Title :
Extracting fuzzy symbolic representation from artificial neural networks
Author :
Faifer, Maciej ; Janikow, Cezary Z. ; Krawiec, Krzysztof
Author_Institution :
Inst. of Comput. Sci., Poznan Univ. of Technol., Poland
Abstract :
The paper presents FUZZYTREPAN, a pedagogical approach to the problem of extracting comprehensible symbolic knowledge from trained artificial neural networks. This approach extends the previously proposed TREPAN method in two ways: it uses fuzzy representation in its knowledge extraction process (by means of fuzzy decision trees), and it uses additional heuristics in its process of generating artificial data. The paper describes the proposed approach in detail, and it presents its empirical evaluation on popular machine learning benchmarks
Keywords :
decision trees; fuzzy set theory; knowledge acquisition; knowledge representation; learning (artificial intelligence); neural nets; FUZZYTREPAN; artificial data; artificial neural networks; comprehensible symbolic knowledge; fuzzy decision trees; fuzzy symbolic representation extraction; heuristics; knowledge extraction process; machine learning benchmarks; pedagogical approach; trained artificial neural networks; Artificial neural networks; Computer networks; Data mining; Decision trees; Fuzzy neural networks; Induction generators; Machine learning; Machine learning algorithms; Neural networks; Neurons;
Conference_Titel :
Fuzzy Information Processing Society, 1999. NAFIPS. 18th International Conference of the North American
Conference_Location :
New York, NY
Print_ISBN :
0-7803-5211-4
DOI :
10.1109/NAFIPS.1999.781764
