检索结果-内蒙古大学图书馆

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2012年第4期7卷 397-401页

作者： Kobayashi, Masaki Nakajima, Akihiro Univ Yamanashi Interdisciplinary Grad Sch Med & Engn Kofu Yamanashi 4008511 Japan

The quaternary neural network (QNN) proposed by Nitta is a high-dimensional neural network. Nitta showed that its learning is faster than that of ordinary neural networks and the number of required parameters is almost one-third of that of real-valued neural networks by computer simulations. In this paper, we propose the twisted quaternary neural network (TQNN) which modifies the directions of multiplications of the QNN. Since quaternions are noncommutative on multiplication, we can get another neural network. When the activation function is linear, multilayered neural networks can be expressed by single-layered neural networks. But the TQNN cannot be expressed by a single-layered QNN even if the activation function is linear. Therefore, the TQNN is expected to produce a variety of signal-processing systems. We performed computer simulations to compare the QNN and the TQNN. Then we found that the latter's learning is a little faster. Moreover, computer simulation showed that the QNN tended to be trapped in local minima or plateaus but the TQNN did not. It is said that reducibility causes local minima and plateaus. We discuss the differences of reducibility between the QNN and the TQNN as well. (c) 2012 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

关键词： neural networks quaternion learning backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Bayesian Regularization and Levenberg-Marquardt Training algorithm for Localization in Wireless Sensor Network

Comparative Analysis of Bayesian Regularization and Levenber...

引用

International Conference on Advanced Communication Technology

作者： Ashish Payal C. S. Rai B. V. R. Reddy University School of Information & Communication Technology GGS Indraprastha University New Delhi India

ISBN: (纸本)9781467331487

Wireless sensor networks (WSNs) have many applications in the field of disaster management, military, healthcare and environmental monitoring. Capability of WSNs is further enhanced by the efficient localization algorithms. Localization is the process by which a sensor node determines its own location after deployment. Neural approaches are gaining popularity in evolving new localization algorithms that are capable of optimizing various parameters of WSNs. In this paper, we analyse two backpropagation algorithms based on multi-layer Perceptron (MLP) neural network. The network is trained using static sensor nodes placed in a grid with their coordinates known. The input values are distances from each anchor nodes to a particular sensor node. The output is the actual coordinates of the sensor nodes. After training, the network will be able to predict the coordinates of unknown sensor nodes. This MLP model is analyzed for Bayesian regularization and Levenberg-Marquardt training algorithm. Both algorithms are tested for the robustness and cross-validation. The simulation results demonstrate the effectiveness of the proposed model on localization error.

关键词： Localization Wireless Sensor Network backpropagation algorithm Neural network Bayesian regularization

来源：评论

学校读者我要写书评

暂无评论

IP Core Based Hardware Implementation of Multi-layer Perceptrons on FPGAs: A Parallel Approach

IP Core Based Hardware Implementation of Multi-layer Percept...

引用

International Conference on Materials Science and Information Technology (MSIT 2011)

作者： Li, Xiaojun Li, Lin S China Univ Technol Sch Mech & Automot Engn Guangzhou Guangdong Peoples R China

ISBN: (纸本)9783037853191

There're many models derived from the famous bio-inspired artificial neural network (ANN). Among them, multi-layer perceptron (MLP) is widely used as a universal function approximator. With the development of EDA and recent research work, we are able to use rapid and convenient method to generate hardware implementation of MLP on FPGAs through pre-designed IP cores. In the mean time, we focus on achieving the inherent parallelism of neural networks. In this paper, we firstly propose the hardware architecture of modular IP cores. Then, a parallel MLP is devised as an example. At last, some conclusions are made.

关键词： Artificial Neural Network (ANN) FPGA hardware implementation backpropagation algorithm IP cores

来源：评论

学校读者我要写书评

暂无评论

Neural Network & Genetic algorithm Based Approach to Network Intrusion Detection & Comparative Analysis of Performance

Neural Network & Genetic Algorithm Based Approach to Network...

引用

15th International Conference on Computer and Information Technology (ICCIT)

作者： Pal, Biprodip Hasan, Md. Al Mehedi Rajshahi Univ Engn & Technol Dept Comp Sci & Engn Rajshahi Bangladesh

ISBN: (纸本)9781467348362;9781467348331

In this paper backpropagation learning algorithm and genetic algorithm is applied for network intrusion detection and also to classify the detected attacks into proper types. During the training process of the backpropagation algorithm two possible set of features in the rule sets are used separately to determine proper rule set features for better performance. Then the performance of genetic algorithm is compared to the performance of both of the backpropagation approach. The process is tested on training dataset as well as test dataset to analyze the performance. It is found that in detecting the attack connections backpropagation algorithm shows better performance but in classifying the detected attacks into proper types the genetic algorithm approach is more successful.

