Symbolic Knowledge Extraction from Trained Neural Networks Governed by Lukasiewicz Logics
This work describes a methodology to extract symbolic rules from trained neural networks. In our approach, patterns on the network are codified using formulas on a Lukasiewicz logic. For this we take advantage of the fact that every connective in this multi-valued logic can be evaluated by a neuron...
| Autor principal: | |
|---|---|
| Outros Autores: | , |
| Formato: | conferenceObject |
| Idioma: | eng |
| Publicado em: |
2013
|
| Assuntos: | |
| Texto completo: | http://hdl.handle.net/10400.21/2249 |
| País: | Portugal |
| Oai: | oai:repositorio.ipl.pt:10400.21/2249 |