Build a Learning Habit
Download Class Central's free printable study calendar
Download for Free
ABOUT THE COURSE:
This course introduces the theoretical foundations, computational models, and design principles underlying AI-driven Personalised Adaptive Learning (PAL) systems. The course begins by grounding personalisation in key learning theories, including constructivism, self-regulated learning, cognition, and metacognition. It traces the historical evolution from Computer-Assisted Instruction (CAI) to classical ITS and contemporary Personalised Learning Environments (PLEs). Central to the course is the well-established four-model architecture of ITS—domain model, learner model, pedagogical model, and interface model—which serves as an organising framework throughout. The course also situates PAL systems within the broader AI landscape by distinguishing traditional AI approaches from recent developments in large language models and discussing their affordances and limitations for adaptive learning. Importantly, the course extends beyond computer-based learning environments to examine how personalisation can be embedded in classrooms, blended settings, and emerging contexts such as VR-based learning.
INTENDED AUDIENCE: Anyone doing BE/BTech or B.Ed education
INDUSTRY SUPPORT: Edtech industries developing adaptive systems would be interested.
This course introduces the theoretical foundations, computational models, and design principles underlying AI-driven Personalised Adaptive Learning (PAL) systems. The course begins by grounding personalisation in key learning theories, including constructivism, self-regulated learning, cognition, and metacognition. It traces the historical evolution from Computer-Assisted Instruction (CAI) to classical ITS and contemporary Personalised Learning Environments (PLEs). Central to the course is the well-established four-model architecture of ITS—domain model, learner model, pedagogical model, and interface model—which serves as an organising framework throughout. The course also situates PAL systems within the broader AI landscape by distinguishing traditional AI approaches from recent developments in large language models and discussing their affordances and limitations for adaptive learning. Importantly, the course extends beyond computer-based learning environments to examine how personalisation can be embedded in classrooms, blended settings, and emerging contexts such as VR-based learning.
INTENDED AUDIENCE: Anyone doing BE/BTech or B.Ed education
INDUSTRY SUPPORT: Edtech industries developing adaptive systems would be interested.
