Communications of the ACM
International Journal of Man-Machine Studies - Special Issue: Knowledge Acquisition for Knowledge-based Systems. Part 5
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
An experimental comparison of symbolic and connectionist learning algorithms
IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
An empirical comparison of ID3 and back-propagation
IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
Symbolic mapping of neurons in feedforward networks
Pattern Recognition Letters
Discovery of comprehensible symbolic rules in a neural network
INBS '95 Proceedings of the First International Symposium on Intelligence in Neural and Biological Systems (INBS'95)
Combining models from neural networks and inductive learning algorithms
Expert Systems with Applications: An International Journal
An investigation of TREPAN utilising a continuous oracle model
International Journal of Data Analysis Techniques and Strategies
Rule extraction from trained support vector machines
PAKDD'05 Proceedings of the 9th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining
Paper: Polygenic trait analysis by neural network learning
Artificial Intelligence in Medicine
Mathematical and Computer Modelling: An International Journal
Reinforcement learning for rule extraction from a labeled dataset
Cognitive Systems Research
Hi-index | 0.00 |
If the back propagation network can produce an inference structure with high and robust performance, then it is sensible to extract rules from it. The KT algonthm is a novel algonthm for generating rules from an adapted net efficiently. The algorithm is able to deal with both single-layer and multi-layer networks, and can learn both confirming and disconfirming rules. Empirically, the algorithm is demonstrated in the domain of wind shear detection by infrared sensors with success.