The ability to move in complex environments is one of the most important features of humans and animals. In this work, we exploit a bio-inspired method to generate different gaits in a bipedal locomotion system. We use the 4-cell CPG model developed by Pinto [21]. This model has been established on symmetric coupling between the cells which are responsible for generating oscillatory signals. These signals are served as activation signals that sent to muscle groups. We used the Morris-Lecar equations as internal nonlinear dynamics of the cells, and considered a diffusive type to model couplings between the cells. We succeeded to obtain periodic solutions corresponding to the bipedal gaits of walk, run, two legged jump, and two legged hop, extracted from the 4-cell CPG model, by numerical simulations. In fact, gait generation is done by the adjustment of the coupling weights which are justifying correct phase differences between the oscillatory outputs of the cells. Moreover, in order to optimize the performance of the produced gaits, a non-dominated sorting genetic algorithm is utilized to adjust the coupling weights. Manuscript profile