检索结果-内蒙古大学图书馆

A real-coded genetic algorithm for training recurrent neural networks

NEURAL NETWORKS 2001年第1期14卷 93-105页

作者： Blanco, A Delgado, M Pegalajar, MC Univ Granada Dept Comp Sci & Artificial Intelligence ETSI Informat E-18071 Granada Spain

The use of Recurrent Neural Networks is not as extensive as Feedforward Neural Networks. training algorithms for Recurrent Neural Networks, based on the error gradient, are very unstable in their search for a minimum and require much computational time when the number of neurons is high. The problems surrounding the application of these methods have driven us to develop new training tools. In this paper, we present a Real-Coded Genetic Algorithm that uses the appropriate operators for this encoding type to train Recurrent Neural Networks. We describe the algorithm and we also experimentally compare our Genetic Algorithm with the Real-Time Recurrent Learning algorithm to perform the fuzzy grammatical inference. (C) 2001 Elsevier Science Ltd. All rights reserved.

关键词： recurrent neural network fuzzy recurrent neural network training algorithms real-coded genetic algorithm fuzzy grammatical inference fuzzy finite-state automaton

来源：评论

学校读者我要写书评

暂无评论

Optimisation-based training of evolutionary convolution neural network for visual classification applications

引用

IET COMPUTER VISION 2020年第5期14卷 259-267页

作者： Tu, Shanshan Rehman, Sadaqat ur Waqas, Muhammad Rehman, Obaid ur Yang, Zhongliang Ahmad, Basharat Halim, Zahid Zhao, Wei Beijing Univ Technol Fac Informat Technol Beijing Peoples R China Beijing Geosci Ctr Schlumberger Peoples R China Ghulam Ishaq Khan Inst Engn Sci & Technol Fac Comp Sci & Engn Khyber Pakhtunkhwa Peoples R China Sarhad Univ Sci & IT Dept Elect Engn Peshawar Pakistan Tsinghua Univ Dept Elect Engn Beijing Peoples R China Ghulam Ishaq Khan Inst Engn Sci & Technol Machine Intelligence Res Grp MInG Khyber Pakhtunkhwa 23640 Pakistan Beijing Electromech Engn Inst Beijing 100074 Peoples R China Namal Inst Dept Comp Sci Mianwali 42250 Pakistan

training of the convolution neural network (CNN) is a problem of global optimisation. This study proposed a hybrid modified particle swarm optimisation (MPSO) and conjugate gradient (CG) algorithm for efficient training of CNN. The training involves MPSO-CG to avoid trapping in local minima. Particularly, improvements in the MPSO by introducing a novel approach for control parameters, improved parameters updating criteria, a novel parameter in the velocity update equation, and fusion of the CG allows handling the issues in training CNN. In this study, the authors validate the proposed MPSO algorithm on three benchmark mathematical test functions and also compared with three different variants of the baseline particle swarm optimisation algorithm. Furthermore, the performance of the proposed MPSO-CG is also compared with other training algorithms focusing on the analysis of computational cost, convergence, and accuracy based on a standard problem specific to classification applications on CIFAR-10 dataset and face and skin detection dataset.

关键词： baseline particle swarm optimisation algorithm particle swarm optimisation evolutionary convolution neural network visual classification applications convolutional neural nets velocity update equation training algorithms optimisation MPSO–CG improved parameters MPSO algorithm control parameters optimisation-based training training CNN image classification global optimisation

来源：评论

学校读者我要写书评

暂无评论

A fast training algorithm for RBF networks based on subtractive clustering

引用

NEUROCOMPUTING 2003年第4期51卷 501-505页

作者： Sarimveis, H Alexandridis, A Bafas, G Natl Tech Univ Athens Sch Chem Engn Athens 15780 Greece

A new algorithm for training radial basis function neural networks is presented in this paper. The algorithm, which is based on the subtractive clustering technique, has a number of advantages compared to the traditional learning algorithms, including faster training times and more accurate predictions. Due to these advantages the method proves suitable for developing models for complex nonlinear systems. (C) 2003 Elsevier Science B.V. All rights reserved.

