Dynamics in Artificial Higher Order Neural Networks with Delays

Dynamics in Artificial Higher Order Neural Networks with Delays

Jinde Cao (Southeast University, China), Fengli Ren (Southeast University, China) and Jinling Liang (Southeast University, China)
Copyright: © 2009 |Pages: 41
DOI: 10.4018/978-1-59904-897-0.ch018
OnDemand PDF Download:
$37.50

Abstract

This chapter concentrates on studying the dynamics of artificial higher order neural networks (HONNs) with delays. Both stability analysis and periodic oscillation are discussed here for a class of delayed HONNs with (or without) impulses. Most of the sufficient conditions obtained in this chapter are presented in linear matrix inequalities (LMIs), and so can be easily computed and checked in practice using the Matlab LMI Toolbox. In reality, stability is a necessary feature when applying artificial neural networks. Also periodic solution plays an important role in the dynamical behavior of all solutions though other dynamics such as bifurcation and chaos do coexist. So here we mainly focus on questions of the stability and periodic solutions of artificial HONNs with (or without) impulses. Firstly, stability analysis and periodic oscillation are analyzed for higher order bidirectional associative memory (BAM) neural networks without impulses. Secondly, global exponential stability and exponential convergence are studied for a class of impulsive higher order bidirectional associative memory neural networks with time-varying delays. The main methods and tools used in this chapter are linear matrix inequalities (LMIs), Lyapunov stability theory and coincidence degree theory.
Chapter Preview
Top

Introduction

In recent years, Hopfield neural networks and their various generalizations have attracted the attention of many scientists (e.g., mathematicians, physicists, computer scientists and so on), due to their potential for the tasks of classification, associative memory, parallel computation and their ability to solve difficult optimization problems (Hopfield, 1984; ChuaYang, 1988; Marcus and Westervelt, 1989; Cohen and Grossberg, 1983; Driessche and Zou, 1998; Cao and Tao, 2001; Cao, 2001; Cao and Wang, 2004; Cao, Wang and Liao, 2003). For the Hopfield neural network characterized by first order deferential equations, Abu-Mostafa and Jacques (1985); McEliece, Posner, Rodemich and Venkatesh (1987) and Baldi (1988) presented its intrinsic limitations. As a consequence, different architectures with higher order interactions (Personnaz, Guyon and Dreyfus, 1987; Psaltis, Park and Hong, 1988; Simpson, 1990; Peretto and Niez, 1986; Ho, Lam, Xu and Tam, 1999) have been successively introduced to design neural networks which have stronger approximation properties, faster convergence rate, greater storage capacity, and higher fault tolerance than lower order neural networks. Meanwhile stability properties of these models have been investigated in Dembo, Farotimi and Kailath (1991); Kamp and Hasler (1990); Kosmatopoulos, Polycarpou, Christodoulou and Ioannou (1995); Xu, Liu and Liao (2003); Ren and Cao (2006); Ren and Cao (2007); Ren and Cao (in press). In this chapter, we will give some criteria on higher order BAM neural networks.

BAM neural networks were proposed in Kosko (1988). This model generalizes the single-layer auto-associative circuit and possesses good application prospects in the areas of pattern recognition, signal and image processing. The circuit diagram and connection pattern implementing the delayed BAM networks can be found in Cao and Wang (2002). From a mathematical viewpoint, although the system in this chapter can be regarded as a network with dimension n+m, it produces many nice properties due to the special structure of connection weights and its practical application in storing paired patterns via both directions: forward and backward. When a neural circuit is employed as an associative memory, the existence of many equilibrium points is a necessary feature. However, when applied to parallel computation and signal processing involving the solution of optimization problems, it is required that there be a well-defined computable solution for all possible initial states. This means that the network should have a unique equilibrium point that is globally attractive. Indeed, earlier applications in optimization have suffered from the existence of a complicated set of equilibriums. Thus, the global attractiveness of systems is of great importance for both practical and theoretical reasons. For more details about BAM neural networks, see Cao (2003); Cao and Dong (2003); Liao and Yu (1998); Mohamad (2001); Chen, Cao and Huang (2004).

In this chapter, firstly, we investigate the following second order BAM neural networks with time delays:

where i=1,2,…, n; j=1,2, …, m; t>0 ; , denote the potential (or voltage) of cell i and j at time t; , are positive constants; time delays, are non-negative constants, which correspond to finite speed of axonal signal transmission; , , , are the first and second order connection weights of the neural network, respectively; , denote the ith and the jth component of an external input source introduced from outside the network to cell i and j, respectively; and =max{, }.

