Adaptation of FCANN method to extract and represent comprehensible knowledge from neural networks

Studies in Computational Intelligence

Volumn 134, Issue , 2008, Pages 163-172

  Dias, Sérgio M ^a   Nogueira, Bruno M ^b   Zárate, Luis E ^a  

^a PONTIFICAL CATHOLIC UNIVERSITY OF MINAS GERAIS   (Brazil)

^b UNIVERSITY OF SÃO PAULO   (Brazil)

Author keywords

Artificial neural networks; Extract knowledge; Formal concept analysis

Indexed keywords

EID: 45949088376     PISSN: 1860949X     EISSN: None     Source Type: Book Series    
DOI: 10.1007/978-3-540-79355-7_16     Document Type: Article

References (14)

1. Towell, G.G., Shavlik, J.W.: The extraction of refined rules from knowledge-based neural networks. In: Machine Learning Research GroupWorking, pp. 71-101 (1993)
2. Hilario, M.: An overview of strategies for neurosymbolic integration. In: Wermter, S., Sun, R. (eds.) Hybrid Neural Systems, Springer, Germany (2000)
3. Craven, M.W.: Extracting Comprehensible Models from Trained Neural Networks. PhD Thesis, department of Computer Sciences, University of Wisconsin-Madison (1996)
4. Vimieiro, R., Zárate, L.E., Silva, J.P.D., Pereira, E.M.D., Diniz, A.S.C.: Rule extraction from trained neural networks via formal concept analysis. In: Del Pobil, A. (ed.) Proc. Eighth IASTED International Conference on Artificial Intelligence and Soft Computing. IASTED, pp. 334-339. ACTA Press (2004)
5. Vimieiro, R., Zárate, L.E., Pereira, E.M.D., Vieira, N.J.: Using the Next Closure Algorithm to Extract Rules from Trained Neural Networks Application in solar energy systems. In: IEEE SMcia, Finland, pp. 184-189 (2005)
6. Gratzer, G.: General lattice theory. ch. Applied lattice theory: Formal concept analysis, 2nd edn., pp. 591-605. Birkhäuser Verlag (1998)
7. Zárate, L.E., Dias, S.M., Song, M.A.J.: FCANN: A new approach for extraction and representation of knowledge from ANN trained via Formal Concept Analysis Neurocomputing, Amsterdam (to appear, 2007)
8. Ganter, B., Wille, R.: Formal concept analysis: Mathematical foundations. Springer, Germany (1996)
9. Carpineto, C., Romano, G.: Concept Data Analysis: Theory and Applications. John Wiley & Sons, Chichester (2004)
10. Ganter, B.: Formal Aoncept analysis: algorithmic aspects. TU Dresden, Germany, Tech. Rep. (2002)
11. Zárate, L.E., Pereira, E.M.D., Soares, D.A., Silva, J.P.D., Vimieiro, R., Diniz, A.S.C.: Optimization of neural networks training sets via clustering: Application in solar collector representation. In: Seruca, I., Filipe, J., Hammoudi, S., Cordeiro, J. (eds.) Proceedings of 6th International Conference on Enterprise Information Systems, Porto, Portugal. ICEIS, vol. 2, pp. 147-152. INSTICC Press (April 2004)
12. Zárate, L.E., Pereira, E.M.D., Silva, J.P.D., Vimieiro, R., Diniz, A.S.C.: Neural representation of a solar collector with optimization of training sets in Lecture Notes in Artificial Intelligence. In: Orchard, B., Yang, C., Moonis, A. (eds.) ISAI, AAAI, ACM/SIGART, INNS, Springer, Heidelberg (2004)
13. Kovács, Z.L.: Redes Neurais Artificiais. Edição Acadêmica São Paulo, Cap. 5, 75-76 (1996)
14. Zárate, L.E., Song, M., Alvarez, A., Soares, B., Nogueira, B., Vimieiro, R., Diaes, S., Santos, T., Vieira, N.: An Approach to Knowledge Extraction From ANN Through Formal Concept Analysis - Computational Tool Proposal: SOPHIANN. In: Proc. ISIE, Montreal Canada (2006)