The pattern-mapping, pattern-classiJication, and optimization capabilities of neural networks have been used to solve a number of structural analysis and design problems. Most applications exploit the pattern-mapping capabilio and are based on the back-propagation paradigm .for neural networks. There are a number of factors that influence the performance of these networks. This paper initially discusses these factors and the domain-dependent and -independent techniques presently available for improving performance. The paper then considers the effect of representation, selected for the inputloutput pattern pairs, on the performance of these networks and demonstrates that representations based on dimensionless terms, derived from dimensional analysis, lead to improved performance. It is shown that dimensional analysis provides a representational framework, with reduced dimensionality and embedded domain knowledge, within which effective learning can take place and that this representational change can be used to enhance the domain-independent and -dependent techniques presently available for improving performance of these networks. 0 1994 Microcompurers in Civil Engineering. Published by Blackwell Publishers,

No abstract

No abstract

In this study, neural network models improved by genetic algorithm were employed to estimate peak ground acceleration (PGA) at seven metropolitan areas in the island of Taiwan, which is frequently subject to earthquakes. By considering a series of historical seismic records, and using the seismic design value in the current building code as the evaluation criteria, two metropolitan areas, Taichung and Chiayi, were identified by computational results as having higher estimated horizontal PGAs than the recommended design values. The approach implemented in this study provides a new and good basis for solving this type of seismic problems in the region studied.

No abstract