PRICAI'00 Proceedings of the 6th Pacific Rim international conference on Artificial intelligence
| Hi-index | 0.00 |
It has been shown in this work that an important consideration when designing network training data is to select carefully those variables that are to be used as inputs. Only those parameters that contribute towards improving the accuracy of the network prediction should be included as input parameters. Despite a large variety of neural network models, back propagation (BP) is found to be the most commonly applied model for an extensive range of applications. However, when applying BP networks to process modeling or control, it is necessary to select the correct network architecture and activation functions in order to minimize computation time and maximize network accuracy. In addition, to improve network performance it is necessary to use sufficient training data, spanning a comprehensive input range. While many of the techniques for improving network performance are based on a heuristic approach, some important aspects are detailed in this paper for selecting the optimum network conditions, with respect to computation time and accuracy, using a mathematical function as a sample application.