Compilation of Symbolic Knowledge and Integration with Numeric Knowledge Using Hybrid Systems
The development of Artificial Intelligence (AI) research has followed mainly two directions: the use of symbolic and connectionist (artificial neural networks) methods. These two approaches have been applied separately in the solution of problems that require tasks of knowledge acquisition and learning. We present the results of implementing a Neuro-Symbolic Hybrid System (NSHS) that allows unifying these two types of knowledge representation. For this, we have developed a compiler or translator of symbolic rules which takes as an input a group of rules of the type IF ... THEN..., converting them into a connectionist representation. Obtained the compiled artificial neural network this is used as an initial neural network in a learning process that will allow the “refinement” of the knowledge. To prove the refinement of the hybrid approach, we carried out a group of tests that show that it is possible to improve in a connectionist way the symbolic knowledge.
KeywordsArtificial Neural Network Hybrid System Hide Unit Output Unit Incremental Learning
Unable to display preview. Download preview PDF.
- 1.Wermter, S., Sun, R. (eds.): Hybrid neural systems. Springer, Heidelberg (2000)Google Scholar
- 2.Towell, G.: Symbolic Knowledge and Neural Networks: Insertion, Refinement and Extraction. Ph.D. Thesis. Univ. of Wisconsin - Madison, USA (1991)Google Scholar
- 3.Osório, F.S.: INSS - Un Système Hybride Neuro-Symbolique pour l’Apprentissage Automatique Constructif. PhD Thesis, LEIBNIZ-IMAG, Grenoble – France (February 1998)Google Scholar
- 4.Sebastian, T.: The Monk’s Problems. School of Computer Science, Carnegie Mellon University. Pittsburgh, PA 15213, USA (1992)Google Scholar
- 5.The apple. Copyright infoagro.com (2003)Google Scholar
- 6.Parr, T.: An Introduction To ANTLR. Another tool for language recognition (2003)Google Scholar
- 7.Charte, F.: Programation in C++Builder 5. Anaya Multimedia Editions (2000)Google Scholar
- 8.Fahlman, S.E., Lebiere, C.: The Cascade-Correlation Learning Architecture. Carnegie Mellon University. Technical Report. CMU-CS-90-100 (1990)Google Scholar
- 10.McGarry, K., MacIntyre, J.: Knowledge transfer between neural networks. In: Proceedings of the sixteenth european meeting on cybernetics and systems research, Vienna, Austria, April 2002, pp. 555–560 (2002)Google Scholar
- 11.Osorio, F.S., Bernard, A.M.Y.: Aprendizado de máquinas: métodos para inserção de regras simbólicas em redes neurais artificiais aplicados ao controle em robótiva autônoma. Revista SCIENTIA. Editora da Unisinos, Out. 12(1), 1–20, Editora da Unisinos, Out (2001)Google Scholar
- 12.Rashad, U., Arullendran, P., Hawthorne, M., Kendal, S.: A hybrid medical information system for the diagnosis of dizziness. In: Proceedings 4th International Conference Neural Networks and Expert Systems in Medicine and Healthcare, Greece (June 2001)Google Scholar