Adaptation of FCANN Method to Extract and Represent Comprehensible Knowledge from Neural Networks

Nowadays, Artificial Neural Networks are being widely used in the representation of physical processes. Once trained, the nets are capable to solve unprecedented situations, keeping tolerable errors in their outputs. However, humans cannot assimilate the knowledge kept by these networks, since such knowledge is implicitly represented by their structure and connection weights. Recently, the FCANN method, based in Formal Concept Analysis, has been proposed as a new approach in order to extract, represent and understand the behavior of the process through rules. In this work, it is presented an adaptation of the FCANN method to extract more comprehensible variables relationships, obtaining a reduced and more interesting set of rules related to a predefined domain parameters subset, which provides a better analysis of the knowledge extracted from the neural networks without the necessity of a posteriori implications mining. As case study the approach FCANN will be applied in solar energy system.

[1]  Mark Craven,et al.  Extracting comprehensible models from trained neural networks , 1996 .

[2]  G. Grätzer.  General Lattice Theory , 1978 .

[3]  Luis E. Zárate,et al.  Using the NextClosure algorithm to extract rules from trained neural networks application in solar energy systems , 2005, Proceedings of the 2005 IEEE Midnight-Summer Workshop on Soft Computing in Industrial Applications, 2005. SMCia/05..

[4]  Luis E. Zárate,et al.  Optimization of Neural Network's Training Sets via Clustering: Application in Solar Collector Representation , 2004, ICEIS.

[5]  Bernhard Ganter,et al.  Formal Concept Analysis: Mathematical Foundations , 1998 .

[6]  Claudio Carpineto,et al.  Concept data analysis - theory and applications , 2004 .

[7]  Luis E. Zárate,et al.  FCANN: A new approach for extraction and representation of knowledge from ANN trained via Formal Concept Analysis , 2008, Neurocomputing.

[8]  Stefan Wermter,et al.  A Novel Modular Neural Architecture for Rule-Based and Similarity-Based Reasoning , 1998, Hybrid Neural Systems.

[9]  Jude W. Shavlik,et al.  Extracting Refined Rules from Knowledge-Based Neural Networks , 1993, Machine Learning.

[10]  Jude Shavlik,et al.  THE EXTRACTION OF REFINED RULES FROM KNOWLEDGE BASED NEURAL NETWORKS , 1993 .

[11]  Bruno M. Nogueira,et al.  An Approach to Knowledge Extraction From ANN Through Formal Concept Analysis - Computational Tool Proposal: SOPHIANN , 2006, 2006 IEEE International Symposium on Industrial Electronics.