关键词： backpropagation algorithm Genetic algorithm Intrusion detection Security

来源：评论

学校读者我要写书评

暂无评论

A highly efficient implementation of a backpropagation learning algorithm using matrix ISA

引用

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 2008年第7期68卷 949-961页

作者： Soliman, Mostafa I. Mohamed, Samir A. S Valley Univ Comp & Control Sect Dept Elect Engn Fac Engn Aswan Egypt

backpropagation (BP) is the most famous learning algorithm for Artificial Neural Networks (ANN). BP has received intensive research efforts to exploit its parallelism in order to reduce the training time for complex problems. A modified version of BP based on matrix-matrix multiplication was proposed for parallel processing. In this paper, we present the implementation of Matrix backpropagation (MBP) using scalar, vector, and matrix Instruction Set Architectures (ISAs). Besides this, we show that the performance of the MBP is improved by switching from scalar ISA to vector ISA. It is further improved by switching from vector ISA to matrix ISA. On a practical application, speech recognition, the speedup of training a neural network using unrolling scalar ISA over scalar ISA is 1.83. On eight parallel lanes, the speedups of using vector, unrolling vector, and matrix ISAs are respectively 10.33, 11.88, and 15.36, where the maximum theoretical speedup is 16. The results obtained show that the use of matrix ISA gives a performance close to optimal, because of reusing the loaded data, decreasing the loop overhead, and overlapping the memory operations with arithmetic operations. (c) 2008 Elsevier Inc. All rights reserved.

关键词： neural networks parallel architecture vector/matrix processing parallel algorithms backpropagation algorithm reusing data loop unrolling

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Parallel backpropagation Learning algorithm for Multilayer Perceptrons

An Enhanced Parallel Backpropagation Learning Algorithm for ...

引用

7th World Congress on Intelligent Control and Automation

作者： Ting, Li Min, Wu Cent S Univ Sch Informat Sci & Engn Changsha Hunan Peoples R China

ISBN: (纸本)9781424421138

backpropagation learning algorithm for multilayer perceptrons (MLPs) has disadvantages of slow convergence and easily being trapped into local optimum. Inspired by efficient global searching ability of particle swarm optimization (PSO), a novel PSO based backpropagation learning algorithm (PSO-BP) is proposed. At first, training procedure for MLPs is formulated as nonlinear optimization problem that can be processed by PSO. Then, combination of PSO learning and BP learning is used to train architecture and weights of MLPs. By using particle update equations, PSO learning provides optimal architecture and weights under the condition of input and desired output that are known. BP learning provides optimal weights of MLPs under the condition of given architecture and initial weights that have been set by PSO learning. The proposed learning algorithm is applied to load forecasting in electric power system. Test results show that the proposed algorithm can effectively avoid to be trapped into local optimum and has faster convergence speed than BP algorithm.

关键词： Neural network Multilayer perceptrons Particle swarm optimization backpropagation algorithm Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Multilayer perceptrons and radial basis function neural network methods for the solution of differential equations: A survey

引用

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2011年第10期62卷 3796-3811页

作者： Kumar, Manoj Yadav, Neha Motilal Nehru Natl Inst Technol Dept Math Allahabad 211004 UP India

Since neural networks have universal approximation capabilities, therefore it is possible to postulate them as solutions for given differential equations that define unsupervised errors. In this paper, we present a wide survey and classification of different Multilayer Perceptron (MLP) and Radial Basis Function (RBF) neural network techniques, which are used for solving differential equations of various kinds. Our main purpose is to provide a synthesis of the published research works in this area and stimulate further research interest and effort in the identified topics. Here, we describe the crux of various research articles published by numerous researchers, mostly within the last 10 years to get a better knowledge about the present scenario. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Differential equations Neural network Multilayer perceptron Radial basis functions backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

WBCD breast cancer database classification applying artificial metaplasticity neural network

引用

EXPERT SYSTEMS WITH APPLICATIONS 2011年第8期38卷 9573-9579页

作者： Marcano-Cedeno, A. Quintanilla-Dominguez, J. Andina, D. Tech Univ Madrid Grp Automat Signals & Commun Madrid Spain

