Artificial neural networks are models that attempt to simulate the decision making processes of the human brain. They provide an effective approach to solving a broad spectrum of problems, such as pattern classifications, system modelling and optimisation. This paper gives a brief introduction to the principle and applications of the neural networks. The emphasis is put on their use in multiobjective-multiresource (MM) decision problems that occur frequently in civil engineering. Researchers have developed many methods for optimisation of MM decision problems. In many cases, the decisions are very hard to make because of negative correlations between some of the objectives. A brief description of these approaches is given and the authors explore the application of the neural network approach to solving these problems. It is argued that by using the models presented in the paper, one can obtain optimal or at least near optimal policies.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £55 +P&P)