Rule extraction from trained neural networks using genetic algorithms

By A. D. Arbatli, H. L. Akin. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Andreas Henelius
2. Kai Puolamäki
3. J. Zurada
4. Rudy Setiono
5. Gabrielle Ras
6. Marcel A. J. van Gerven
7. Lars Asker
8. Panagiotis Papapetrou

Citations in the corpus

• Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges (2018, methodology): “Rule-extraction methods extract human interpretable rules that approximate the decision-making process in a DNN. Older genetic algorithm based rule extraction methods for ANNs can be found in (Andrews et al., 1995; Arbatli and Akin, 1997; Lu et al., 2006).”
• Computational intelligence methods for rule-based data understanding (2004, methodology): “Another simple method belonging to this group has been presented by Geczy and Usui [81].”
• A peek into the black box: exploring classifiers by randomization (2014, methodology): “A third option is to translate the black box model into an approximate model that allows for interpretation, as described in the extensive literature on rule extraction, see, e.g., Andrews et al. (1995); Johansson et al. (2003).”