An approach to improve the interpretability of neuro-fuzzy systems

In this paper it is presented an approach to improve the interpretability of a neuro-fuzzy system. This improvement is achieved through the modification of the Sugeno form of the consequent polynomials into corresponding triangular membership functions. The resulting neuro-fuzzy inference system has the same performance as the initial one and is an extension to our already published neuro-fuzzy architecture. This architecture has been used in the classification and control applications. In simulation, the proposed approach is applied after the corresponding neuro-fuzzy model of a non-linear function is obtained. A helicopter motion controller model was used as the non-linear function. The increase of interpretability of the controller shows the effectiveness of the proposed approach.