Results 1 - 10
of
10
Machine teaching: an inverse problem to machine learning and an approach toward optimal education
- THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI “BLUE SKY” SENIOR MEMBER PRESENTATION TRACK)
, 2015
"... I draw the reader’s attention to machine teaching, the prob-lem of finding an optimal training set given a machine learning algorithm and a target model. In addition to generating fascinating mathematical questions for computer scientists to ponder, machine teaching holds the promise of enhancing ed ..."
Abstract
-
Cited by 5 (4 self)
- Add to MetaCart
I draw the reader’s attention to machine teaching, the prob-lem of finding an optimal training set given a machine learning algorithm and a target model. In addition to generating fascinating mathematical questions for computer scientists to ponder, machine teaching holds the promise of enhancing education and personnel training. The Socratic dialogue style aims to stimulate critical thinking.
Multiarmed bandits for intelligent tutoring systems. (submitted
, 2015
"... We present an approach to Intelligent Tutoring Systems which adaptively personalizes sequences of learn-ing activities to maximize skills acquired by students, taking into account the limited time and motiva-tional resources. At a given point in time, the system proposes to the students the activity ..."
Abstract
-
Cited by 4 (4 self)
- Add to MetaCart
We present an approach to Intelligent Tutoring Systems which adaptively personalizes sequences of learn-ing activities to maximize skills acquired by students, taking into account the limited time and motiva-tional resources. At a given point in time, the system proposes to the students the activity which makes them progress faster. We introduce two algorithms that rely on the empirical estimation of the learning progress, RiARiT that uses information about the difficulty of each exercise and ZPDES that uses much less knowledge about the problem. The system is based on the combination of three approaches. First, it leverages recent models of intrinsically motivated learning by transposing them to active teaching, relying on empirical estimation of learning progress provided by specific activities to particular students. Second, it uses state-of-the-art Multi-Arm Bandit (MAB) techniques to efficiently manage the exploration/exploitation challenge of this optimization process. Third, it leverages expert knowledge to constrain and bootstrap initial exploration of the MAB, while requiring only coarse guidance information of the expert and allowing the system to deal with didactic gaps in its knowledge. The system is evaluated in a scenario where 7-8 year old schoolchildren learn how to decompose numbers while manipulating money. Systematic experiments are presented with simulated students, followed by results of a user study across a population of 400 school children.
Online Optimization of Teaching Sequences with Multi-Armed Bandits
"... We present an approach to Intelligent Tutoring Systems which adaptively personalizes sequences of learning activi-ties to maximize skills acquired by each student, taking into account limited time and motivational resources. At a given point in time, the system tries to propose to the student the ac ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
(Show Context)
We present an approach to Intelligent Tutoring Systems which adaptively personalizes sequences of learning activi-ties to maximize skills acquired by each student, taking into account limited time and motivational resources. At a given point in time, the system tries to propose to the student the activity which makes him progress best. We introduce two algorithms that rely on the empirical estimation of the learning progress, one that uses information about the dif-ficulty of each exercise RiARiT and another that does not use any knowledge about the problem ZPDES. The system is based on the combination of three approaches. First, it leverages recent models of intrinsically motivated learning by transposing them to active teaching, relying on empirical estimation of learning progress provided by spe-cific activities to particular students. Second, it uses state-of-the-art Multi-Arm Bandit (MAB) techniques to efficiently manage the exploration/exploitation challenge of this op-timization process. Third, it leverages expert knowledge to constrain and bootstrap initial exploration of the MAB, while requiring only coarse guidance information of the ex-pert and allowing the system to deal with didactic gaps in its knowledge. 1.
Exploring the Impact of Data-driven Tutoring Methods on Students' Demonstrative Knowledge in Logic Problem Solving
"... ABSTRACT We have been incrementally adding data-driven methods into the Deep Thought logic tutor for the purpose of creating a fully data-driven intelligent tutoring system. Our previous research has shown that the addition of data-driven hints, worked examples, and problem assignment can improve s ..."
Abstract
- Add to MetaCart
(Show Context)
ABSTRACT We have been incrementally adding data-driven methods into the Deep Thought logic tutor for the purpose of creating a fully data-driven intelligent tutoring system. Our previous research has shown that the addition of data-driven hints, worked examples, and problem assignment can improve student performance and retention in the tutor. In this study, we investigate how the addition of these methods affects students' demonstrative knowledge of logic proof solving using their post-tutor examination scores. We have used data collected from three test conditions with different combinations of our data-driven additions to determine which methods are most beneficial to students who demonstrate higher or lower knowledge of the subject matter. Our results show that students who are assigned problems based on profiling proficiency compared to prior exemplary students with similar problem-solving behavior show higher examination scores overall, and the use of proficiency profiling increases retention and reduces the amount of time taken in-tutor for lower performing students in particular. The results from this study also helps differentiate the behavior of higher and lower performing students in tutor, which can allow quicker interventions for lower proficiency students.
