Rule Extraction from Trained Neural Networks via Formal Concept Analysis

R. Vimieiro, L.E. Zárate, J.P.D. Silva, E.M.D. Pereira, and A.S.C. Diniz (Brazil)


Neural Networks, Rule Extraction, Formal Concept Anal ysis, Solar Energy


Due to their capability of dealing with nonlinear problems, Artificial Neural Networks (ANN) are widely used with several purposes. Once trained, they are also capable of solving unprecedented situations, keeping tolerable errors in their outputs. However, humans can not assimilate the knowledge kept by those nets, since such knowledge is im plicitly represented by their connections weights. So, in order to facilitate the extraction of rules that describe the knowledge of ANN, some devices (specially the diagrams) are, in this work, borrowed from Formal Concept Anal ysis (FCA). Such methodology is presented in this work, combining ANN, FCA and Rule Based Systems (RBS). As an example, solar energy system is the domain application considered here, due to their importance as substitutes of traditional energy systems.

Important Links:

Go Back