Artificial Intelligence Education - Self Guided Learning
Yu Ting Toh, Wei Yue Ngoh, Sagar Sureka, Ganesh Neelakanta Iyer, Prabhu Natarajan · 2023
In recent years, there has been a noticeable surge in the utilization of artificial intelligence (AI) across various domains, including science and engineering. This growing demand has placed greater importance on AI education, with undergraduate students from diverse majors being introduced to introductory AI modules. However, it's worth noting that not all students come with a pre-existing background in problem-solving, which can result in some finding the content covered in AI courses to be both challenging and lacking in engagement. To address this challenge, we propose the implementation of AiEduSys (AI Education System). In AiEduSys, we aim to provide a solution by offering customized programming assignments and quizzes tailored to students' specific majors. Additionally, our course recommendations will be customized to align with their chosen fields of study. This approach is designed to enhance students' understanding of AI concepts and, in turn, stir up their interest in AI algorithms. We aspire to motivate them to explore how AI can be applied within their respective domains, extending beyond the confines of the AI module itself. In our user study, we created customized programming assignments and quizzes centered around the topic of the K-Nearest Neighbour (kNN) algorithm. Furthermore, we employed a hybrid model that combines Content-based filtering and Collaborative filtering to develop the AI course recommendation system. The results were promising, as we observed positive feedback from students. The majority of participants expressed significant interest in the custom-tailored programming assignments, personalized quizzes, and course recommendations. Most notably, these students demonstrated a heightened level of motivation to explore AI applications within their fields of study following their interaction with AiEduSys.