Individualized AI Tutor Based on Developmental Learning Networks

Abstract

In recent years, in the field of education technology, artificial intelligence tutors have come to be expected to provide individualized educational services to help learners achieve high levels of academic success. To this end, AI tutors need to be able to understand the current status and preferences of a learner and then suggest appropriate learning contents accordingly. However, it is challenging to monitor learner status and preferences continually and to recommend appropriate educational services. In this paper, we propose an individualized AI tutor as an integrated system of three developmental learning networks (DLNs) by extending a deep adaptive resonance theory (Deep ART) network, a neural network capable of incremental learning. Specifically, the learner status DLN is able to easily add new input channels about learner status without disrupting existing classifiers. The learner preference DLN is to categorize learner preferences based on frequency as well as sequence of events. The learner experience DLN is updated to immediately reflect alteration of the educational effectiveness in the current classification. Our AI tutor is currently embedded in a commercialized mobile application for teaching the Korean language to children. Experimental results show that the AI tutor application efficiently helps children learn the Korean language.

Learning analytics and collaborative groups of learners in distance education: a systematic mapping study

“…The main recommendation systems have similar characteristics, namely, they are based on the analysis of student profiles and mostly offer learning content recommendation (Sharma and Ahuja, 2016;Venugopalan et al, 2016;Chanaa and Faddouli, 2018;Joy et al, 2019;Kim and Kim, 2020), recommendation of learning objects (Kapembe and Quenum, 2019), exercise recommendation (Huang et al, 2019), course recommendation (El Moustamid et al, 2017;Dahdouh et al, 2019) and learning resources (Chen et al, 2020).…”

“…The benefits categorized as intelligent services are: learning management system (Lavoie and Proulx, 2019), semantic recommendation using ontology (Sharma and Ahuja, 2016); hybrid recommendation based on student profile (Kapembe and Quenum, 2019); deep reinforcement learning structure (Huang et al, 2019); decision-making system (El Fouki et al, 2017), content-based recommendation system (Venugopalan et al, 2016), domain-specific language (Balderas et al, 2013), WAVE architecture (Manhães et al, 2014), intelligent teaching assistant system (Wang et al, 2019), profile analysis system (El Moustamid et al, 2017), algorithm based on the technique of optimizing ant colonies (Kozierkiewicz-Hetmańska and Zyśk, 2013), prototype indicators (Florian et al, 2011), online learning systems based on big data technologies (Dahdouh et al, 2018), agentbased recommendation system, Java2D technology-based e-learning system (Hamada, 2012), ID based recommendation system (Zakrzewska, 2012;Anaya et al, 2013), capture system (Lagman and Mansul, 2017), custom model (Chanaa and Faddouli, 2018), ontology model (Joy et al, 2019), evaluation tool (Dimopoulos et al, 2013), adaptive recommendation method (Chen et al, 2020), Kernel Context Recommendender System algorithm (Iqbal et al, 2019), distributed course recommendation systems (Dahdouh et al, 2019), custom user interface (Kolekar et al, 2018), recommendation system techniques for educational data mining (Thai-Nghe et al, 2010), individualized artificial intelligence tutor and LBA model (Kim and Kim, 2020) based on a system called SBAN (Zaoudi and Belhadaoui, 2020). The application of methods and techniques of data analysis provide student grade prediction, behavior pattern detection, academic progress forecasting, modeling, course dropout risk prediction, also providing student performance feedback to teachers.…”

A Literature Review on Intelligent Services Applied to Distance Learning

“…Kim and Kim [37] Individualized Tutor of Artificial Intelligence as a system that integrates three developmental learning networks (DLNS). Manhães et al [40] WAVE architecture that provides useful information about student performance.…”

Artificial Tutor: Subjectivity or Agency?

“…В первую очередь не вполне ясно, что в данном случае подразумевается под искусственным интеллектом. Идет ли речь о так называемом специализированном искусственном интеллекте, который разрабатывается для 12 13 14 решения определенного круга задач, или же о гипотетическом общем ИИ, способном выполнять любую интеллектуальную деятельность и фактически быть искусственным аналогом человека. Если предположить, что специализированного ИИ достаточно для вытеснения людей-педагогов, то это значит, что сам процесс обучения не требует от того, кто обучает, специфических человеческих свойств.…”

“…Таким образом, искусственные интеллектуальные системы, если применять их в обучении, несут в себе, скорее, функции тьюторов, а не преподавателей. В настоящее время уже существует опыт разработки таких искусственных тьюторов, представляющих собой варианты специализированного искусственного интеллекта [13]. Такие системы являются показательной реализацией делегирования компетенций и наделения искусственных систем агентностью, но не предполагают никакой субъектности, которая могла бы вытеснить субъектность преподавателя.…”