Complete Chapter List

Search this Book:
Reset
Dedication
Table of Contents
Acknowledgment
Ming Zhang
Chapter 1
Ming Zhang
This chapter delivers general format of Higher Order Neural Networks (HONNs) for nonlinear data analysis and six different HONN models. This chapter... Sample PDF
Artificial Higher Order Neural Network Nonlinear Models: SAS NLIN or HONNs?
$37.50
Chapter 2
Adam Knowles, Abir Hussain, Wael El Deredy, Paulo G.J. Lisboa, Christian L. Dunis
Multi-Layer Perceptrons (MLP) are the most common type of neural network in use, and their ability to perform complex nonlinear mappings and... Sample PDF
Higher Order Neural Networks with Bayesian Confidence Measure for the Prediction of the EUR/USD Exchange Rate
$37.50
Chapter 3
Da Shi, Shaohua Tan, Shuzhi Sam Ge
Real-world financial systems are often nonlinear, do not follow any regular probability distribution, and comprise a large amount of financial... Sample PDF
Automatically Identifying Predictor Variables for Stock Return Prediction
$37.50
Chapter 4
John Seiffertt, Donald C. Wunsch II
As the study of agent-based computational economics and finance grows, so does the need for appropriate techniques for the modeling of complex... Sample PDF
Higher Order Neural Network Architectures for Agent-Based Computational Economics and Finance
$37.50
Chapter 5
Yuehui Chen, Peng Wu, Qiang Wu
Forecasting exchange rates is an important financial problem that is receiving increasing attention especially because of its difficulty and... Sample PDF
Foreign Exchange Rate Forecasting Using Higher Order Flexible Neural Tree
$37.50
Chapter 6
Yuehui Chen, Peng Wu, Qiang Wu
Artificial Neural Networks (ANNs) have become very important in making stock market predictions. Much research on the applications of ANNs has... Sample PDF
Higher Order Neural Networks for Stock Index Modeling
$37.50
Chapter 7
Ming Zhang
This chapter develops a new nonlinear model, Ultra high frequency Trigonometric Higher Order Neural Networks (UTHONN), for time series data... Sample PDF
Ultra High Frequency Trigonometric Higher Order Neural Networks for Time Series Data Analysis
$37.50
Chapter 8
Panos Liatsis, Abir Hussain, Efstathios Milonidis
The research described in this chapter is concerned with the development of a novel artificial higher order neural networks architecture called the... Sample PDF
Artificial Higher Order Pipeline Recurrent Neural Networks for Financial Time Series Prediction
$37.50
Chapter 9
Abir Hussain, Panos Liatsis
The research described in this chapter is concerned with the development of a novel artificial higherorder neural networks architecture called the... Sample PDF
A Novel Recurrent Polynomial Neural Network for Financial Time Series Prediction
$37.50
Chapter 10
David R. Selviah, Janti Shawash
Generalized correlation higher order neural network designs are developed. Their performance is compared with that of first order networks... Sample PDF
Generalized Correlation Higher Order Neural Networks for Financial Time Series Prediction
$37.50
Chapter 11
Godfrey C. Onwubolu
Real world problems are described by nonlinear and chaotic processes, which makes them hard to model and predict. This chapter first compares the... Sample PDF
Artificial Higher Order Neural Networks in Time Series Prediction
$37.50
Chapter 12
Rozaida Ghazali, Dhiya Al-Jumeily
This chapter discusses the use of two artificial Higher Order Neural Networks (HONNs) models; the Pi- Sigma Neural Networks and the Ridge Polynomial... Sample PDF
Application of Pi-Sigma Neural Networks and Ridge Polynomial Neural Networks to Financial Time Series Prediction
$37.50
Chapter 13
Edgar N. Sanchez, Alma Y. Alanis, Jesús Rico
In this chapter, we propose the use of Higher Order Neural Networks (HONNs) trained with an extended Kalman filter based algorithm to predict the... Sample PDF
Electric Load Demand and Electricity Prices ForecastingUsing Higher Order Neural Networks Trained by Kalman Filtering
$37.50
Chapter 14
Shuxiang Xu
Business is a diversified field with general areas of specialisation such as accounting, taxation, stock market, and other financial analysis.... Sample PDF
Adaptive Higher Order Neural Network Models and Their Applications in Business
$37.50
Chapter 15
Jean X. Zhang
This chapter proposes nonlinear models using artificial neural network models to study the relationship between chief elected official (CEO) tenure... Sample PDF
CEO Tenure and Debt: An Artificial Higher Order Neural Network Approach
$37.50
Chapter 16
Christian L. Dunis, Jason Laws, Ben Evans
This chapter investigates the soybean-oil “crush” spread, that is the profit margin gained by processing soybeans into soyoil. Soybeans form a large... Sample PDF
Modelling and Trading the Soybean-Oil Crush Spread with Recurrent and Higher Order Networks: A Comparative Analysis
$37.50
Chapter 17
Madan M. Gupta, Noriyasu Homma, Zeng-Guang Hou, Ashu M. G. Solo, Takakuni Goto
In this chapter, we aim to describe fundamental principles of artificial higher order neural units (AHONUs) and networks (AHONNs). An essential core... Sample PDF
Fundamental Theory of Artificial Higher Order Neural Networks
$37.50
Chapter 18
Jinde Cao, Fengli Ren, Jinling Liang
This chapter concentrates on studying the dynamics of artificial higher order neural networks (HONNs) with delays. Both stability analysis and... Sample PDF
Dynamics in Artificial Higher Order Neural Networks with Delays
$37.50
Chapter 19
Zhao Lu, Leang-san Shieh, Guanrong Chen
Aiming to develop a systematic approach for optimizing the structure of artificial higher order neural networks (HONN) for system modeling and... Sample PDF
A New Topology for Artificial Higher Order Neural Networks: Polynomial Kernel Networks
$37.50
Chapter 20
David R. Selviah
This chapter describes the progress in using optical technology to construct high-speed artificial higher order neural network systems. The chapter... Sample PDF
High Speed Optical Higher Order Neural Networks for Discovering Data Trends and Patterns in Very Large Databases
$37.50
Chapter 21
Zidong Wang, Yurong Liu, Xiaohui Liu
This chapter deals with the analysis problem of the global exponential stability for a general class of stochastic artificial higher order neural... Sample PDF
On Complex Artificial Higher Order Neural Networks: Dealing with Stochasticity, Jumps and Delays
$37.50
Chapter 22
Lei Zhang, Simeon J. Simoff, Jing Chun Zhang
This chapter introduces trigonometric polynomial higher order neural network models. In the area of financial data simulation and prediction, there... Sample PDF
Trigonometric Polynomial Higher Order Neural Network Group Models and Weighted Kernel Models for Financial Data Simulation and Prediction
$37.50
About the Contributors