Foundations of genetic algorithms
Foundations of genetic algorithms
Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
The discovery of propositions in noisy data
Machine intelligence 13
Structural learning with forgetting
Neural Networks
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Data Mining Techniques: For Marketing, Sales, and Customer Support
Data Mining Techniques: For Marketing, Sales, and Customer Support
Back-Propagation: Theory, Architecture, and Applications
Back-Propagation: Theory, Architecture, and Applications
Extracting propositions from trained neural networks
IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
Evolutionary Bi-objective Learning with Lowest Complexity in Neural Networks: Empirical Comparisons
ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part I
| Hi-index | 0.00 |
We presented an algorithm for extracting Boolean functions (propositions, rules) from the units in trained neural networks. The extracted Boolean functions make the hidden units understandable. However, in some cases, the extracted Boolean functions are complicated, and so are not understandable, which means that the hidden units are not functionally localized. This paper presents an algorithm for the functional localization of (the hidden units of) neural networks. When a hidden unit is well approximated to a low-order Boolean function, the unit can be regarded as functionally localized. The functional localization of a hidden unit is evaluated by the error between the hidden unit and the low-order Boolean function extracted from the hidden unit. The optimization is executed by genetic algorithms. We applied it to vote data, mushroom data and chess data. Experimental results show that the algorithm works well.