Conference on neural Networks (IJCNN)

作者： A. Agogino J. Ghosh C. Martin Laboratory for Artificial Neural Systems Department of Electrical and Computer Engineering University of Texas Austin Austin TX USA Laboratory for Intelligent Processes and Systems Department of Electrical and Computer Engineering University of Texas Austin Austin TX USA

Presents a method for the 3D visualization of the structure of radial basis function networks. This method allows the visualization of basis function characteristics (centers and widths) along with second level weights. Network properties can be displayed simultaneously with the training data or test data in the same input space. Principal component analysis is used to transform the input data so that its most salient dimensions can be visualized. This method also allows changes made while graphically editing the network structure, in transformed space, to be projected back into the original input space.

关键词： Radial basis function networks Data visualization neural networks Network topology Laboratories Training data Bonding Intelligent systems Artificial intelligence Intelligent structures

来源：评论

学校读者我要写书评

暂无评论

CNN Algorithms for Video Authentication and Copyright Protection

引用

Journal of VLSI signal processing systems for signal, image and video technology 1999年第2期23卷 449-463页

作者： Csapodi, Márton Vandewalle, Joos Preneel, Bart Analogic and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences Budapest Hungary ESAT SISTA/COSIC Laboratory Department of Electrical Engineering Katholieke Universiteit Leuven Leuven Belgium

This paper is concerned with the implementation of an image comparison algorithm and cryptographic hash functions on the regular array of cellular neural network (CNN) cells. These operations are necessary for message authentication and copyright protection in the multimedia service environment, serving both the interest of the copyright owner and the user. The basic problems of multimedia protection along with the requirements and role of the different actors in a multimedia service environment are also described here.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image recognition in context: application to microscopic urinalysis 99

Image recognition in context: application to microscopic uri...

引用

Proceedings of the 13th International Conference on neural Information Processing systems

作者： Xubo Song Joseph Sill Yaser Abu-Mostafa Harvey Kasdan Department of Electrical and Computer Engineering Oregon Graduate Institute of Science and Technology Beaverton OR Department of Computation and Neural Systems California Institute of Technology Pasadena CA Department of Electrical Engineering California Institute of Technology Pasadena CA International Remote Imaging Systems Inc. Chatsworth CA

We propose a new and efficient technique for incorporating contextual information into object classification. Most of the current techniques face the problem of exponential computation cost. In this paper, we propose a new general framework that incorporates partial context at a linear cost. This technique is applied to microscopic urinalysis image recognition, resulting in a significant improvement of recognition rate over the context free approach. This gain would have been impossible using conventional context incorporation techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptation of current signals with floating-gate circuits

Adaptation of current signals with floating-gate circuits

引用

Proceedings of the International Conference on Microelectronics for neural, Fuzzy and Bio-Inspired systems, MicroNeuro

作者： A. Pesavento T. Horiuchi C. Diorio C. Koch Department of Electrical Engineering California Institute of Technology Pasadena CA USA Zanvyl Krieger Mind/Brain Institute Johns Hopkins University Baltimore MD USA Department of Computer Science and Engineering University of Washington Seattle WA USA Computation and Neural Systems California Institute of Technology Pasadena CA USA

In this paper we present a new, adaptive spatial-derivative circuit for use in CMOS image sensors. The circuit removes its offset as a natural part of its operation using a combination of electron tunneling and hot-electron injection to add or remove charge on a floating-gate of an auto-zeroing amplifier. We designed fabricated and successfully tested a chip with the circuit. Test results show that the circuit reduces the offsets by more than an order of magnitude.

关键词： Tunneling Circuit testing Very large scale integration Fabrication CMOS technology Photoreceptors Circuit noise Silicon Rain computer science

来源：评论

学校读者我要写书评

暂无评论

Invertible operations on a Cellular neural Network Universal Machine

引用

International Journal of Circuit Theory and Applications 1999年第6期26卷

作者： Márton Csapodi Joos Vandewalle Tamás Roska Analogic and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences P.O. Box 63 H-1502 Budapest Hungary ESAT Laboratory Department of Electrical Engineering Katholieke Universiteit Leuven K. Mercierlaan 94 B-3001 Leuven Belgium

This paper is concerned with the invertibility of parallel operations definable on two-dimensional binary arrays by means of a local Boolean function. In this way, it contributes to the theory of cellular automata and may open new potentialities to cellular neural network applications. We provide a theoretically new approach to the invertibility of two-dimensional additive maps which can be used to obtain detailed information on the behaviour of these operations. Other ways to make invertible operations are also investigated, including local maps which are additive in only one of the terms, and second-order cellular automata. The discussed techniques yield a rich variety of invertible operations on infinite and/or finite two-dimensional binary arrays. When implemented on CNN Universal Chips, all of these operations, performed by TeraOPS speed, become subroutines of a 2D analogic algorithm. These operations can be used in 2D cryptography. © 1998 John Wiley & Sons, Ltd.

关键词： CNN universal machine two-dimensional CA additive maps complementary landscapes

来源：评论

学校读者我要写书评

暂无评论

Localized subspace pattern classification

Localized subspace pattern classification

引用

International Joint Conference on neural Networks (IJCNN)

作者： T. Balachander R. Kothari Department of Electrical & Computer Engineering & Computer Science Artificial Neural Systems Laboratory University of Cincinnati Cincinnati OH USA

Subspace classifiers assume that different output classes primarily lie in different subspaces of the original feature space. Hence, associated with each output class is a projection subspace. The class discriminant function is then the projected distance of a given input vector onto these subspaces (each subspace can be uniquely specified by a projection matrix), the input vector being classified into that class on whose subspace it gives maximal projection. We extend this basic model of a subspace classifier allowing different submanifolds to be associated with a single class. We define a new cost function which incorporates the notion of local manifolds. To obtain the different local submanifolds for each class, we 'cluster' the input space and then compute the projection submanifolds for each class in each cluster. The clustering in the feature space is dependent on the associated class labels of the training examples and proceeds to minimize the overall cost function. Simulation results on standard data sets are used to demonstrate the efficacy of the proposed method.

关键词： Pattern classification Pattern recognition Cost function Vectors Piecewise linear techniques Nearest neighbor searches Laboratories computer science Computational modeling Image coding

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：