Predicting Off-task Behaviors in an Adaptive Vocabulary Learning System
"... ABSTRACT In many studies, engagement has been considered as an important aspect of effective learning. Retaining student engagement is thus an important goal in intelligent tutoring systems (ITS). My current studies with collaborators on Dynamic Support of Contextual Vocabulary Acquisition for Read ..."
Abstract
- Add to MetaCart
(Show Context)
ABSTRACT In many studies, engagement has been considered as an important aspect of effective learning. Retaining student engagement is thus an important goal in intelligent tutoring systems (ITS). My current studies with collaborators on Dynamic Support of Contextual Vocabulary Acquisition for Reading (DSCoVAR) include building prediction models for students' off-task behaviors. By extracting linguistically meaningful features and historical context information from interaction log data, these studies illustrate how some types of off-task behavior can be modeled from behavioral logs. The results of this research contribute to existing studies by providing examples of how to extract behavioral measures and predict off-task behaviors within a vocabulary learning system. Identifying off-task behaviors can improve students' learning by providing personalized learning materials: for example, off-task behavior classifiers can be used to achieve more accurate predictions of the student's vocabulary mastery level, which in turn can improve the system's adaptive performance. Toward our goal of developing highly effective personalized vocabulary learning systems, this research would benefit from expert feedback on issues that include: principled approaches for adaptive assessment and feedback in a vocabulary learning system; and alternative methods for defining and generating off-task labels.
Learning on the Job: Optimal Instruction for Crowdsourcing
"... A large body of crowdsourcing research focuses on using techniques from artificial intelligence to improve estimates of latent answers to ques-tions, assuming fixed (latent) worker quality. Re-cently, researchers have begun to investigate how best to actively improve worker quality through instructi ..."
Abstract
- Add to MetaCart
A large body of crowdsourcing research focuses on using techniques from artificial intelligence to improve estimates of latent answers to ques-tions, assuming fixed (latent) worker quality. Re-cently, researchers have begun to investigate how best to actively improve worker quality through instruction (Basu & Christensen, 2013; Singla et al., 2014). However, none of the existing work considers the fundamental tradeoff between pro-viding instruction and getting actual work done. In this work, we present a reinforcement learn-ing agent capable of optimizing the instruction it provides, by learning the effectiveness of its teaching actions, the quality of the worker pop-ulation, and the amount of work output it can expect from individual workers. Evaluations on synthetic data show that our agent learns adaptive instruction policies that significantly outperform common baseline strategies such as providing a tutorial of fixed length. 1.
Developmental Learning for Intelligent Tutoring Systems
, 2014
"... HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte p ..."
Abstract
- Add to MetaCart
(Show Context)
HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
Online Optimization and Personalization of Teaching Sequences
, 2014
"... HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte p ..."
Abstract
- Add to MetaCart
(Show Context)
HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
Learning to Teach like a Bandit
"... Designing a good course curriculum is a non-trivial task many teachers have to deal with on a regular basis. There are multiple learning methodologies available, but some of the basics are common; thus, one of the important steps is to identify key concepts and knowledge or skills prerequisites for ..."
Abstract
- Add to MetaCart
(Show Context)
Designing a good course curriculum is a non-trivial task many teachers have to deal with on a regular basis. There are multiple learning methodologies available, but some of the basics are common; thus, one of the important steps is to identify key concepts and knowledge or skills prerequisites for mastering them. If this can be done properly, a teacher acting as a course designer can think how to sequence the material. After the first edition of the course the teacher takes into account what went well and what adjustments to the course curriculum would be appropriate. With the growing popularity of ITS and recently MOOCs there are more opportunities for data-driven decisions on how to sequence learning materials and activities to optimize the learning process. Personalizing curriculum to different students is also becoming possible based on how well students learn or are expected to learn. Finding the best possible curriculum for all, a group or an individual student is a nontrivial problem that has an explore-exploit nature. We can use ideas of reinforcement learning and consider course design and learning activities sequencing as a kind of multi-armed bandit problem. We illustrate how to sequence these activities iteratively by employing the genetic process mining framework for generating a population of curriculum candidates from historical data and how to choose these candidates using the Bandit strategy to address the exploration-exploitation trade-off.
