A multi-input multi-output adaptive neuro fuzzy inference system (MIMO-ANFIS) was proposed in this study to reduce dynamic responses of a seismically excited building. A multi-objective genetic algorithm (MOGA) was used to optimize the MIMO-ANFIS controller. Two MR dampers were used as multiple control devices and a scaled five-story building model was selected as an example structure. A MIMO fuzzy control algorithm was compared with the proposed MIMO-ANFIS controller. A multi-input multi output adaptive neuro-fuzzy inference system (MIMO-ANFIS) with several outputs was proposed. In case study, after numerical simulation, it has been verified that the MIMO ANFIS control algorithm can present better control performance compared to the MIMO fuzzy control algorithm in reducing both displacement and acceleration responses.