You are here
Home > Networks

Advances in Neural Networks – ISNN 2007: 4th International - download pdf or read online

By Hongwei Wang, Hong Gu (auth.), Derong Liu, Shumin Fei, Zengguang Hou, Huaguang Zhang, Changyin Sun (eds.)

ISBN-10: 3540723927

ISBN-13: 9783540723929

ISBN-10: 3540723935

ISBN-13: 9783540723936

This publication is a part of a 3 quantity set that constitutes the refereed lawsuits of the 4th overseas Symposium on Neural Networks, ISNN 2007, held in Nanjing, China in June 2007.

The 262 revised lengthy papers and 192 revised brief papers awarded have been conscientiously reviewed and chosen from a complete of 1,975 submissions. The papers are prepared in topical sections on neural fuzzy keep watch over, neural networks for regulate functions, adaptive dynamic programming and reinforcement studying, neural networks for nonlinear platforms modeling, robotics, balance research of neural networks, studying and approximation, info mining and have extraction, chaos and synchronization, neural fuzzy structures, education and studying algorithms for neural networks, neural community constructions, neural networks for development attractiveness, SOMs, ICA/PCA, biomedical functions, feedforward neural networks, recurrent neural networks, neural networks for optimization, help vector machines, fault diagnosis/detection, communications and sign processing, image/video processing, and purposes of neural networks.

Show description

Read or Download Advances in Neural Networks – ISNN 2007: 4th International Symposium on Neural Networks, ISNN 2007, Nanjing, China, June 3-7, 2007, Proceedings, Part II PDF

Best networks books

Download PDF by John G. Taylor (auth.), Jimmy Shadbolt MSc, John G. Taylor: Neural Networks and the Financial Markets: Predicting,

This quantity seems to be at monetary prediction from a huge diversity of views. It covers: - the industrial arguments - the practicalities of the markets - how predictions are used - how predictions are made - how predictions are changed into anything usable (asset destinations) It combines a dialogue of normal thought with state of the art fabric on quite a lot of info processing ideas as utilized to state-of-the-art monetary difficulties.

Neural Networks and Soft Computing: Proceedings of the Sixth - download pdf or read online

This quantity offers new tendencies and advancements in smooth computing ideas. themes comprise: neural networks, fuzzy platforms, evolutionary computation, wisdom discovery, tough units, and hybrid tools. It additionally covers a variety of functions of soppy computing ideas in economics, mechanics, drugs, automatics and photograph processing.

Extra resources for Advances in Neural Networks – ISNN 2007: 4th International Symposium on Neural Networks, ISNN 2007, Nanjing, China, June 3-7, 2007, Proceedings, Part II

Example text

In this paper, we will investigate the effect of parameter mismatches on chaos synchronization of fuzzy neural networks by impulsive controls. It is known that the main obstacle for the impulsive synchronization in the presence of parameter mismatches is to get a good estimate of the synchronization error bound. To overcome this problem, we will obtain a numerically tractable, though suboptimal, sufficient condition using linear decomposition and comparison-system method. This paper is organized as follows.

Theorem 1. Let χ = {x ∈ Rn |||x|| ≤ δ1 }, and parameter mismatches satisfy ΔDT ΔD + ΔAT ΔA + ΔB T ΔB ≤ δ2 , δ = δ12 δ22 . and let the sequence of impulses be equidistant and separated by an interval τ . If there exists a symmetric and positive definite matrix P > 0 such that the following conditions hold: (i)−2P D + P 2 + 2L|A| + P 2 L2 + 2L|B| + P 2 L2 − λP ≤ 0, (ii) (I + C)T P (I + C) − ρP ≤ 0, (iii) lnρ + λτ < 0. then the synchronization error system (3) converges exponentially to a small region containing the origin which is τδ } λm (P )ρ(lnρ + τ λ) {e ∈ Rn |||e|| ≤ Thus, the quasi-synchronization with error bound ε = τδ λm (P )ρ(lnρ+τ λ) (11) between the systems (1) and (2) achieved.

The validity of the proposed method is demonstrated with the result of numerical example simulation. 5 Conclusion In the paper, the orthogonal function neural network based on Laguerre orthogonal polynomial is utilized to realize the synchronization of chaotic systems. The parameters of orthogonal neural network are adjusted to accomplish the synchronization of two chaotic systems with the perturbation of parameters by Lyapunov steady theorem. The proposed method can guarantee the synchronization of two chaotic systems with the perturbation of parameters.

Download PDF sample

Advances in Neural Networks – ISNN 2007: 4th International Symposium on Neural Networks, ISNN 2007, Nanjing, China, June 3-7, 2007, Proceedings, Part II by Hongwei Wang, Hong Gu (auth.), Derong Liu, Shumin Fei, Zengguang Hou, Huaguang Zhang, Changyin Sun (eds.)


by David
4.0

Rated 4.98 of 5 – based on 18 votes
Top