A novel dual neuro-fuzzy system approach for large-scale knowledge consolidation

Fuzzy and neuro-fuzzy systems are increasingly among the key technologies employed in many real-world applications. However, traditional neuro-fuzzy systems are generally still lacking the scalability traits required in the face of large-scale data and the capability to incorporate new information without catastrophically disrupting the existing knowledge base. This work aims at addressing these issues by proposing a novel neuro-fuzzy system termed dual consolidation network (DCN) that models the complementary interactions between hippocampus and neocortex regions in the human brain to consolidate and exploit knowledge effectively. This approach allows the DCN to handle data sets with high-dimensional features and/or a very large number of samples efficiently, as well as to minimize interference when acquiring new information. Preliminary experiments employing DCN on large-scale biomedical data have shown encouraging results.