Knowledge Graph-Based Genetic Fuzzy Agent for Human Intelligence and Machine Co-Learning
Chang-Shing Lee, Mei‐Hui Wang, Chih‐Yu Chen, Marek Reformat, Yusuke Nojima, Naoyuki Kubota · 2023
This paper proposes a novel approach for evaluating the co-learning performance of human intelligence (HI) and machine intelligence (MI) using a Knowledge Graph-based genetic fuzzy agent. The agent utilizes a Knowledge Graph structure to represent a specific knowledge domain related to human learning and employs a genetic fuzzy learning mechanism to construct a personalized learning model. Human learners can engage in co-learning with machines using state-of-the-art AI tools such as the Meta AI S2ST Taiwanese-English language model and the OpenAI ChatGPT text model. The proposed approach was evaluated using human learning data from an undergraduate computer science course and a series of Taiwanese and English language translation experience activities. The experimental results indicate that the proposed approach can effectively enhance the co-learning process for both human and machine learners.