检索结果-内蒙古大学图书馆

On the optimal structure design of multilayer feedforward neural networks for pattern recognition

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2002年第4期16卷 375-398页

作者： Chen, DQ Burrell, P S Bank Univ Knowledge Based Syst Ctr Sch Comp Informat Syst & Math London SE1 0AA England

In this survey paper, the-state-of-the-art of the optimal structure design of Multilayer Feedforward Neural Network (MFNN) for pattern recognition is reviewed. Special emphasis is laid on the scale-limited MFNN and the internal representation and decision boundary-based design methodologies. A comprehensively comparative study of the main characteristics of each method is presented. Also, future research directions are outlined.

关键词： multilayer feedforward neural network multilayer perceptron internal representation pruning algorithm genetic algorithm constructive algorithm discriminant decision machine learning support vector machine

来源：评论

学校读者我要写书评

暂无评论

Identification of factors governing mechanical properties of TRIP-aided steel using genetic algorithms and neural networks

引用

MATERIALS AND MANUFACTURING PROCESSES 2008年第2期23卷 130-137页

作者： Datta, Shubhabrata Pettersson, Frank Ganguly, Subhas Saxen, Henrik Chakraborti, Nirupam Bengal Engn & Eci Univ Sch Mat Sci & Engn Sibpur 711103 Howrah India Abo Akad Univ Fac Technol Heat Engn Labb Turku Finland Indian Inst Technol Dept Metallurg & Mat Engn Kharagpur West Bengal India

Mechanical properties of transformation induced plasticity (TRIP)-aided multiphase steels are modeled by neural networks using two methods of reducing the network connectivity, viz. a pruning algorithm and a predator prey algorithm, to gain understanding on the impact of steel composition and treatment. The pruning algorithm gradually reduces the complexity of the lower layer of connections, removing less significant connections. In the predator prey algorithm, a genetic algorithm based multi-objective optimization technique evolves neural networks on a Pareto front, simultaneously minimizing training error and network size. The results show that the techniques find parsimonious models and, furthermore, extract useful knowledge from the data.

关键词： alloy design evolutionary algorithms genetic algorithms multi-objective optimization neural network predator-prey pruning algorithm TRIP-aided steel

来源：评论

学校读者我要写书评

暂无评论

Scenario-Simplified Successive Cancellation Decoding of Polar Codes for Channel With Deletions

引用

IEEE ACCESS 2019年 7卷 18172-18182页

作者： Tian, Kuangda Liu, Rongke Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China

Successive cancellation-based decoding algorithm and corresponding polarization theorems for polar codes over channels with deletions have been proposed recently. In that decoding algorithm, each node in the conventional successive cancellation decoding trellis is divided into many different scenarios according to different deletion patterns. The number of scenarios increases with the square of the number of deletion errors d which results in high decoding complexity. In this paper, to reduce the decoding complexity, we propose the scenario-simplified successive cancellation decoding algorithm for the polar codes over the deletion channel. In the proposed decoding algorithm, we use exact upper and lower bounds to identify the feasible scenarios of each node in the decoding trellis and avoid calculating the impossible scenarios. And by rearranging the scenario index table, the operations of calculating indices of scenarios can be simplified. We also investigate the joint-weight for each scenario. By setting a threshold tau to prune the scenarios with low joint-weight probabilities, the complexity can be reduced further. For polar codes of length N = 512 and d = 10, we can reduce 42.5% stored scenarios and 46.8% computed scenarios when tau = 10(-5) with a negligible performance loss.

关键词： Polar codes successive cancellation decoding deletion channel low-complexity pruning algorithm

来源：评论

学校读者我要写书评

暂无评论

A new algorithm to design compact two-hidden-layer artificial neural networks

引用

NEURAL NETWORKS 2001年第9期14卷 1265-1278页

作者： Islam, MM Murase, K Univ Fukui Dept Human & Artificial Intelligence Syst Fukui 9108507 Japan

This paper describes the cascade neural network design algorithm (CNNDA), a new algorithm for designing compact, two-hidden-layer artificial neural networks (ANNs). This algorithm determines an ANN's architecture with connection weights automatically. The design strategy used in the CNNDA was intended to optimize both the generalization ability and the training time of ANNs. In order to improve the generalization ability, the CNDDA uses a combination of constructive and pruning algorithms and bounded fan-ins of the hidden nodes. A new training approach, by which the input weights of a hidden node are temporarily frozen when its output does not change much after a few successive training cycles, was used in the CNNDA for reducing the computational cost and the training time. The CNNDA was tested on several benchmarks including the cancer, diabetes and character-recognition problems in ANNs. The experimental results show that the CNNDA can produce compact ANNs with good generalization ability and short training time in comparison with other algorithms. (C) 2001 Elsevier Science Ltd. All rights reserved.

