This introductory chapter establishes the theoretical and contextual background for the application of neural networks and genetic algorithms to solving chemical problems. This chapter is divided into three major sections, namely neural networks, genetic algorithms and a literature review of previous applications of these techniques. Each of these sections are further subdivided into subsections. In the case o f the neural networks section, the order of the subsections reflects a logical progression from small to large scale properties of biological neural systems. This progression is again expressed in the descriptions o f artificial neural networks (ANNs). A number of different ANN architectures which have found chemical applications or have been discussed in a cognitive context are described, with particular emphasis on the backpropagation training algorithm for feedforward networks. The genetic algorithms section mainly describes the formal framework underlying the use of the simple genetic algorithm (SGA) and Holland’s Schema Theorem. The applications section is divided into those applications which involved neural networks and those which involved genetic algorithms.