8,438 Hits in 4.8 sec

Eliciting good teaching from humans for machine learners

Maya Cakmak, Andrea L. Thomaz
2014 Artificial Intelligence  
Interactive machine learning We propose using computational teaching algorithms to improve human teaching for machine learners.  ...  We investigate example sequences produced naturally by human teachers and find that humans often do not spontaneously generate optimal teaching sequences for arbitrary machine learners.  ...  Given the significant potential of good teaching we pose two questions: • How well do humans naturally teach machine learners? • Can we influence humans to teach more optimally?  ... 
doi:10.1016/j.artint.2014.08.005 fatcat:72q23jiwlfgsjg5aqruyyrq2qu

Learning to interact and interacting to learn: Active statistical learning in human-robot interaction

Chen Yu, Tian Xu, Yiwen Zhong, Seth Foster, Hui Zhang
2014 2014 International Joint Conference on Neural Networks (IJCNN)  
Toward this goal, we developed a real-time human-robot interaction paradigm in which a robot learner acquired lexical knowledge from a human teacher through free-flowing interaction.  ...  In addition, more activities from the robot revealed its robot's internal learning states in real time, which allowed human teachers to provide more useful and "on-demand" teaching signals to facilitate  ...  We thank Hong-Wei Shen and Amanda Favata for help with running experiments. This research was supported by NIH R01HD074601and NSF BCS 0924248.  ... 
doi:10.1109/ijcnn.2014.6889698 dblp:conf/ijcnn/YuXZFZ14 fatcat:el557w3xrzb2zcp3or43n7x6f4

Human-AI Interaction Design in Machine Teaching [article]

Karan Taneja, Harshvardhan Sikka, Ashok Goel
2022 arXiv   pre-print
Machine Teaching (MT) is an interactive process where a human and a machine interact with the goal of training a machine learning model (ML) for a specified task.  ...  ., the teaching interface, the machine learner, and the knowledge base, and focus on the human-AI interaction design involved in realizing the teaching interface.  ...  The knowledge base is used for feedback interpretation by the machine learner, and for assisting human teachers through the teaching interface to increase teaching efficiency.  ... 
arXiv:2206.05182v1 fatcat:4qrl7wlr2ndsnetxhiag5m57iy

How people talk when teaching a robot

Elizabeth S. Kim, Dan Leyzberg, Katherine M. Tsui, Brian Scassellati
2009 Proceedings of the 4th ACM/IEEE international conference on Human robot interaction - HRI '09  
We examine affective vocalizations provided by human teachers to robotic learners.  ...  for social learning interactions.  ...  Explorations into interactive machine learning have observed the need to modify classical machine learning models to fit natural human teaching preferences [29] .  ... 
doi:10.1145/1514095.1514102 dblp:conf/hri/KimLTS09 fatcat:4jeumh235rbk5jtbmi2l76kw3i

Page 21 of Linguistics and Language Behavior Abstracts: LLBA Vol. 27, Issue 1 [page]

1993 Linguistics and Language Behavior Abstracts: LLBA  
The cultural literacy movement promotes a theory of human intelligence derived from computer models of machine learning, a human analog to data processing in machines.  ...  It is argued that many native-French-speaking instructors in classes for foreign learners do not have a good grasp of linguistic notions essential for in- struction.  ... 

Reinforcement Learning with Human Teachers: Understanding How People Want to Teach Robots

Andrea L. Thomaz, Guy Hoffman, Cynthia Breazeal
2006 ROMAN 2006 - The 15th IEEE International Symposium on Robot and Human Interactive Communication  
While Reinforcement Learning (RL) is not traditionally designed for interactive supervisory input from a human teacher, several works in both robot and software agents have adapted it for human input by  ...  We report three main observations on how people administer feedback when teaching a robot a task through Reinforcement Learning: (a) they use the reward channel not only for feedback, but also for future-directed  ...  However, learning from a human teacher poses additional challenges (and benefits) for Machine Learning systems.  ... 
doi:10.1109/roman.2006.314459 dblp:conf/ro-man/ThomazHB06 fatcat:hmssozyf7rdk7ghuzzi6vaiu34

Good Teachers: Visions of Values and Virtues in University Student Metaphors

Martin Cortazzi, Lixian Jin
2020 KEMANUSIAAN: The Asian Journal of Humanities  
This gives challenging insights for teachers (and students) to self-cultivate virtues if these participant visions are taken seriously for learner-centred approaches to humanities in new balances of continuity  ...  This elicited metaphor analysis explores student views of "good" teachers expressed in such metaphors as "a good teacher is a burning candle" or "a piece of chalk".  ...  An element of innovation is to recognise the fixity in some students' momentary expression in metaphors, as one Malaysian student reflected on her metaphors "Teachers are the virtues of good values, for  ... 
doi:10.21315/kajh2020.27.2.8 fatcat:hhz7wkoc7ngjlh2zlodm5uu7d4

Optimality of human teachers for robot learners

Maya Cakmak, Andrea L. Thomaz
2010 2010 IEEE 9th International Conference on Development and Learning  
In the second experiment we try to elicit the optimal teaching strategy.  ...  In this paper we address the question of how closely everyday human teachers match a theoretically optimal teacher.  ...  These results inform the design of robot learners, pointing out that a good place for the learner to intervene in the learning process is in helping the human select optimal negative examples. II.  ... 
doi:10.1109/devlrn.2010.5578865 dblp:conf/icdl/CakmakT10 fatcat:uawizgww4re2bgqnrrwlgmipey