关键词： radial basis function networks training algorithms model selection

来源：评论

学校读者我要写书评

暂无评论

An evaluation of back-propagation neural networks for the optimal design of structural systems: Part I. training procedures

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2002年第25-26期191卷 2873-2886页

作者： Zhang, L Subbarayan, G Univ Colorado Dept Mech Engn Boulder CO 80309 USA

Design optimization using approximations based on feed-forward back-propagation neural network is the topic of much recent research. The neural network schemes that have been proposed in the literature for optimal design of structural systems differ in their architecture and training procedures. Furthermore, their utility vis-a-vis classical optimization techniques is not always clear. A systematic comparison of the efficiency and accuracy of the neural network-based solution schemes to classical structural optimization techniques is the aim of this and the companion paper. In this paper. the neural network training procedures used in the present evaluation are described in detail. When using first-order nonlinear programming algorithms with neural networks, the ability to approximate derivatives is important. Therefore, mainly for completeness of evaluation, two new training methods that use the derivative information are proposed in addition to the now common function-based training method, The first method uses the derivatives to create additional training points in the vicinity of the original points, based on Taylor's series expansion. The second method attempts to minimize the error in derivatives while imposing the error in Output functions as constraint. Expressions for analytical derivatives are derived for both function-based and derivative-based training. Significant savings in computational time are reported when calculating derivatives using built-in analytical derivatives instead of using finite difference derivatives. In the companion paper the proposed methods are applied to solve five optimization problems with varying degree of complexity. Approximately 1100 test cases are executed in the companion paper to compare the accuracy and efficiency of neural network-based optimization with the classical approaches, (C) 2002 Elsevier Science B.V. All rights reserved.

关键词： feed forward neural networks structural optimization training algorithms approximation methods

来源：评论

学校读者我要写书评

暂无评论

ON THE training OF RADIAL BASIS FUNCTION CLASSIFIERS

引用

NEURAL NETWORKS 1992年第4期5卷 595-603页

作者： MUSAVI, MT AHMED, W CHAN, KH FARIS, KB HUMMELS, DM University of Maine USA

An approach for the implementation of the Radial Basis Function (RBF) technique is presented and applied to a network of the appropriate architecture. The paper explores a methodology for selecting kernel function parameters and the extent to which the number of RBF nodes can be reduced without significantly affecting the overall training error These objectives are accomplished through algorithms that shall be described in detail. Emphasis is also placed on the problems faced by a technique that has been proved superior to the more traditional training algorithms, particularly in terms of processing speed and solvability of nonlinear patterns. Solutions are consequently proposed in view of making RBF a more efficient method for interpolation and classification purposes.

关键词： NEURAL NETWORK CLASSIFIERS RADIAL BASIS FUNCTIONS training algorithms

来源：评论

学校读者我要写书评

暂无评论

A survey of artificial neural network training tools

引用

NEURAL COMPUTING & APPLICATIONS 2013年第3-4期23卷 609-615页

作者： Baptista, Dario Morgado-Dias, Fernando Univ Madeira Madeira Interact Technol Inst P-9000390 Funchal Portugal Univ Madeira Competence Ctr Exact Sci & Engn P-9000390 Funchal Portugal

Artificial neural networks (ANN) are currently an additional tool which the engineer can use for a variety of purposes. Classification and regression are the most common tasks;however, control, modeling, prediction and forecasting are common tasks as well. For over three decades, the field of ANN has been the center of intense research. As a result, one of the outcomes has been the development of a large set of software tools used to train these kinds of networks, making the selection of an adequate tool difficult for a new user. This paper aims to help the ANN user choose the most appropriate tool for its application by providing a large survey of the solutions available, as well as listing and explaining their characteristics and terms of use. The paper limits itself to focusing on the tools which were developed for ANN and the relevant characteristics of these tools, such as the operating systems, hardware requirements, license types, architectures and algorithms available.

