Evolutionary Practice Problems Generation: Design Guidelines
Keywords
Coevolutionary algorithms; Computer-Aided learning; Interactive evolutionary algorithms
Abstract
This paper identifies design guidelines for the application of evolutionary techniques to the task of generating practice problems for learners in an Intelligent Tutoring System. To this end, we designed experiments that progressively incorporated an increasing number of the characteristics we expect to find in our target application. These features included noisy evaluations, overspecialization, and the need to mitigate user fatigue resulting from interactive evaluations of practice problems. As we did so, we evaluated the potential of recent breakthroughs in coevolutionary learning theory and identified the tradeoff specific to educational applications.
Publication Date
1-11-2017
Publication Title
Proceedings - 2016 IEEE 28th International Conference on Tools with Artificial Intelligence, ICTAI 2016
Number of Pages
544-548
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICTAI.2016.86
Copyright Status
Unknown
Socpus ID
85013629809 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85013629809
STARS Citation
Gaspar, Alessio; Bari, A. T.M.Golam; Kumar, Amruth N.; Bucci, Anthony; and Wiegand, R. Paul, "Evolutionary Practice Problems Generation: Design Guidelines" (2017). Scopus Export 2015-2019. 7441.
https://stars.library.ucf.edu/scopus2015/7441