Method to improve the transparency of neurofuzzy systems

Neurofuzzy systems have been widely applied to a diverse range of applications because their robust operation and network transparency. A neurofuzzy system is specified by a set of rules with confidences. However, as knowledge base systems, neurofuzzy systems suffer from the curse of dimensionality i.e., exponential increase in the demand of resources and in the number of rules. So, the interpretability of the final model can be lost. Thus, it is desired to have a simple rule-base to ensure transparency and implementation efficiency. After training, a rule can have several non-zero confidences. The more number of non-zero confidences, the less transparent the final model becomes. Therefore, it is elemental to reduce the number of non-zero confidences. To achieve this, the proposed algorithm search for (a maximum of) two non-zero confidences which give the same result. Thus, the system can keep its complexity with a better transparency. The proposed methodology is tested in a practical control problem to illustrate its effectiveness.