Neural Network Approaches in Structural Mechanics Computations

The neural computing paradigm has not been extensively researched in terms of its applicability to a wide variety of structural engineering problems. At an intellectual level this research aims to increase our understanding of the role of neural network technology in the structural mechanics domain and to demonstrate its applicability over a variety of applications beginning with the transition of the paradigm from pure research to applications and use. At a technical level the work includes detailed explorations to the diversity of the different neural models and computing architectures, both in serial and parallel computing environment, demonstrating strengths, weaknesses, and extending the technological base as rquired for applications.