A Mutual Information-Based Two-Phase Memetic Algorithm for Large-Scale Fuzzy Cognitive Map Learning

Various automatic learning algorithms have been proposed to learn fuzzy cognitive maps (FCMs), but most of them were only applied to learn small-scale FCMs and the learned maps obtained by such methods are usually much denser than the real maps. Learning FCMs requires the learning methods to not only determine the existence of links between concepts but also optimize the edge weights, which is the difficulty for FCM learning methods. Therefore, we propose a mutual information (MI)-based two-phase memetic algorithm (MA) for learning large-scale FCMs, termed as MIMA-FCM. In MIMA-FCM, the first phase is oriented to determine the existence of links between concepts by MI, which can reduce the search space significantly for MA, and then MA is used to optimize the edge weights according to the multiple observed response sequences in the second phase. Experiments on both synthetic and real-life data and the application for the gene regulatory network reconstruction problem demonstrate that the proposed method can not only find the plausible existence of links between concepts, but also optimize the edge weights rapidly. The comparison with existing algorithms shows that MIMA-FCM can learn large-scale FCMs with higher accuracy without expert knowledge.