Learning large-scale fuzzy cognitive maps using a hybrid of memetic algorithm and neural network

Fuzzy cognitive maps (FCMs) are cognition fuzzy influence graphs, which are based on fuzzy logic and neural network. In this paper, we propose a novel method combining Memetic Algorithms (MAs) and Neural Networks (NNs) to learn large-scale FCMs, which is labeled as MA-NN-FCM. In MA-NN-FCM, MAs are used to determine the regulatory connections in the network from multiple observed response sequences and NNs are used to calculate the interactions between concepts. In the experiments, the performance of MA-NN-FCM is validated on synthetic data with different number of nodes. The experimental results demonstrate the efficiency of our method, and show MA-NN-FCM can construct FCMs with high accuracy without expert knowledge. The performance of MA-NN-FCM is better than that of other FCM learning algorithms, such as ant colony optimization, non-linear Hebbian learning, and real-coded genetic algorithm.