检索结果-内蒙古大学图书馆

Exploring constructive cascade networks

IEEE TRANSACTIONS ON NEURAL NETWORKS 1999年第6期10卷 1335-1350页

作者： Treadgold, NK Gedeon, TD Univ New S Wales Sch Engn & Comp Sci Sydney NSW Australia

constructive algorithms have proved to be powerful methods for training feedforward neural networks. An important property of these algorithms is generalization. A series of empirical studies were performed to examine the effect of regularization on generalization in constructive cascade algorithms. It was found that the combination of early stopping and regularization resulted in better generalization than the use of early stopping alone. A cubic penalty term that greatly penalizes large weights was shown to be beneficial for generalization in cascade networks. An adaptive method of setting the regularization magnitude in constructive algorithms was introduced and shown to produce generalization results similar to those obtained with a fixed, user-optimized regularization setting. This adaptive method also resulted in the construction of smaller networks for more complex problems. The acasper algorithm, which incorporates the insights obtained from the empirical studies, was shown to have good generalization and network construction properties. This algorithm was compared to the cascade correlation algorithm on the Proben 1 and additional regression data sets.

关键词： cascade constructive algorithms feedforward neural network generalization regularization

来源：评论

学校读者我要写书评

暂无评论

Navigating mobile robots with a modular neural architecture

引用

NEURAL COMPUTING & APPLICATIONS 2003年第3-4期12卷 200-211页

作者： Silva, C Ribeiro, B Univ Coimbra Ctr Informat & Sistemas P-3030 Coimbra Portugal

Neural architectures have been proposed to navigate mobile robots within several environment definitions. In this paper a new neural modular constructive approach to navigate mobile robots in unknown environments is presented. The problem, in its basic form, consists of defining and executing a trajectory to a predefined goal while avoiding all obstacles, in an unknown environment. Some crucial issues arise when trying to solve this problem, such as an overflow of sensorial information and conflicting objectives. Most neural network (NN) approaches to this problem focus on a monolithic system, i.e., a system with only one neural network that receives and analyses all available information, resulting in conflicting training patterns, long training times and poor generalisation. The work presented in this article circumvents these problems by the use of a constructive modular NN. Navigation capabilities were proven with the NOMAD 200 mobile robot.

关键词： constructive algorithms mobile robot navigation modular neural networks sensor fusion

来源：评论

学校读者我要写书评

暂无评论

A constructive approach to calculating lower entropy bounds

引用

NEURAL PROCESSING LETTERS 1999年第1期9卷 1-12页

作者： Beiu, V Draghici, S De Pauw, T Univ Calif Los Alamos Natl Lab Div NIS 1 Los Alamos NM 87545 USA Wayne State Univ Dept Comp Sci Vis & Neural Networks Lab Detroit MI 48202 USA Univ Catholique Louvain Dept Math B-1348 Louvain Belgium

This paper presents a constructive approach to estimating the size of a neural network necessary to solve a given classification problem. The results are derived using an information entropy approach in the context of limited precision integer weights. Such weights are particularly suited for hardware implementations since the area they occupy is limited, and the computations performed with them can be efficiently implemented in hardware. The considerations presented use an information entropy perspective and calculate lower bounds on the number of bits needed in order to solve a given classification problem. These bounds are obtained by approximating the classification hypervolumes with the volumes of several regular (i.e., highly symmetric) n-dimensional bodies. The bounds given here allow the user to choose the appropriate size of a neural network such that: (i) the given classification problem can be solved, and (ii) the network architecture is not oversized. All considerations presented take into account the restrictive case of limited precision integer weights, and therefore can be directly applied when designing VLSI implementations of neural networks.

