This paper gives a brief overview of fuzzy model identification techniques. The paper discusses how the membership functions of a fuzzy system can be extracted from an input/output data (pattern) set without human interference. There are several methods used for rule extraction known from the literature. The bacterial algorithm is an evolutionary technique that was inspired by the microbial evolution phenomenon. The Levenberg-Marquardt algorithm is an advanced gradient type optimization method that has been developed initially for neural networks and is introduced here for the optimization of the fuzzy rule base. Fuzzy clustering is presented also as another alternative way for the rule extraction. In the part describing the model the fuzzy rule interpolation method and the approach of hierarchical rule bases are introduced. Combining fuzzy rule interpolation with the use of hierarchically structured fuzzy rule bases leads to the reduction of the fuzzy algorithms' complexity. Hierarchical fuzzy modeling by clustering techniques is also introduced in the paper.