Integrating Machine Learning Techniques in a Guided Discovery Tutoring Environment: MEMOCAR

摘要: This chapter presents how Machine Learning Techniques can effectively contribute to improve the quality of interactions in Guided Discovery Tutoring Environments (GDTE) . We review several approaches integrate ITS. Most these use concept learning from examples maintain a Student Model. go along presenting an alternative induction techniques learn concepts on same data that are presented learner. present concrete example this approach is integrated GDTE called MEMOCAR, Computer Aided Language System for Chinese characters. Three main types activity identified MEMOCAR: familiarization with characters, collaborative discovery similarities between characters and exercises test acquisition. The stage supported by exploration hyperdata whilst exercises' diagnosis tool based CHARADE, top-down system. Such integration offers new complex problem making Environment more collaborative. Resume: Le theme aborde dans ce rapport est celui de l'utilisation d’apprentissage symbolique automatique (ASA) pour l'amelioration des les environnements d’enseignement par la decouverte assiste ordinateur. Nous presentons differents integrant d'apprentissage automatique; principalement construire et/ou mettre jour un modele l'eleve. ensuite une originale l’ASA le cadre d'un environnement dedie l'apprentissage caracteres chinois decouverte: MEMOCAR. Notre approche consiste utiliser l'ASA faire apprendre au systeme sur memes donnees que l'eleve, et resultats cet apprentissage interactions. Deux principales activites du l'apprenant similarites entre exercices l’apprentissage sont ainsi basees l'adaptation algorithme inductif: CHARADE. Ce type d’integration s'insere recherches visant rendre tels plus cooperatifs.