关键词： constructive algorithm pruning algorithm weight freezing generalization ability training time

来源：评论

学校读者我要写书评

暂无评论

Fast Trajectory Generation and Asteroid Sequence Selection in Multispacecraft for Multiasteroid Exploration

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第7期52卷 6071-6082页

作者： Qi, Naiming Fan, Zichen Huo, Mingying Du, Desong Zhao, Ce Harbin Inst Technol Sch Astronaut Harbin 150001 Peoples R China

As an increasing number of asteroids are being discovered, detecting them using limited propulsion resources and time has become an urgent problem in the aerospace field. However, there is no universal fast asteroid sequence selection method that finds the trajectories for multiple low-thrust spacecraft for detecting a large number of asteroids. Furthermore, the calculation efficiency of the traditional trajectory optimization method is low, and it requires a large number of iterations. Therefore, this study combines Monte Carlo tree search (MCTS) with spacecraft trajectory optimization. A fast MCTS pruning algorithm is proposed, which can quickly complete asteroid sequence selection and trajectory generation for multispacecraft exploration of multiple asteroids. By combining the Bezier shape-based (SB) method and MCTS, this study realizes the fast search of the exploration sequence and the efficient optimization of the continuous transfer trajectories. In the simulation example, compared with the traversal algorithm, the MCTS pruning algorithm obtained the global optimal detection sequence of the search tree in a very short time. Under the same conditions, the Bezier SB method obtained the transfer trajectory with a better performance index faster than the finite Fourier series SB method. Performances of the proposed method are illustrated through a complex asteroid multiflyby mission design.

关键词： Solar system Trajectory Space vehicles Acceleration Performance analysis Trajectory optimization Monte Carlo methods Bezier shape-based (SB) method low-thrust trajectory generation Monte-Carlo tree search multiasteroid exploration multispacecraft pruning algorithm

来源：评论

学校读者我要写书评

暂无评论

Boundary recovery for conforming Delaunay triangulation of curved complexes

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2012年第5期6卷 324-330页

作者： Cerqueira, A. M. L. G. Lisboa, A. C. Mesquita, R. C. Univ Fed Minas Gerais Grad Program Elect Engn BR-31270901 Belo Horizonte MG Brazil

This study presents a method to recover boundaries of Delaunay meshes conformed to curved geometries. The method uses a topological property to identify simplices and to insert Steiner points into the initial mesh before its refinement. A pruning algorithm is introduced to avoid unnecessary predicate tests. Its implementation is both effective and efficient.

关键词： mesh generation geometry topology Finite element analysis Delaunay mesh boundaries topological property pruning algorithm Numerical analysis Delaunay triangulation Combinatorial mathematics Numerical approximation and analysis curved complexes curved geometries Geometry, differential geometry, and topology

来源：评论

学校读者我要写书评

暂无评论

Efficient Sorting Architecture for List-Fast-SSC Decoding of Polar Codes

引用

IEEE ACCESS 2018年 6卷 61773-61781页

作者： Zhang, Xiaojun Sui, Rongquan Cui, Jianming Zhang, Dexue Zeng, Qingtian Shandong Univ Sci & Technol Coll Elect Commun & Phys Qingdao 266590 Peoples R China

Polar codes have been proven to achieve the symmetric capacity of memoryless channel. Compared with a successive cancellation list decoder, list-Fast simplified-successive cancellation generates more candidate paths, which leads to more resource costs and higher decoding latency. To remedy this drawback, we present a simplified sorting architecture. An M*L ordered candidate path matrix is constructed by preliminary sorter, where M and L denote the number of candidate path expanded by one constituent code and the list size of the decoder, respectively. Then, we eliminate the candidate paths that are definitely not in the L best paths by the proposed lossless pruning algorithm. Finally, a compatible sorting network combining the advantages of bitonic sorter and odd-even sorter is proposed. Numerical results show that for L = 32 and M = 8, the proposed architecture can reduce 66.7% of candidate paths and save 52.3% of compare and swap units (CASUs) and 25% of CASU stages compared with the odd-even sorter.

