Meeting the requisites of the student objective is the hardest constraint to satisfy in FIC/DK-P¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? The fitness metric ν2 (mastery lacking to match objective requisites) shows the poorest performance, with more than 70% of initial-population individuals at zero and only about 19% of final-population individuals at zero. → Lebis 2024

Evidence¶

Lebis 2024¶

Lebis, A., Humeau, J., Fleury, A., Lucas, F., & Vermeulen, M. (2024). Fully Individualized Curriculum with Decaying Knowledge, a New Hard Problem: Investigation and Recommendations. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-023-00376-9

q2 · i? · design · r2

Cumulative distribution analysis of the four fitness metrics across GA runs (Fig. 8). The ν2 metric shows "more than 70% of the individuals are such that ν2 = 0" in the initial population, improving to "no more than about 19%" after optimization.

"the initial population performed very poorly: more than 70% of the individuals are such that ν2 = 0. The final population shows a significant improvement, where no more than about 19% of the individuals obtain zero to the metric – which is still not ideal for real-life context scenarios."

Discussion¶

Related Claims¶

• Knowledge decay can be compensated with a thoughtful sequence of courses — related
• A genetic algorithm can find near-faultless curricula for full-scale FIC/DK-P instances despite intractability of exact methods — related
• Problem instance variability strongly affects FIC/DK-P solvability — related