We review the theory and practice of the multilayer perceptron. We aim at addressing a range of issues which are important from the point of view of applying this approach to practical problems. A number of examples are given, illustrating how the multilayer perceptron compares to alternative, conventional approaches. The application fields of classification and regression are especially considered. Questions of implementation, i.e. of multilayer perceptron architecture, dynamics, and related aspects, are discussed. Recent studies, which are particularly relevant to the areas of discriminant analysis, and function mapping, are cited.