检索结果-内蒙古大学图书馆

Fusion of multiple fingerprint matchers by single-layer perceptron with class-separation loss function

pattern recognition LETTERS 2005年第12期26卷 1830-1839页

作者： Marcialis, GL Roli, F Univ Cagliari Dept Elect & Elect Engn I-09123 Cagliari Italy

In this paper, a perception-based algorithm for fusion of multiple fingerprint matchers is presented. The person to be identified submits to the personal authentication system her/his fingerprint and claimed identity. Multiple fingerprint matchers provide a set of verification scores, that are then fused by a single-layer perceptron with class-separation loss function. Weights of such perceptron are explicitly optimised to increase the separation between genuine users and impostors (i.e., unauthorized users). Reported experiments show that such modified perceptron allows improving the performances and the robustness of the best individual fingerprint matcher, and outperforming some commonly used fusion rules. (c) 2005 Elsevier B.V. All rights reserved.

关键词： automatic fingerprint verification fusion of multiple fingerprint matchers multiple classifiers systems neural networks pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Probabilistic neural network playing and learning Tic-Tac-Toe

Probabilistic neural network playing and learning Tic-Tac-To...

引用

1st iapr tc3 workshop on artificial neural networks in pattern recognition

作者： Grim, J Somol, P Pudil, P Acad Sci Czech Republic Inst Informat Theory & Automat CZ-18208 Prague Czech Republic

A probabilistic neural network is applied as a tool to approximate the statistical evaluation function for a simple version of the game Tic-Tac-Toe. We solve the problem by a sequential estimation of the underlying di... 详细信息

关键词： probabilistic neural networks distribution mixtures supervised learning sequential EM algorithm weighting of data playing Tic-Tac-Toe

来源：评论

学校读者我要写书评

暂无评论

Wide coverage natural language processing using kernel methods and neural networks for structured data

Wide coverage natural language processing using kernel metho...

引用

1st iapr tc3 workshop on artificial neural networks in pattern recognition

作者： Menchetti, S Costa, F Frasconi, P Pontil, M Univ Florence Dept Comp Sci & Syst I-50139 Florence Italy UCL Dept Comp Sci London WC1E 6BT England

Convolution kernels and recursive neural networks are both suitable approaches for supervised learning when the input is a discrete structure like a labeled tree or graph. We compare these techniques in two natural language problems. In both problems, the learning task consists in choosing the best alternative tree in a set of candidates. We report about an empirical evaluation between the two methods on a large corpus of parsed sentences and speculate on the role played by the representation and the loss function. (c) 2005 Elsevier B.V. All rights reserved.

关键词： convolution kernels recursive neural networks learning preferences natural language

来源：评论

学校读者我要写书评

暂无评论

Recursive neural networks learn to localize faces

Recursive neural networks learn to localize faces

引用

1st iapr tc3 workshop on artificial neural networks in pattern recognition

作者： Bianchini, M Maggini, M Sarti, L Scarselli, F Univ Siena Dipartimento Ingn Informaz I-53100 Siena Italy

Localizing faces in images is a difficult task, and represents the first step towards the solution of the face recognition problem. Moreover, devising an effective face detection method can provide some suggestions to solve similar object and pattern detection problems. This paper presents a novel approach to the solution of the face localization problem using Recursive neural networks (RNNs). The proposed method assumes a graph-based representation of images that combines structural and symbolic visual features. Such graphs are then processed by RNNs, in order to establish the possible presence and the position of faces inside the image. A novel RNN model that can deal with graphs with labeled edges has been also exploited. Some experiments on snapshots from video sequences are reported, showing very promising results. (c) 2005 Elsevier B.V. All rights reserved.

关键词： recursive neural networks face recognition localization of faces

来源：评论

学校读者我要写书评

暂无评论

Probabilistic neural network playing and learning Tic-Tac-Toe

引用

pattern recognition LETTERS 2005年第12期26卷 1866-1873页

作者： Grim, J Somol, P Pudil, P Acad Sci Czech Republic Inst Informat Theory & Automat CZ-18208 Prague Czech Republic

关键词： probabilistic neural networks distribution mixtures supervised learning sequential EM algorithm weighting of data playing Tic-Tac-Toe

来源：评论

学校读者我要写书评

暂无评论

Sign-based learning schemes for pattern classification

Sign-based learning schemes for pattern classification

引用

1st iapr tc3 workshop on artificial neural networks in pattern recognition

作者： Anastasiadis, AD Magoulas, GD Vrahatis, MN Univ London Birkbeck Coll Sch Comp Sci & Informat Syst Knowledge Lab London WC1N 3QS England Univ London Birkbeck Coll Sch Comp Sci & Informat Syst London WC1E 7HX England Univ Patras UPAIRC Dept Math GR-26110 Patras Greece

This paper introduces a new class of sign-based training algorithms for neural networks that combine the sign-based updates of the Rprop algorithm with the composite nonlinear Jacobi method. The theoretical foundations of the class are described and a heuristic Rprop-based Jacobi algorithm is empirically investigated through simulation experiments in benchmark pattern classification problems. Numerical evidence shows that this new modification of the Rprop algorithm exhibits improved learning speed in all cases tested, and compares favorably against the Rprop and a recently proposed modification, the improved Rprop. (c) 2005 Elsevier B.V. All rights reserved.

