Artificial Intelligence in Education (AIEd): a high-level academic and industry note 2021

AI and Ethics, Год журнала: 2021, Номер 2(1), С. 157 - 165

Опубликована: Июль 7, 2021

In the past few decades, technology has completely transformed world around us. Indeed, experts believe that next big digital transformation in how we live, communicate, work, trade and learn will be driven by Artificial Intelligence (AI) [83]. This paper presents a high-level industrial academic overview of AI Education (AIEd). It focus latest research AIEd on reducing teachers' workload, contextualized learning for students, revolutionizing assessments developments intelligent tutoring systems. also discusses ethical dimension potential impact Covid-19 pandemic future AIEd's practice. The intended readership this article is policy makers institutional leaders who are looking an introductory state play AIEd.

Язык: Английский

---

Teaching and learning with children: Impact of reciprocal peer learning with a social robot on children’s learning and emotive engagement

Computers & Education, Год журнала: 2020, Номер 150, С. 103836 - 103836

Опубликована: Фев. 5, 2020

Язык: Английский

---

Leveraging AI in E-Learning: Personalized Learning and Adaptive Assessment through Cognitive Neuropsychology—A Systematic Analysis

Electronics, Год журнала: 2024, Номер 13(18), С. 3762 - 3762

Опубликована: Сен. 22, 2024

This paper reviews the literature on integrating AI in e-learning, from viewpoint of cognitive neuropsychology, for Personalized Learning (PL) and Adaptive Assessment (AA). review follows PRISMA systematic methodology synthesizes results 85 studies that were selected an initial pool 818 records across several databases. The indicate can improve students’ performance, engagement, motivation; at same time, some challenges like bias discrimination should be noted. covers historic development education, its theoretical grounding, practical applications within PL AA with high promise ethical issues AI-powered educational systems. Future directions are empirical validation effectiveness equity, algorithms reduce bias, exploration implications regarding data privacy. identifies transformative potential developing personalized adaptive learning (AL) environments, thus, it advocates continued as a means to outcomes.

Язык: Английский

---

Research Trends in Social Robots for Learning

Current Robotics Reports, Год журнала: 2020, Номер 1(3), С. 75 - 83

Опубликована: Июнь 16, 2020

Язык: Английский

---

Multimodal Engagement Analysis From Facial Videos in the Classroom

IEEE Transactions on Affective Computing, Год журнала: 2021, Номер 14(2), С. 1012 - 1027

Опубликована: Ноя. 13, 2021

Student engagement is a key component of learning and teaching, resulting in plethora automated methods to measure it. Whereas most the literature explores student analysis using computer-based often lab, we focus on classroom instruction authentic environments. We collected audiovisual recordings secondary school classes over one half month period, acquired continuous labeling per (N=15) repeated sessions, explored computer vision classify from facial videos. learned deep embeddings for attentional affective features by training Attention-Net head pose estimation Affect-Net expression recognition previously-collected large-scale datasets. used these representations train classifiers our data, individual multiple channel settings, considering temporal dependencies. The best performing achieved student-independent AUCs .620 .720 grades 8 12, respectively, with attention-based outperforming features. Score-level fusion either improved or was par modality. also investigated effect personalization found that only 60 seconds person-specific selected margin uncertainty base classifier, yielded an average AUC improvement .084.

Язык: Английский

---

A Systematic Literature Review of Decision-Making and Control Systems for Autonomous and Social Robots

International Journal of Social Robotics, Год журнала: 2023, Номер 15(5), С. 745 - 789

Опубликована: Март 26, 2023

Abstract In the last years, considerable research has been carried out to develop robots that can improve our quality of life during tedious and challenging tasks. these contexts, operating without human supervision open many possibilities assist people in their daily activities. When autonomous collaborate with humans, social skills are necessary for adequate communication cooperation. Considering facts, endowing decision-making control models is critical appropriately fulfiling initial goals. This manuscript presents a systematic review evolution systems architectures three decades. These have incorporating new methods based on biologically inspired Machine Learning enhance systems’ developed societies. The explores most novel advances each application area, comparing essential features. Additionally, we describe current challenges software architecture devoted action selection, an analysis not provided similar reviews behavioural robots. Finally, present future directions take future.

Язык: Английский

---

Reinforcement learning tutor better supported lower performers in a math task

Machine Learning, Год журнала: 2024, Номер 113(5), С. 3023 - 3048

Опубликована: Фев. 9, 2024

Abstract Resource limitations make it challenging to provide all students with one of the most effective educational interventions: personalized instruction. Reinforcement learning could be a pivotal tool decrease development costs and enhance effectiveness intelligent tutoring software, that aims right support, at time, student. Here we illustrate deep reinforcement can used adaptive pedagogical support about concept volume in narrative storyline software. Using explainable artificial intelligence tools, extracted interpretable insights policy learned demonstrated resulting had similar performance different student population. Most importantly, both studies, reinforcement-learning system largest benefit for those lowest initial pretest scores, suggesting opportunity AI adapt need.

Язык: Английский

---

Examining Human–Robot Interactions: Design Guidelines for Trust and Acceptance

Springer series in adaptive environments, Год журнала: 2025, Номер unknown, С. 117 - 137

Опубликована: Янв. 1, 2025

Язык: Английский

---

Exploring the Effects of a Social Robot's Speech Entrainment and Backstory on Young Children's Emotion, Rapport, Relationship, and Learning

Frontiers in Robotics and AI, Год журнала: 2019, Номер 6

Опубликована: Июль 9, 2019

In positive human-human relationships, people frequently mirror or mimic each other's behavior. This mimicry, also called entrainment, is associated with rapport and smoother social interaction. Because in learning scenarios has been shown to lead improved outcomes, we examined whether enabling a robotic companion perform rapport-building behaviors could improve children's engagement during storytelling activity. We enabled the robot two specific relationship-building behaviors: speech entrainment self-disclosure (shared personal information form of backstory about robot's poor hearing abilities). recruited 86 children aged 3-8 years interact 2x2 between-subjects experimental study testing effects (Entrainment vs. No Entrainment) abilities (Backstory Backstory) The engaged one-on-one conversation, told story embedded key vocabulary words, asked retell story. measured recall words their emotions interaction, retellings, questions relationship robot. found that led show more fewer negative emotions. Children who heard were likely accept abilities. Entrainment paired use match phrases retells. Furthermore, these consider human-like comply one requests. These results suggest increased enjoyment perception relationship, contributed success at retelling

Язык: Английский

---

An Off-Policy Trust Region Policy Optimization Method With Monotonic Improvement Guarantee for Deep Reinforcement Learning

IEEE Transactions on Neural Networks and Learning Systems, Год журнала: 2021, Номер 33(5), С. 2223 - 2235

Опубликована: Янв. 22, 2021

In deep reinforcement learning, off-policy data help reduce on-policy interaction with the environment, and trust region policy optimization (TRPO) method is efficient to stabilize procedure. this article, we propose an TRPO method, TRPO, which exploits both on- guarantees monotonic improvement of policies. A surrogate objective function developed use keep We then optimize by approximately solving a constrained problem under arbitrary parameterization finite samples. conduct experiments on representative continuous control tasks from OpenAI Gym MuJoCo. The results show that proposed achieves better performance in majority compared other policy-based methods using data.

Язык: Английский

---