A genetic algorithm can find near-faultless curricula for full-scale FIC/DK-P instances despite intractability of exact methods¶

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? A genetic algorithm across 124740 runs always obtained better solutions than the initial pseudo-randomized population, in some cases approaching full constraint satisfaction with f ≈ 0.1. → 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

Metaheuristic experiment using a GA implemented in C++ with the Paradiseo library across 124740 simulated FIC/DK-P instances on a cluster. "we always obtained better solutions than the initial, pseudo-randomized, population," with some cases reaching f ≈ 0.1.

"Fitness-wise, considering the entirety of the experiments we conduct, we always obtained better solutions than the initial, pseudo-randomized, population, as presented in Fig. 6. In some cases, we were even close to fully solving FIC/DK-P , with f ≈ 0.1."

Discussion¶

Related Claims¶

• Knowledge decay can be compensated with a thoughtful sequence of courses — related
• FIC/DK-P exhibits combinatorial explosion making exact solving intractable beyond small problem sizes — related
• Problem instance variability strongly affects FIC/DK-P solvability — related
• Meeting the requisites of the student objective is the hardest constraint to satisfy in FIC/DK-P — related
• Increasing the number of courses per semester does not necessarily make FIC/DK-P easier to solve well — related