关键词： classification problems complexity n-dimensional volumes number of bits limited and integer weights constructive algorithms

来源：评论

学校读者我要写书评

暂无评论

A fill-and-reduce greedy algorithm for the container pre-marshalling problem

引用

OPERATIONAL RESEARCH 2023年第3期23卷 1-29页

作者： Araya, Ignacio Toledo, Martin Pontificia Univ Catolica Valparaiso Ave Brasil 2241 Valparaiso Chile

We address the Container Pre-Marshalling Problem (CPMP). The CPMP consists in ordering containers in stacks such that the retrieval of these containers is carried out without additional movements. The ordering has to be done in a minimum number of steps. Target-guided constructive heuristics report very good results in a short time. At each step, they select one poorly located container and rearrange it to an adequate position by a sequence of movements. The sequence of movements is generally generated by following a set of rules. In this work, we propose a different and more direct approach. Whenever possible, ordered stacks are filled by directly moving badly placed containers into them such that the containers become well placed. If it is not possible, then a stack is emptied or reduced to have more available slots, and the process is repeated. Unlike target-guided algorithms which rigidly adhere to a predefined sequence of movements for each badly placed container, our fill-and-reduce approach maintains the capacity to adapt to the evolving situation making choices based on the current state of the container stacks. The algorithm has shown superior performance compared to traditional target-guided heuristics, particularly in larger instances of classical benchmark sets. Furthermore, when embedded in a beam search algorithm, it reports the best results compared to traditional techniques that do not use machine learning.

关键词： (O) Combinatorial optimization Container premarshalling problem constructive algorithms Beam search transportation

来源：评论

学校读者我要写书评

暂无评论

A multi-output-layer perceptron

引用

NEURAL COMPUTING & APPLICATIONS 1996年第1期4卷 10-20页

作者： Owens, FJ Zheng, GH Irvine, DA Northern Ireland Bioengineering Centre School of Electrical and Mechanical Engineering Faculty of Engineering University of Ulster at Jordanstown Newtownabbey Co. Antrim Northern Ireland

This paper investigates the possibility of improving the classification capability of single-layer and multilayer perceptrons by incorporating additional output layers. This Multi-Output-Layer Perceptron (MOLP) is a new type of constructive network, though the emphasis is on improving pattern separability rather than network efficiency. The MOLP is trained using the standard back-propagation (BP) algorithm. The studies are concentrated on realizations of arbitrary functions which map from an x-dimensional input vector into a y-dimensional output vector. With the MOLP, all problems existing in an original n-dimensional space in the hidden layer are transformed to a higher (n + 1)-dimensional space, so that the possibility of linear separability is increased. Experimental investigations show that the classification ability of the MOLP is superior to that of an equivalent MLP. In general, this performance increase can be achieved with shorter training times and simpler network architectures.

关键词： constructive algorithms multi-output-layer perceptrons neural networks

来源：评论

学校读者我要写书评

暂无评论

Layered_CasPer: Layered Cascade Artificial Neural Networks

Layered_CasPer: Layered Cascade Artificial Neural Networks

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Shen, Tengfei Zhu, Dingyun Australian Natl Univ Res Sch Comp Sci Coll Engn & Comp Sci Canberra ACT Australia

ISBN: (纸本)9781467314909

Previous research has demonstrated that constructive algorithms are powerful methods for training feedforward neural networks. The CasPer algorithm is a constructive neural network algorithm that generates networks from a simple architecture and then expands it. The A_CasPer algorithm is a modified version of the CasPer algorithm which uses a candidate pool instead of a single neuron being trained. This research adds an extension to the A_CasPer algorithm in terms of the network architecture - the Layered_CasPer algorithm. The hidden neurons form as layers in the new version of the network structure which results in less computational cost being required. Beyond the network structure, other aspects of Layered_CasPer are the same as A_CasPer. The Layered_CasPer algorithm extension is benchmarked on a number of classification problems and compared to other constructive algorithms, which are CasCor, CasPer, A_CasPer, and AT_CasPer. It is shown that Layered_CasPer has a better performance on the datasets which have a large number of inputs for classification tasks. The Layered_CasPer algorithm has an advantage over other cascade style constructive algorithms in being more similar in topology to the familiar layered structure of traditional feedforward neural networks.

