scholarly journals A New Optimized GA-RBF Neural Network Algorithm

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Weikuan Jia ◽  
Dean Zhao ◽  
Tian Shen ◽  
Chunyang Su ◽  
Chanli Hu ◽  
...  
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Rbf Neural Network ◽  
Lms Algorithm ◽  
Learning Ability ◽  
Operating Efficiency ◽  
Complex Problems ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Hidden Layer

When confronting the complex problems, radial basis function (RBF) neural network has the advantages of adaptive and self-learning ability, but it is difficult to determine the number of hidden layer neurons, and the weights learning ability from hidden layer to the output layer is low; these deficiencies easily lead to decreasing learning ability and recognition precision. Aiming at this problem, we propose a new optimized RBF neural network algorithm based on genetic algorithm (GA-RBF algorithm), which uses genetic algorithm to optimize the weights and structure of RBF neural network; it chooses new ways of hybrid encoding and optimizing simultaneously. Using the binary encoding encodes the number of the hidden layer’s neurons and using real encoding encodes the connection weights. Hidden layer neurons number and connection weights are optimized simultaneously in the new algorithm. However, the connection weights optimization is not complete; we need to use least mean square (LMS) algorithm for further leaning, and finally get a new algorithm model. Using two UCI standard data sets to test the new algorithm, the results show that the new algorithm improves the operating efficiency in dealing with complex problems and also improves the recognition precision, which proves that the new algorithm is valid.

A CONSTRUCTIVE NEURAL NETWORK ALGORITHM FOR FUNCTION APPROXIMATION USING LOCALLY FIT SIGMOIDS

1998 ◽  
Vol 07 (03) ◽  
pp. 373-398
Author(s):  
TIM DRAELOS ◽  
DON HUSH
Keyword(s):  
Neural Network ◽  
Function Approximation ◽  
Piecewise Linear ◽  
Target Function ◽  
Approximation Problem ◽  
Sigmoidal Functions ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Training Error ◽  
Hidden Layer

A study of the function approximation capabilities of single hidden layer neural networks strongly motivates the investigation of constructive learning techniques as a means of realizing established error bounds. Learning characteristics employed by constructive algorithms provide ideas for development of new algorithms applicable to the function approximation problem. In addition, constructive techniques offer efficient methods for network construction and weight determination. The development of a novel neural network algorithm, the Constructive Locally Fit Sigmoids (CLFS) function approximation algorithm, is presented in detail. Basis functions of global extent (piecewise linear sigmoidal functions) are locally fit to the target function, resulting in a pool of candidate hidden layer nodes from which a function approximation is obtained. This algorithm provides a methodology of selecting nodes in a meaningful way from the infinite set of possibilities and synthesizes an n node single hidden layer network with empirical and analytical results that strongly indicate an O(1/n) mean squared training error bound under certain assumptions. The algorithm operates in polynomial time in the number of network nodes and the input dimension. Empirical results demonstrate its effectiveness on several multidimensional function approximate problems relative to contemporary constructive and nonconstructive algorithms.

scholarly journals Application of Elman Neural Network Based on Genetic Algorithm in Initial Alignment of SINS for Guided Projectile

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Lei Sun ◽  
Wenjun Yi ◽  
Dandan Yuan ◽  
Jun Guan
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Navigation System ◽  
Inertial Navigation System ◽  
Inertial Navigation ◽  
Strapdown Inertial Navigation System ◽  
Initial Alignment ◽  
Elman Neural Network ◽  
Network Algorithm ◽  
Neural Network Algorithm

The purpose of this paper is to present an in-flight initial alignment method for the guided projectiles, obtained after launching, and utilizing the characteristic of the inertial device of a strapdown inertial navigation system. This method uses an Elman neural network algorithm, optimized by genetic algorithm in the initial alignment calculation. The algorithm is discussed in details and applied to the initial alignment process of the proposed guided projectile. Simulation results show the advantages of the optimized Elman neural network algorithm for the initial alignment problem of the strapdown inertial navigation system. It can not only obtain the same high-precision alignment as the traditional Kalman filter but also improve the real-time performance of the system.

PBP: A Type of BP Neural Network Algorithm Based on Priori Triggering

2011 ◽  
Vol 271-273 ◽  
pp. 441-447
Author(s):  
Xiao Mei Chen ◽  
Dang Gang ◽  
Tian Yang
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Large Scale ◽  
Learning Ability ◽  
Traffic Flows ◽  
It Use ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Large Scale Networks ◽  
High Level

The algorithm of anomaly detection for large scale networks is a key way to promptly detect the abnormal traffic flows. In this paper, priori triggered BP neural network algorithm(PBP) is analyzed for the purpose of dealing with the problems caused by typical algorithms that are not able to adapt and learn; detect with high precision; provide high level of correctness. PBP uses K-Means and PCA to trigger self-adapting and learning ability, and also, it uses historical neuron parameter to initialize the neural network, so that it use the trained network to detect the abnormal traffic flows. According to experiments, PBP can obtain a higher level of correctness of detection than priori algorithm, and it can adapt itself according to different network environments.

Sign in / Sign up

Export Citation Format

Share Document