AN IMPROVED CONTROLLED CHAOTIC NEURAL NETWORK FOR PATTERN RECOGNITION
Authors
Abstract:
A sigmoid function is necessary for creation a chaotic neural network (CNN). In this paper, a new function for CNN is proposed that it can increase the speed of convergence. In the proposed method, we use a novel signal for controlling chaos. Both the theory analysis and computer simulation results show that the performance of CNN can be improved remarkably by using our method. By means of this control method, the outputs of the controlled CNN converge to the stored patterns and they are dependent on the initial patterns. We observed that the controlled CNN can distinguish two initial patterns even if they are slightly different. These characteristics imply that the controlled CNN can be used for pattern recognition.
similar resources
an improved controlled chaotic neural network for pattern recognition
a sigmoid function is necessary for creation a chaotic neural network (cnn). in this paper, a new function for cnn is proposed that it can increase the speed of convergence. in the proposed method, we use a novel signal for controlling chaos. both the theory analysis and computer simulation results show that the performance of cnn can be improved remarkably by using our method. by means of this...
full textAn Evaluation of Mahalanobis-Taguchi System and Neural Network for Multivariate Pattern Recognition
The Mahalanobis-Taguchi System is a diagnosis and predictive method for analyzing patterns in multivariate cases. The goal of this study is to compare the ability of the Mahalanobis- Taguchi System and a neural-network to discriminate using small data sets. We examine the discriminant ability as a function of data set size using an application area where reliable data is publicly available. The...
full textAn Improved Fuzzy Neural Network for Solving Uncertainty in Pattern Classification and Identification
Dealing with uncertainty is one of the most critical problems in complicatedpattern recognition subjects. In this paper, we modify the structure of a useful UnsupervisedFuzzy Neural Network (UFNN) of Kwan and Cai, and compose a new FNN with 6 types offuzzy neurons and its associated self organizing supervised learning algorithm. Thisimproved five-layer feed forward Supervised Fuzzy Neural Netwo...
full textIdeal Chaotic Pattern Recognition Using the Modified Adachi Neural Network
The benchmark of a chaotic Pattern Recognition (PR) system is the following: First of all, one must be able to train the system with a set of “training” patterns. Subsequently, as long as there is no testing pattern, the system must be chaotic. However, if the system is, thereafter, presented with an unknown testing pattern, the behavior must ideally be as follows. If the testing pattern is not...
full textAn Improved Chaotic Maximum Neural Network for Maximum Clique Problem
We propose an improved chaotic maximum neural network to solve maximum clique problem. Through analyzing the character of maximum neural network with an added vertex in maximum clique problem, we find that the quality and size of clique solution can be modified by tuning a parameter about vertex weight. Based on the analysis, a random nonlinear self-feedback and flexible annealing strategy are ...
full textAn Improved Transiently Chaotic Neural Network to Maximum Clique Problem
By analyzing the dynamics behavior and parameter distribution of the transiently chaotic neural network, we propose an improved transiently neural network model with new embedded back-end chaotic dynamics for combinatorial optimization problem and test it on the maximum clique problem. With the new embedded back-end chaotic dynamics, the proposed model can get enough chaotic dynamics to do glob...
full textMy Resources
Journal title
volume 4 issue 3 (SUMMER)
pages 267- 276
publication date 2014-03-21
By following a journal you will be notified via email when a new issue of this journal is published.
Hosted on Doprax cloud platform doprax.com
copyright © 2015-2023