AI in Education: Transforming Education using Personalised Adaptive Learning
There has been a significant rise in the gross enrolment ratio of the students in public schools over the past few decades. However, there is a decline in their learning outcomes, which results from staff crunch, crowded classrooms and insufficient infrastructure. Moreover, students are learning less as they move to higher classes. National Achievement Survey – 2017 shows that the national average score of a grade 8 student was barely 40% in Maths, Science and Social Studies. The survey also highlights the fact the country is short of at least 10 lakhs qualified teachers. With the advent of technology and AI, Personalised Adaptive Learning solutions might solve the current education crisis.
With the belief that every child is unique, funtoot, an Intelligent Tutoring System designs a personalised learning path for each child. Funtoot tailors the teaching instructions according to the knowledge states of each learner and leads the learner towards her unique learning trajectory. Funtoot is used by more than 1.5 lakh school students (Grades 2 to 9) across different states in India.
In this talk, we will go deep into the architecture of an Intelligent Tutoring System. We will start with Domain Model which helps deconstruct the knowledge. We will then move to Student Model which is an overlay on Domain Model used to estimate the students' knowledge states. We will also touch upon the Tutor Model to understand how the student's cognitive and affective states are used to design the student's personalised learning path.
Outline/Structure of the Talk
- Education Crisis (in India)
- National Achievement Survey (NAS) - 2017
- Bloom's Two Sigma Problem
- Intelligent Tutoring System
- Domain Model
- Cognitive Domain: Revised Bloom's Taxonomy
- Student Model
- Knowledge Tracing
- Bayesian Knowledge Tracing
- Deep Knowledge Tracing (RNN and LSTM)
- Tracing the Forgetting Curves using Deep Knowledge Tracing
- Discovery of Structure and Domain Knowledge
- Learning Outcomes: Impact and Improvement
Learning Outcome
- Understanding of Intelligent Tutoring Systems and its algorithms.
- How AI and Data Science can be used to improve learning outcomes
- Personalised and Adaptive Learning
Target Audience
Anybody who is interested in education and AI.
Links
- A talk at Anthill Inside - 2017 (by hasGeek) on "How deep is Deep Learning?" https://youtu.be/WaVV_1BRT3Q
- A talk at RMIT @ IIIT-Bangalore on "Genetic Grammars as a formalism for the Evaluation of TSP Heuristics". RMIT (Ramanujan, Math & IT) is series held annually at IIITB. https://www.youtube.com/watch?v=YJ1l6DLLK34
- A talk on Artificial Intelligence and Genetic Algorithms @ Sri Kumaran Children's Home, Bangalore. https://www.youtube.com/watch?v=fWUYxwv36Jk
This talk is based on the our active research and various papers published in top tier conferences on AI in Education. Following are the relevant publications:
- Paper Title: "Few hundred parameters outperform few hundred thousand?"
- Conference: Educational Data Mining - 2017 (EDM-2017)
- Paper Title: "Analysing problem sequencing strategies based on Revised Bloom's Taxonomy using Deep Knowledge Tracing"
- Conference: Intelligent Tutoring Systems - 2018 (ITS-2018)
- Paper Title: What does Time Tell? Tracing the Forgetting Curve Using Deep Knowledge Tracing (Accepted, To Appear)
Public Feedback