502 search results - page 3 / 101 » Extraction of Logical Rules from Neural Networks |
KES
2000
Springer
13 years 9 months ago
2000
Springer
APIN
2010
13 years 5 months ago
2010
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...
IDEAL
2005
Springer
13 years 11 months ago
2005
Springer
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...
ICML
1991
IEEE
13 years 9 months ago
1991
IEEE
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 ...
ESANN
2003
13 years 7 months ago
2003
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...