A reduced rule-based localist network for data comprehension

Localist networks and especially neuro-fuzzy systems constitute promising techniques for data comprehension, but generally exhibit poor system interpretability and generalization ability. This paper aims at addressing the issues through a novel localist reduced fuzzy cerebellar model articulation controller (RFCMAC), that models the two-stage development of cortical memories in the human brain to compress and refine the formulated (fuzzy) rule base respectively. The proposed mechanisms allow the RFCMAC associative memory to induce a concise, interpretable rule base, and at the same time to improve generalization, fostering in turn system scalability and robustness. Experimental results on several benchmark tasks have demonstrated the potential of the proposed system as an effective tool for understanding data.