This course on Adaptive Tutoring Systems (ATS) explores the design, implementation, and evaluation of intelligent systems that personalize learning experiences. It combines foundations from learning sciences, AI, and human-computer interaction.
Student modeling approaches:
Item Response Theory (IRT)
Bayesian Knowledge Tracing (BKT)
Capturing learner preferences and behaviors
Adapting content and feedback based on performance
Domain / Expert Module
Learner Module
Tutoring Module
Interaction Module
System architecture of ITS
Role of AI in education
Agentic AI in Personalized Adaptive Learning (PAL)
Recommendation systems and collaborative filtering
System interaction and critique exercises
Hands-on exploration of tutoring systems
Discussions on learning theories and classroom challenges
We followed a continuous evaluation model to ensure consistent learning and practical skill development. Students are assessed through a balanced mix of theoretical exams and hands-on applications.
Assessment include:
Three Surprise Quizzes
Three Development Assignments
Course Project (Group)
Mid and End-Semester Exams