关键词： Cascade constructive algorithms feedforward neural network CasPer A_CasPer CasCor AT_CasPer Layered_CasPer

来源：评论

学校读者我要写书评

暂无评论

Neural networks for monitoring of engine condition data

引用

Neural Computing & Applications 1993年第1期1卷 96-102页

作者： Cumming, Simon Heathrow Airport Hounslow TW6 2JA British Airways plc E172 United Kingdom

Neural networks are being tested to monitor aircraft engine condition data, in addition to current techniques and newer methods such as knowledge-based systems or case-based reasoning, in order to increase safety and assist in aircraft maintenance activity. It is possible that neural networks can help to measure subtle changes in a wide number of variables, and produce indications of adverse trends to serve as early warning signals. Unsupervised networks were trained on 300 records, each with 31 attributes, and independently validated on 1662 records (the recall set). Results are presented for self-organising maps and recirculation networks. The next phase is to incorporate diagnostic capability by adding a supervised learning element. Monitoring of sensor reliability and the provision of confidence limits are further extensions of these approaches. © 1993 Springer-Verlag London Limited.

关键词： Airline operations Autoassociative recirculation network constructive algorithms Dimensionality reduction Engine condition monitoring Kohonen self-organising map

来源：评论

学校读者我要写书评

暂无评论

B-spline and neuro-fuzzy models design with function and derivative equalities

B-spline and neuro-fuzzy models design with function and der...

引用

5th International Symposium on Intelligent Automation and Control/9th International Symposium on Manufacturing and Applications held at the 6th Biannual World Automation Congress

作者： Cabrita, C Ruano, A Univ Algarve Ctr Intelligent Syst Algarve Portugal

ISBN: (纸本)1889335223

The design of neuro-fuzzy models is still a complex problem, as it involves not only the determination of the model parameters, but also its structure. Of special importance is the incorporation of a priori information in the design process. In this paper two known desigm algorithms for B-spline models will be updated to account for function and derivatives equality restrictions, which am important when the neural model is used for performing single or multi-objective optimization on-line.

关键词： constructive algorithms B-Splines neuro-fuzzy systems genetic programming

来源：评论

学校读者我要写书评

暂无评论

An agent-based evaluation of transit network design 10

An agent-based evaluation of transit network design

引用

10th International Conference on Ambient Systems, Networks and Technologies (ANT) / 2nd International Conference on Emerging Data and Industry 4.0 (EDI40)

作者： Nnene, Obiora A. Joubert, Johan W. Zuidgeest, Mark H. P. Univ Cape Town Fac Engn & Built Environm Ctr Transport Studies Private Bag X3 ZA-7701 Rondebosch South Africa Univ Pretoria Ctr Transport Dev Ind Engn ZA-0083 Pretoria South Africa

This article presents the design and evaluation of transit networks using a route expansion heuristic and agent-based travel demand simulation. The route expansion mechanism is a type of constructive heuristic algorithm that derives new transit routes by inserting neighbouring nodes into existing routes with the aim of improving the demand coverage. The resulting networks are evaluated with an agent-based travel demand simulation model. The use of agent-based modelling is a departure from the existing route expansion literature and indeed the broader transit network design discipline in which the four step model has been extensively used. The procedure is tested on a bus rapid transit network in the City of Cape Town in South Africa. (C) 2019 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND (http://***/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the Conference Program Chairs.

关键词： transit network design agent-based simulation network evaluation route expansion node insertion constructive algorithms

来源：评论

学校读者我要写书评

暂无评论

Programming with BSP Homomorphisms

Programming with BSP Homomorphisms

引用

19th International Conference on Euro-Par

作者： Legaux, Joeffrey Hu, Zhenjiang Loulergue, Frederic Matsuzaki, Kiminori Tesson, Julien Univ Orleans LIFO F-45067 Orleans France Natl Inst Informat Tokyo Japan Kochi Univ Technol Kochi Japan Univ Paris Est LACL Creteil France

ISBN: (纸本)9783642400476

Algorithmic skeletons in conjunction with list homomorphisms play an important role in formal development of parallel algorithms. We have designed a notion of homomorphism dedicated to bulk synchronous parallelism. In this paper we derive two application using this theory: sparse matrix vector multiplication and the all nearest smaller values problem. We implement a support for BSP homomorphism in the Orleans Skeleton Library and experiment it with these two applications.

关键词： Algorithmic skeletons constructive algorithms Bulk synchronous parallelism All nearest smaller values Sparse linear algebra

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：