Skip to Main Content
A computational intelligent system that models the human cognitive abilities may promise significant performance in problem learning because a human is effective in learning and problem solving. Functionally modeling the human cognitive abilities not only avoids the details of the underlying neural mechanisms performing the tasks but also reduces the complexity of the system. The complementary learning mechanism is responsible for human pattern recognition, that is, a human attends to positive and negative samples when making a decision. Furthermore, human concept learning is organized in a hierarchical fashion. Such hierarchical organization allows the divide-and-conquer approach to the problem. Thus, integrating the functional models of hierarchical organization and complementary learning can potentially improve the performance in pattern recognition. Hierarchical complementary learning (HCL) exhibits many of the desirable features of pattern recognition. It is further supported by the experimental results that verify the rationale of the integration and that the HCL system is a promising pattern recognition tool.