Abstract: ANN-based approach for inverse design of slopes with circular sliding surface has shortcomings such as slow speed of convergence, poor capability of fitting, low accuracy of prediction and indefiniteness of the training results. In order to overcome these shortcomings, Adaptive Neu-ro-Fuzzy Inference System is used to establish an ANFIS-based approach for inverse design of sliding slopes. Furthermore, this approach is used for the inverse design of several examples and the results show that it has the merits of high speed of convergence, good capability of fitting, high accuracy of prediction and definiteness of the training results, and is an excellent approach for inverse design of sliding slopes with circular fqilure surface.