Emerging Roles of Virtual Patients in the Age of AI

2019 The AMA Journal of Ethic  
Today's web-enabled and virtual approach to medical education is different from the 20th century's Flexner-dominated approach.  ...  This article reviews literature on virtual patients (VPs) and their underlying virtual reality technology, examines VPs' potential through the example of psychiatric intake teaching, and identifies promises  ...  One example is a virtual human, named Norman, created at the Massachusetts Institute of Technology. 24 Norman illustrates that the data used to teach a machine learning algorithm can significantly influence  ... 
doi:10.1001/amajethics.2019.153 pmid:30794125 fatcat:bjolkhts6vb7xpoizl2ugtlu3a

AI in Online-Learning Research: Visualizing and Interpreting the Journal Publications from 1997 to 2019

Gwo-Jen Hwang, Yun-Fang Tu, Kai-Yu Tang
2022 International Review of Research in Open and Distance Learning  
Accordingly, the roles and research trends as well as several suggestions for future research in the field of AIoL are provided as a reference for researchers and policy makers.  ...  In 2010–2014, AIoL research emphasized learner-oriented learning. In 2015–2019, learner-system interactions to facilitate personalized, adaptive, and collaborative learning became the main focus.  ...  technologies for online learning and teaching.  ... 
doi:10.19173/irrodl.v23i1.6319 doaj:2b3a93b3bfeb4f4bb333aa91deb75bed fatcat:peew5gcatvbsjcc2lniuz2phsq

Modelling Human Teaching Tactics and Strategies for Tutoring Systems: 14 Years On

Benedict du Boulay, Rosemary Luckin
2015 International Journal of Artificial Intelligence in Education  
These were via (i) the observation of human expert teachers, (ii) theoretical derivation from learning theories, and (iii) empirical observation of human and simulated students.  ...  Our original paper tried to characterize the richness of the teaching repertoire of expert human teachers and to give a sense of how far there still was to go in the development of pedagogic expertise  ...  Acknowledgments We thank the anonymous reviewers of this article for their many helpful comments and suggestions.  ... 
doi:10.1007/s40593-015-0053-0 fatcat:5bs6nvobqnbyjom7y5axsopzbu

Teachable robots: Understanding human teaching behavior to build more effective robot learners

Andrea L. Thomaz, Cynthia Breazeal
2008 Artificial Intelligence  
While Reinforcement Learning (RL) is not traditionally designed for interactive supervisory input from a human teacher, several works in both robot and software agents have adapted it for human input by  ...  This work demonstrates the importance of understanding the human-teacher/robot-learner partnership in order to design algorithms that support how people want to teach and simultaneously improve the robot's  ...  Approach: A HRI framework for machine learning Our approach is based on a Social Learner Hypothesis, namely that humans will naturally want to teach robots as social learners.  ... 
doi:10.1016/j.artint.2007.09.009 fatcat:tkudc3vyn5eovhanokt7cogecy

Designing Interactions for Robot Active Learners

Maya Cakmak, Crystal Chao, Andrea L Thomaz
2010 IEEE Transactions on Autonomous Mental Development  
Active learning is an attractive strategy for robot learners because it has the potential to improve the accuracy and the speed of learning, but it can cause issues from an interaction perspective.  ...  We conduct an experiment in which 24 human subjects teach concepts to our upper-torso humanoid robot, Simon, in each interaction mode, and we compare these modes against a baseline mode using only passive  ...  Prior work has tended to look at the problem of human-in-theloop active learning from the perspective of the machine learner. In this work, we also take the perspective of the human partner.  ... 
doi:10.1109/tamd.2010.2051030 fatcat:yte5lmqa5zh6zecjxjvab5pjx4

Learning From Others

Patrick Shafto, Noah D. Goodman, Michael C. Frank
2012 Perspectives on Psychological Science  
From early childhood, human beings learn not only from collections of facts about the world, but also in social contexts: from observation of other people, from communication, and from explicit teaching  ...  Learning from human action 3 Learning from others: The consequences of psychological reasoning for human learning Children are often compared to scientists, but even a perfect scientist, using experiments  ...  Alternately, my goal may be to communicate or teach someone something: Learning from human action 10 that this is good coffee (Clark, 1996; Grice, 1975; Sperber & Wilson, 1986) .  ... 
doi:10.1177/1745691612448481 pmid:26168471 fatcat:iykcdtv5yffohcrs4ef3h6s7xu

Factors Influencing Low Performance of Pupils in BDT Sewing at a Junior High School in Efutu Municipality

Rosemary Quarcoo
2018 International Journal of Innovative Research & Development  
The first part elicited responses on research question 1 'What factors accounts for the low performance of pupils in BDT sewing?'  ...  And also methods of teaching should be related to the stages of growth and development of learners. Sewing as a practical course should have been an interesting course when a good teacher handles it.  ...  allocate adequate time for BDT sewing.  The government, school authorities and individual families should help provide the basic teaching learning resources for BDT (Sewing) to the pupils.  Pupils should  ... 
doi:10.24940/ijird/2018/v7/i2/feb18020 fatcat:wrydw5nuazht7od7h7ule7ze7a
« Previous Showing results 1 — 15 out of 8,438 results