关键词： Artificial neural networks training tools training algorithms Software

来源：评论

学校读者我要写书评

暂无评论

Cutting-plane training of structural SVMs

引用

MACHINE LEARNING 2009年第1期77卷 27-59页

作者： Joachims, Thorsten Finley, Thomas Yu, Chun-Nam John Cornell Univ Dept Comp Sci Ithaca NY 14853 USA

Discriminative training approaches like structural SVMs have shown much promise for building highly complex and accurate models in areas like natural language processing, protein structure prediction, and information retrieval. However, current training algorithms are computationally expensive or intractable on large datasets. To overcome this bottleneck, this paper explores how cutting-plane methods can provide fast training not only for classification SVMs, but also for structural SVMs. We show that for an equivalent "1-slack" reformulation of the linear SVM training problem, our cutting-plane method has time complexity linear in the number of training examples. In particular, the number of iterations does not depend on the number of training examples, and it is linear in the desired precision and the regularization parameter. Furthermore, we present an extensive empirical evaluation of the method applied to binary classification, multi-class classification, HMM sequence tagging, and CFG parsing. The experiments show that the cutting-plane algorithm is broadly applicable and fast in practice. On large datasets, it is typically several orders of magnitude faster than conventional training methods derived from decomposition methods like SVM-light, or conventional cutting-plane methods. Implementations of our methods are available at http://***.

关键词： Structural SVMs Support vector machines Structured output prediction training algorithms

来源：评论

学校读者我要写书评

暂无评论

A discriminative training algorithm for VQ-based speaker identification

引用

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING 1999年第3期7卷 353-356页

作者： He, JL Liu, L Palm, G Univ Ulm Abt Neuroinformat D-89069 Ulm Germany

A novel method, referred to as group vector quantization (GVQ), is proposed to train VQ codebooks for closed-set speaker identification, In GVQ training, speaker codebooks are optimized for vector groups rather than for individual vectors. An evaluation experiment has been conducted to compare the codebooks trained by the Linde-Buzo-Grey (LBG), the learning vector quantization (LVQ), and the GVQ algorithms. It is shown that the frame scores from the GVQ trained codebooks are Less correlated, therefore, the sentence level speaker identification rate increases more quickly with the length of test sentences.

关键词： neural networks speaker identification training algorithms vector quantization

来源：评论

学校读者我要写书评

暂无评论

ADVANCED ADAPTIVE NONMONOTONE CONJUGATE GRADIENT training ALGORITHM FOR RECURRENT NEURAL NETWORKS

引用

INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS 2008年第5期17卷 963-984页

作者： Peng, Chun-Cheng Magoulas, George D. Univ London Birkbeck Coll Sch Comp Sci & Informat Syst London WC1E 7HX England

Recurrent networks constitute an elegant way of increasing the capacity of feed forward networks to deal with complex data in the form of sequences of vectors. They are well known for their power to model temporal dependencies and process sequences for classification, recognition, and transduction. In this paper we propose an advanced nonmonotone Conjugate Gradient training algorithm for recurrent neural networks, which is equipped with an adaptive tuning strategy for both the nonmonotone learning horizon and the stepsize. Simulation results in sequence processing using three different recurrent architectures demonstrate that this modification of the Conjugate Gradient method is more effective than previous attempts.

关键词： Conjugate gradient methods global convergence nonmonotone linesearch adaptive learning training algorithms recurrent neural networks sequence processing

来源：评论

学校读者我要写书评

暂无评论

A Computationally Efficient Second Order Deep Learning training Algorithm with Adaptive Momentum 24

A Computationally Efficient Second Order Deep Learning Train...

引用

13th Hellenic Conference on Artificial Intelligence

作者： Sakketou, Flora Ampazis, Nicholas Lufthansa Grp Digital Hangar Frankfurt Germany Univ Aegean Dept Financial & Management Engn Chios Greece

ISBN: (纸本)9798400709821

In this paper we evaluate the performance of an efficient second order algorithm for training deep neural networks. Unlike traditional SGD with momentum, the algorithm incorporates two significant modifications originating from treating the training task as a constrained optimization problem: Firstly, it scales the momentum term with curvature information, derived from the Hessian. Secondly, it dynamically adjusts coefficients for the learning rate and the scaled momentum term. The implementation of the algorithm requires minimal additional computations compared to classical SGD with momentum iterations since it only involves computing a Hessian-vector product rather than the entire Hessian matrix, which can be efficiently computed within any modern computational graph framework. We present experimental results on various neural network architectures trained on standard benchmarks which demonstrate the effectiveness of the proposed approach.

关键词： training algorithms Deep Neural Networks Optimization

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：