关键词： List-Fast-SSC ordered candidate path matrix pruning algorithm compatible sorting network

来源：评论

学校读者我要写书评

暂无评论

Method for the selection of inputs and structure of feedforward neural networks

引用

COMPUTERS & CHEMICAL ENGINEERING 2006年第6-7期30卷 1038-1045页

作者： Saxen, H. Pettersson, F. Abo Akad Univ Fac Technol FIN-20500 Turku Finland

Feedforward neural networks of multi-layer perception type can be used as nonlinear black-box models in data-mining tasks. Common problems encountered are how to select relevant inputs from a large set of variables that potentially affect the outputs to be modeled, as well as high levels of noise in the data sets. In order to avoid over-fitting of the resulting model, the input dimension and/or the number of hidden nodes have to be restricted. This paper presents a systematic method that can guide the selection of both input variables and a sparse connectivity of the lower layer of connections in feedforward neural networks of multi-layer perceptron type with one layer of hidden nonlinear units and a single linear output node. The algorithm is illustrated on three benchmark problems. (c) 2006 Published by Elsevier Ltd.

关键词： neural networks detection of relevant inputs pruning algorithm

来源：评论

学校读者我要写书评

暂无评论

A Simplified Sphere Decoding-Based Detector for Generalized SCMA Codebooks

引用

IEEE ACCESS 2022年 10卷 516-534页

作者： Fu, Xiaotian Le Ruyet, Didier Fontana Da Silva, Bruno Uchoa-Filho, Bartolomeu F. CNAM CEDRIC LAETITIA F-75141 Paris France Magazine Luiza Adv Analyt BR-93804870 Sao Paulo Brazil Univ Fed Santa Catarina GPqCom LCS EEL BR-88040900 Florianopolis SC Brazil

Sparse code multiple access (SCMA) is one of the promising schemes to meet high connectivity and spectral efficiency in the future wireless networks. The iterative detectors, for example message passing algorithm (MPA), can provide near optimal multiuser detection (MUD) performance but becomes infeasible when the codebook size is large or the overloading factor is high. Recently, sphere decoding (SD) has been considered in the MUD of SCMA by rewriting the generalized transmission into a linear system. In this work, we first review the state-of-the-art SD-based detectors for SCMA: sphere decoding for SCMA (SD-SCMA) and generalized SD-SCMA (GSD-SCMA). We not only explain the state-of-the-art in a comprehensive way, but also exploit the sorted QR decomposition and Schnorr-Euchner enumeration to accelerate the tree search. Although GSD-SCMA overcomes the codebook constraint of SD-SCMA, its computational complexity is extremely sensitive to the overloading factor. To satisfy the trade-off between complexity and MUD performance, we propose two pruning algorithms, PRUN1 and PRUN2, and introduce the simplified GSD-SCMA (SGSD-SCMA). In the paper, error probabilities of the proposed pruning algorithms are derived. Simulation results show that the proposed detector outperforms the iterative detectors and SD-based state-of-the-art when the overloading factor is moderate and the codebook size is large.

关键词： Detectors Multiuser detection Uplink NOMA Iterative decoding Receivers Computational complexity SCMA sphere decoding pruning algorithm float-point operations

来源：评论

学校读者我要写书评

暂无评论

Designing high strength multi-phase steel for improved strength-ductility balance using neural networks and multi-objective genetic algorithms

引用

ISIJ INTERNATIONAL 2007年第8期47卷 1195-1203页

作者： Datta, Shubhabrata Pettersson, Frank Ganguly, Subhas Saxen, Henrik Chakraborti, Niruopam Bengal Engn & Sci Univ Sch Mat Sci & Engn Howrah 711103 India Abo Akad Univ Fac Chem Engn Heat Engn Lab FIN-20500 Turku Finland Indian Inst Technol Dept Met & Mat Engn Kharagpur 721302 W Bengal India

The properties of steels depend in a complex way on their composition and heat treatment and neural networks have therefore recently been widely used for capturing these relationships. Two different methods of reducing the network connectivity, viz a pruning algorithm and a multi-objective predator prey genetic algorithm, have been used for neural network modeling of the mechanical properties of high strength steels, so that relevant connections within the networks are revealed. This provides important understanding on the variables and their relationship with mechanical properties, In the pruning algorithm the lower layer of the network is gradually reduced by removing less significant connections. In the predator prey algorithm, a genetic algorithm based multi-objective optimization technique is used to train the neural network and a Pareto front is developed by minimizing the training error along with the network size. The results of both techniques reveal that they can extract more knowledge from the data, which is difficult to obtain from conventional neural models. The relative relevance of the composition and processing parameters detected could be used for designing steel with tailored property balance. The results developed by the two techniques are also found to be comparable.

关键词： high strength multiphase steel neural network model pruning algorithm genetic algorithm multi-objective optimization predator prey algorithm alloy design

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：