AUTHORS: Azam Beg and P.W.C. Prasad
PUBLICATION/VENUE: 8th WSEAS International Conference on Evolutionary Computing, Jun 2007, pp. 314-319.
Data transformation is an important step in developing practical and robust neural networks and can take a relatively large percentage of development efforts. In this paper, we present different techniques and their algorithms for data transformation as they apply to the neural network models for predicting Boolean function complexity. The data transformation techniques proposed in this paper yield a high level of model accuracy. The given techniques can also be applied to neural networks developed for other applications.
CITATIONS: Google | Yahoo