High-level power estimation and the area complexity of Boolean functions
ISLPED '96 Proceedings of the 1996 international symposium on Low power electronics and design
Role of function complexity and network size in the generalization ability of feedforward networks
IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
Hi-index | 0.00 |
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.