Explaining Human Cognition through Deep Learning
Revised Bloom’s Taxonomy is very well known and widely used taxonomy for classifying educational objectives. The said taxonomy describes a hierarchical ordering of cognitive skills from simple to complex. The Revised Taxonomy relaxed the strict cumulative hierarchical assumptions of the Original Taxonomy allowing overlaps. We use a knowledge tracing model, Deep Knowledge Tracing (DKT), to investigate the hierarchical nature of the Revised Taxonomy and also study the overlapping behaviour of the Taxonomy. The DKT model is trained on about 42 million problems attempted on funtoot by the students. We propose a novel way to interpret model output to measure the effects of each learning objectives on every other learning objectives. The results confirms the relaxed hierarchy of the skills from simple to complex. Moreover, results also suggest overlaps even between the non-adjacent skills.
This work is accepted (and will be published) in the top tier conference, Internation Conference of Artificial Intelligence in Education, 2018 (AIED-2018) as a full paper.
Bloom’s Taxonomy (The Cognitive Domain)
Revised Bloom’s Taxonomy (The Cognitive Domain)
Deep Knowledge Tracing (Deep Learning Model)
Model Interpretation and Output
Proposed Formulae and other Metrics (including Simplex structure)
Results and Analysis
Insights and Conclusion
Amar Lalwani, Head, R&D @ funtoot, is responsible for research and development of funtoot’s Brain. funtoot is a personalised digital tutor in K-12 space for Math and Science. funtoot is actively used by more than 1 lakh students and more than 130 schools across India.
Amar Lalwani is also pursuing Ph.D. from IIIT-Bangalore in the area of Machine Learning and Artificial Intelligence.
Amar has published papers in best international peer reviewed conferences like AIED (Artificial Intelligence in Education), ITS (Intelligent Tutoring Systems) and EDM (Educational Data Mining)