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 ...
详细信息
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. To elicit better teaching, we propose giving humans teaching guidance, which are instructions on how to teach, derived from computational teaching algorithms or heuristics. We present experimental results demonstrating that teaching guidance substantially improves human teaching in three different problem domains. This provides promising evidence that human intelligence and flexibility can be leveraged to achieve better sample efficiency when input data to a learning system comes from a human teacher. (C) 2014 Elsevier B.V. All rights reserved.
The present paper introduces a new model for teaching randomized learners. Our new model, though based on the classical teaching dimension model, allows to study the influence of the learner's memory size and of t...
详细信息
The present paper introduces a new model for teaching randomized learners. Our new model, though based on the classical teaching dimension model, allows to study the influence of the learner's memory size and of the presence or absence of feedback. Moreover, in the new model the order in which examples are presented may influence the teaching process. The resulting models are related to Markov decision processes, and characterizations of optimal teachers for memoryless learners with feedback and for learners with infinite memory and feedback are shown. Furthermore, in the new model it is possible to investigate new aspects of teaching like teaching from positive data only or teaching with inconsistent teachers. Characterization theorems for teachability from positive data for both ordinary teachers and inconsistent teachers with and without feedback are provided. (C) 2010 Elsevier Inc. All rights reserved.
Robots can learn preferences from human demonstrations, but their success depends on how informative these demonstrations are. Being informative is unfortunately very challenging, because during teaching, people typic...
详细信息
Robots can learn preferences from human demonstrations, but their success depends on how informative these demonstrations are. Being informative is unfortunately very challenging, because during teaching, people typically get no transparency into what the robot already knows or has learned so far. In contrast, human students naturally provide a wealth of nonverbal feedback that reveals their level of understanding and engagement. In this work, we study how a robot can similarly provide feedback that is minimally disruptive, yet gives human teachers a better mental model of the robot learner, and thus enables them to teach more effectively. Our idea is that at any point, the robot can indicate what it thinks the correct next action is, shedding light on its current estimate of the human's preferences. We analyze how useful this feedback is, both in theory and with two user studies-one with a virtual character that tests the feedback itself, and one with a PR2 robot that uses gaze as the feedback mechanism. We find that feedback can be useful for improving both the quality of teaching and teachers' understanding of the robot's capability.
暂无评论