AI-VT: An example of CBR that generates a variety of solutions to the same problem
Résumé
AI-Virtual Trainer (AI-VT) is an Intelligent tutoring system based on Case-based reasoning. AI-VT has been design to generate per-sonalised, varied and consistent training sessions to learners. It has been though as a system which can help learners to train themselves to different abilities during a cycle. The training sessions of AI-VT propose different exercises in regards of a capacity. AI-VT can elaborate a list of exercises personalised to each learner. One of the main requierement and challenge studied in this work is its ability to propose varied training sessions to the same learner for many weeks which constituted the challenge studied in the present work. Indeed, if the same set of exercises is proposed time after time to learners, it will not keep their attention and motivation. Thus, even if the generation of training sessions is based on analogy and must integrate the repetition of some exercises, it also must introduce some diversity and AI-VT must deals with diversity. In this paper, we have highlighted the fact that the capitalisation phase of CBR is of the utmost importance for diversity, and we have also highlighted that the tension between reptition and variety depends on the abilities learned. This tension has an important impact on the capitali-sation phase of AI-VT.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...
