Artificial neural networks can be trained to perform excellently in many application areas. While they can learn from raw data to solve sophisticated recognition and analysis prob...
Artificial neural networks play an important role for pattern recognition tasks. However, due to poor comprehensibility of the learned network, and the inability to represent expl...
Artificial neural networks have proven to be a successful, general method for inductive learning from examples. However, they have not often been viewed in terms of constructive ...
In this paper we propose a new algorithm for rule extraction from a trained Multilayer Feedforward network. The algorithm is based on an interval arithmetic network inversion for p...