关键词： supervised learning nonlinear iterative methods nonlinear Jacobi subminimization feed-forward neural networks Rprop pattern classification

来源：评论

学校读者我要写书评

暂无评论

Using unsupervised learning of a finite Dirichlet mixture model to improve pattern recognition applications

Using unsupervised learning of a finite Dirichlet mixture mo...

引用

1st iapr tc3 workshop on artificial neural networks in pattern recognition

作者： Bouguila, N Ziou, D Univ Sherbrooke Fac Sci Dept Informat Sherbrooke PQ J1K 2R1 Canada

Mixture modeling is the problem of identifying and modeling components in a given set of data. Gaussians are widely used in mixture modeling. At the same time, other models such as Dirichlet distributions have not received attention. In this paper, we present an unsupervised algorithm for learning a finite Dirichlet mixture model. The proposed approach for estimating the parameters of a Dirichlet mixture is based on the maximum likelihood (ML) expressed in a Riemannian space. Experimental results are presented for the following applications: summarization of texture image databases for efficient retrieval, and human skin color modeling and its application to skin detection in multimedia databases. (c) 2005 Elsevier B.V. All rights reserved.

关键词： Dirichlet distribution mixture modeling image summarization for efficient retrieval human skin detection

来源：评论

学校读者我要写书评

暂无评论

Polyphonic monotimbral music transcription using dynamic networks

Polyphonic monotimbral music transcription using dynamic net...

引用

1st iapr tc3 workshop on artificial neural networks in pattern recognition

作者： Pertusa, A Inesta, JM Univ Alicante Dept Lenguajes & Sistemas Informat E-03080 Alicante Spain

The automatic extraction of the notes that were played in a digital musical signal (automatic music transcription) is an open problem. A number of techniques have been applied to solve it without concluding results. The monotimbral polyphonic version of the problem is posed here: a single instrument has been played and more than one note can sound at the same time. This work tries to approach it through the identification of the pattern of a given instrument in the frequency domain. This is achieved using time-delay neural networks that are fed with the band-grouped spectrogram of a polyphonic monotimbral music recording. The use of a learning scheme based on examples like neural networks permits our system to avoid the use of an auditory model to approach this problem. A number of issues have to be faced to have a robust and powerful system, but promising results using synthesized instruments are presented. (c) 2005 Elsevier B.V. All rights reserved.

关键词： Computer music

来源：评论

学校读者我要写书评

暂无评论

Time series forecasting: Obtaining long term trends with self-organizing maps

Time series forecasting: Obtaining long term trends with sel...

引用

1st iapr tc3 workshop on artificial neural networks in pattern recognition

作者： Simon, G Lendasse, A Cottrell, M Fort, JC Verleysen, M Univ Catholique Louvain DICE Machine Learning grp B-1348 Louvain Belgium Helsinki Univ Technol Lab Comp & Informat Sci Neural Networks Res Ctr FIN-02015 Espoo Finland Univ Paris 01 CNRS UMR 8595 Samos Matisse F-75634 Paris France Univ Toulouse 3 CNRS C55830 Lab Stat & Probabil F-31062 Toulouse France

Kohonen self-organisation maps are a well know classification tool, commonly used in a wide variety of problems, but with limited applications in time series forecasting context. In this paper, we propose a forecasting method specifically designed for multi-dimensional long-term trends prediction, with a double application of the Kohonen algorithm. Practical applications of the method are also presented. (c) 2005 Elsevier B.V. All rights reserved.

关键词： self-organizing maps time series forecasting long-term trends

来源：评论

学校读者我要写书评

暂无评论

Hybrid generative/discriminative classifier for unconstrained character recognition

Hybrid generative/discriminative classifier for unconstraine...

引用

1st iapr tc3 workshop on artificial neural networks in pattern recognition

作者： Prevost, L Oudot, L Moises, A Michel-Sendis, C Milgram, M Univ Paris 06 Lab Instruments & Syst Ile France Grp PARC F-75252 Paris France

Handwriting recognition for hand-held devices like PDAs requires very accurate and adaptive classifiers. It is such a complex classification problem that it is quite usual now to make co-operate several classification methods. In this paper, we present an original two stages recognizer. The first stage is a model-based classifier which store an exhaustive set of character models. The second stage is a pairwise classifier which separate the most ambiguous pairs of classes. This hybrid architecture is based on the idea that the correct class almost systematically belongs to the two more relevant classes found by the first classifier. Experiments on a 80,000 examples database show a 30% improvement on a 62 classes recognition problem. Moreover, we show experimentally that such an architecture suits perfectly for incremental classification. (c) 2005 Elsevier B.V. All rights reserved.

关键词： handwriting recognition multiple classifier system pairwise neural networks confusion matrix adaptive classifier

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：