ANFIS: General description for modeling dynamic objects
Marwan Alakhras, Mourad Oussalah, M. Hussein · 2015
This work advocates the use of neuro-fuzzy based approach for the task of modeling nonlinear dynamic objects using Adaptive (Hybrid) learning mechanism in unknown environment. It aims to give to new researchers description on ANFIS capability to model nonlinear plants; i.e., combining (NN) and (FL) in what is referred in literature as "neuro-fuzzy". This combination seems natural because the two approaches generally attack the design of "intelligent" systems from different angles. NNs provide algorithms for learning, classification, and optimization, whereas FL deals with issues such as reasoning on a higher (semantic or linguistic) level. Consequently, the two technologies complement each other. By integrating neural networks with fuzzy logic, it is possible to bring the low-level of computational power and learning of NNs into FL systems.