Forgetting-Based Concept-Cognitive Learning for Classification in Fuzzy Formal Decision Context

Concept-cognitive learning reveals the principle of human cognition by simulating the brain’s process of learning and processing concepts. Nevertheless, for neighborhood similarity granules, the average information of objects regarding all attributes is not considered, which may lead to unbalanced acquisition of knowledge. On the other hand, there are some unnecessary concepts in the extension of fuzzy concepts, which results in poor classification learning. To tackle these challenges, we present a forgetting-based concept-cognitive learning model for classification in a fuzzy formal decision context. Firstly, the fuzzy concept space is established based on the the correlation coefficient matrix. Then, to delete unnecessary objects that are in the zone of proximal development, we construct the forgetting fuzzy concept space by selecting the concept corresponding to the maximum similarity. Subsequently, a forgetting-based fuzzy concept model (FCCLM) mechanism is proposed. In the end, experimental results on eight datasets validate the feasibility and efficiency of the proposed learning mechanism through classification performance assessment.