On Interval Weighted Three-Layer Neural Networks

In solving application problems, the data sets used to train a neural network may not be hundred percent precise but within certain ranges. Representing data sets with intervals, we have interval neural networks. By analyzing the mathematical model, we categorize general three-layer neural network training problems into two types. One of them can be solved by finding numerical solutions of nonlinear systems of equations. The other can be transformed into nonlinear optimization problems. Reliable interval algorithms such as interval Newton/generalized bisection method and interval branchand-bound algorithm are applied to obtain optimal weights for interval neural networks. The applicable state-of-art interval software packages are reviewed in this paper as well.

• Type: Conference
• Year: 1998
• Where: ANSS
• Authors: Mohsen Beheshti, Ali Berrached, André de Korvin, Chenyi Hu, Ongard Sirisaengtaksin
• Keywords: ANSS 1998, Applicable State-of-art Interval, Interval Neural Networks, Modelling And Simulation, Neural Networks