The correct diagnosis of breast cancer is one of the major problems in the medical field. From the literature it has been found that different pattern recognition techniques can help them to improve in this domain. These techniques can help doctors form a second opinion and make a better diagnosis. In this paper we present a novel improvement in neural network training for pattern classification. The proposed training algorithm is inspired by the biological metaplasticity property of neurons and Shannon's information theory. During the training phase the Artificial metaplasticity Multilayer Perceptron (AMMLP) algorithm gives priority to updating the weights for the less frequent activations over the more frequent ones. In this way metaplasticity is modeled artificially. AMMLP achieves a more effcient training, while maintaining MLP performance. To test the proposed algorithm we used the Wisconsin Breast Cancer Database (WBCD). AMMLP performance is tested using classification accuracy, sensitivity and specificity analysis, and confusion matrix. The obtained AMMLP classification accuracy of 99.26%, a very promising result compared to the backpropagation algorithm (BPA) and recent classification techniques applied to the same database. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Neural network backpropagation algorithm Pattern recognition Metaplasticity Breast cancer AMMLP

来源：评论

学校读者我要写书评

暂无评论

Influence of the input layer signals of ANNs on wind power estimation for a target site: A case study

引用

RENEWABLE & SUSTAINABLE ENERGY REVIEWS 2011年第3期15卷 1556-1566页

作者： Velazquez, Sergio Carta, Jose A. Matias, J. M. Univ Las Palmas Gran Canaria Dept Mech Engn Las Palmas Gran Canaria 35017 Canary Islands Spain Univ Las Palmas Gran Canaria Dept Elect & Automat Engn Las Palmas Gran Canaria 35017 Canary Islands Spain Univ Vigo Dept Stat Vigo 36200 Spain

In the scientific literature concerning renewable energies there have been proposals for the use of Artificial Neural Networks (ANNs) as a tool to estimate the mean wind speed at a target station for which only incomplete data series are available. In general terms, the wind speeds recorded at neighbouring reference stations are used as signals of the input layer of multilayer perceptron (MLP) architectures. An analysis is undertaken in this paper of the extent to which estimation of the wind speed, the wind power density and the power output of an installed wind turbine at a target site is affected by the number of reference stations, the degree of correlation between the wind speeds of the reference stations and the target station, the wind direction and the manner in which the direction signal is introduced into the input layer. For the purposes of this study mean hourly wind speeds and directions were used which had been recorded at twenty two weather stations located in the Canary Archipelago (Spain) in 2002 and 2006. The power-wind speed characteristic curves of five wind turbines of different rated power were also used. The MLP architectures were trained using the backpropagation algorithm. Amongst other conclusions reached with the tests performed with the set of data not used in the training nor in the validation of the models is that the estimation errors tend to decrease as the number of reference stations used increases, independently of the existing correlation coefficient values between the reference stations and the candidate station. It was also observed that if input signals of angular wind direction and wind speed are used then the number of reference stations required to achieve a certain decrease in the error is lower than the number required if only wind speed input signals are used. By using multiple reference stations with input signals of angular wind direction and speed, error reductions have been achieved for some stations in the estimation

关键词： Artificial Neural Networks Wind power estimation Wind direction Multilayer perceptron backpropagation algorithm Mean absolute relative error

来源：评论

学校读者我要写书评

暂无评论

Breast cancer classification applying artificial metaplasticity algorithm

引用

NEUROCOMPUTING 2011年第8期74卷 1243-1250页

作者： Marcano-Cedeno, A. Quintanilla-Dominguez, J. Andina, D. Tech Univ Madrid Grp Automat Signals & Commun Madrid Spain

A novel improvement in neural network training for pattern classification is presented in this paper. The proposed training algorithm is inspired by the biological metaplasticity property of neurons and Shannon's information theory. This algorithm is applicable to artificial neural networks (ANNs) in general, although here it is applied to a multilayer perceptron (MLP). During the training phase, the artificial metaplasticity multilayer perceptron (AMMLP) algorithm assigns higher values for updating the weights in the less frequent activations than in the more frequent ones. AMMLP achieves a more efficient training and improves MLP performance. The well-known and readily available Wisconsin Breast Cancer Database (WBCD) has been used to test the algorithm. Performance of the AMMLP was tested through classification accuracy, sensitivity and specificity analysis, and confusion matrix analysis. The results obtained by AMMLP are compared with the backpropagation algorithm (BPA) and other recent classification techniques applied to the same database. The best result obtained so far with the AMMLP algorithm is 99.63%. (C) 2010 Elsevier B.V. All rights reserved.

关键词： Neural network backpropagation algorithm Pattern recognition Metaplasticity Breast cancer

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：