ABSTRACT
In this chapter, we will introduce computational devices known as neural networks that are used to solve a variety of problems, including aspects of the control of complex dynamical systems. With standard control, we rely on a mathematical model; with fuzzy control, we use a set of rules. When the information available about a system’s behavior consists primarily of numerical data, the methodology of neural networks is very useful. As you will see later, some problems are best solved with a combination of fuzzy and neural approaches. We set forth here the basic mathematical ideas used in neural networks for
control. Although neural networks have applications in many Þelds, we will attempt to address only the parts of neural network theory that are directly applicable in control theory. We will address questions such as “What are neural networks?,” “Why do we need neural networks?,” and “How can we use neural networks to solve problems?” The applications of neural networks in control will be expanded upon in later chapters.
