Fuzzy Cognitive Map (FCM) is a tool for modeling and representing discrete dynamical systems. Several approaches were proposed for the automatic learning of FCM on the basis of historical data. The learning techniques can be grouped into three types: Hebbian-based, population-based, and hybrid, which combines both types. Despite the good overall results achieved by population-based approaches relative to the other learning paradigms, it is possible to improve their performance by combining them with local search procedures. In this paper, we investigate the performance of a multi-start gradient-based method and two evolutionary methods hybridized with a gradient-based local search procedure for the learning of FCMs. We tested the proposed approaches for synthetic and real world FCM models. The results show that it was possible to improve the performance of the evolutionary methods with a relatively small increase in the resultant computational time. © 2012 IEEE.1 344349Kosko, B., Fuzzy cognitive maps (1986) International Journal OfMan-Machine Studies, 24, pp. 65-75Stach, W., Kurgan, L., Pedrycz, W., Reformat, M., Geneticlearning of fuzzy cognitive maps (2005) Fuzzy Sets and Systems, 153 (3), pp. 371-401Papageorgiou, E., Learning algorithms for fuzzy cognitivemaps- A review study (2012) IEEE Trans. Syst., Man, Cybern. C,Appl. Rev, 42 (2), pp. 150-163Froelich, W., Juszczuk, P., Predictive capabilities of adaptiveand evolutionary fuzzy cognitive maps- A comparativestudy (2009) Intelligent Systems for Knowledge Management, Ser.Studies in Computational Intelligence, 252, pp. 153-174. , SpringerStach, W., Kurgan, L., Pedrycz, W., A divide and conquermethod for learning large fuzzy cognitive maps (2010) Fuzzy Setsand Systems, 161 (19), pp. 2515-2532Salomon, R., Evolutionary algorithms and gradient search:similarities and differences (1998) IEEE Trans. Evol. Comput, 2 (2), pp. 45-55Jin, Y., Branke, J., Evolutionary optimization in uncertainenvironments- A survey (2005) IEEE Trans. Evol. Comput, 9 (3), pp. 303-317Chen, X., A multi-facet survey on memetic computation (2011) IEEE Trans. Evol. Comput, 15 (5), pp. 591-607Axelrod, R., (1976) Structure of Decision: The Cognitive Maps OfPolitical Elites, , Princeton University PressKosko, B., Adaptive inference in fuzzy knowledge networks (1987) IEEE International Conference on Neural Networks, pp. 261-268Galor, O., (2010) Discrete Dynamical Systems, , SpringerZhang, W., Chen, S., A logical architecture for cognitivemaps (1988) IEEE International Conference on Neural Networks, pp. 231-238Neri, F., Tirronen, V., Recent advances in differentialevolution: A survey and experimental analysis (2010) ArtificialIntelligence Review, 33, pp. 61-106Back, T., Fogel, D., Michalewicz, Z., (2000) EvolutionaryComputation 1: Basic Algorithms and Operators, , Taylor &FrancisMichalewicz, Z., (1998) Genetic Algorithms + Data Structures =Evolution Programs, , SpringerM̈uhlenbein, H., Schlierkamp-Voosen, D., Predictive modelsfor the breeder genetic algorithm (1993) Evolutionary Computation, 1 (1), pp. 25-49Haykin, S., (1999) Neural Networks: A Comprehensive Foundation, , Prentice HallKelley, C.T., Iterative methods for optimization (1999) Society ForIndustrial and Applied MathematicsGhaderi, S., Azadeh, A., Nokhandan, B.P., Fathi, E., Behavioral simulation and optimization of generationcompanies in electricity markets by fuzzy cognitive map (2012) Expert Syst. Appl, 39 (5), pp. 4635-4646Hossain, S., Brooks, L., Fuzzy cognitive map modellingeducational software adoption (2008) Computers & Education, 51 (4), pp. 1569-1588