Filters








1,126 Hits in 6.1 sec

Simulated Students, Mastery Learning, and Improved Learning Curves for Real-World Cognitive Tutors

Stephen E. Fancsali, Tristan Nixon, Annalies Vuong, Steven Ritter
2013 International Conference on Artificial Intelligence in Education  
specifically on aspects of mastery learning in Bayesian Knowledge Tracing and learning curve analysis to improve cognitive (skill) models.  ...  We briefly describe three approaches to simulating students to develop and improve intelligent tutoring systems.  ...  Introduction There are at least three general approaches to simulating students for the purposes of improving cognitive (skill) models and other features of intelligent tutoring systems (ITSs).  ... 
dblp:conf/aied/FancsaliNVR13 fatcat:xoyj4q33ivbirbqqn4x4tuqlem

Optimal and Worst-Case Performance of Mastery Learning Assessment with Bayesian Knowledge Tracing

Stephen Fancsali, Tristan Nixon, Steven Ritter
2013 Educational Data Mining  
By implementing mastery learning, intelligent tutoring systems aim to present students with exactly the amount of instruction they need to master a concept.  ...  In this paper, we provide a framework for understanding the role of the mastery threshold in Bayesian Knowledge Tracing and use simulations to model the effects of setting different thresholds under different  ...  Charles Murray, Brendon Towle, and Michael Yudelson on an early draft of this paper.  ... 
dblp:conf/edm/FancsaliNR13 fatcat:5dhr35oobfbmzmihkiicbzikl4

The real world significance of performance prediction

Zachary A. Pardos, Qing Yang Wang, Shubhendu Trivedi
2012 Educational Data Mining  
Two years of student tutor use and corresponding student state test scores are used for the analysis of test prediction while a simulation study is conducted to investigate the correspondence between performance  ...  While these models have brought statistically reliable improvement to performance prediction, the real world significance of the differences in errors has been largely unexplored.  ...  We thank Feng & Heffernan for the datasets and the Worcester Public Schools for their ongoing partnership and for making test scores available to us.  ... 
dblp:conf/edm/PardosWT12 fatcat:qjjcvxwi3bgcjelcgzjhr5ci7e

Lifelong Personalization via Gaussian Process Modeling for Long-Term HRI

Samuel Spaulding, Jocelyn Shen, Hae Won Park, Cynthia Breazeal
2021 Frontiers in Robotics and AI  
We evaluate this method in a series of simulation experiments comparing different approaches to continual and multitask learning on simulated student data.  ...  We expect this method to substantially improve learning in Gaussian Process models in dynamic domains, establishing Gaussian Processes as another flexible modeling tool for Long-term Human-Robot Interaction  ...  Without accounting for shift in dynamic student mastery, the learning curve for static-GP models flattens and even declines slightly.  ... 
doi:10.3389/frobt.2021.683066 pmid:34164437 pmcid:PMC8215502 fatcat:wetgbxbkbnconkcfkwnhy3jcxi

Exploring the Assistance Dilemma in Experiments with Cognitive Tutors

Kenneth R. Koedinger, Vincent Aleven
2007 Educational Psychology Review  
Cognitive Tutors are a type of intelligent tutor based on cognitive psychology theory of problem solving and learning.  ...  Intelligent tutoring systems are highly interactive learning environments that have been shown to improve upon typical classroom instruction.  ...  For example, the Algebra Cognitive Tutor, shown in Fig. 1 , provides students with real-world scenarios that require algebraic reasoning, as well as various tools, such as a worksheet, a grapher, and  ... 
doi:10.1007/s10648-007-9049-0 fatcat:2smamx25ije7vpkysql57uoixi

Convergent Validity of a Student Model: Recent-Performance Factors Analysis

Ilya M. Goldin, April Galyardt
2015 Educational Data Mining  
We use a dataset from a tutoring system where the skill model has been improved by the Learning Factors Analysis algorithm for skill model refinement and by expert validation.  ...  We argue that R-PFA may be sensible as a predictive model in Learning Factors Analysis because of its convergent validity and because the R predictor of R-PFA represents mastery-aligned learning curves  ...  We thank Ran Liu for thoughtful comments and assistance.  ... 
dblp:conf/edm/GoldinG15 fatcat:eeskui54uzajjlsf5lqr3oij7m

Reconstruction of collaborative problem solving based learning in thermodynamics with the aid of interactive simulation and derivative games

A R Sinensis, H Firman, I Hamidah, M Muslim
2019 Journal of Physics, Conference Series  
Therefore through the CPS model can be students are trained in cooperating, collaborating, arguing for solutions by utilizing technology and information to address world challenges in the 21st century.  ...  The reconstruction of thermodynamic learning aims to develop and innovate the student-centred learning.  ...  Acknowledgments Thanks to the LPDP (Lembaga Dana Dana Pendidikan) the Indonesian Ministry of Finance who has provided financial support to support the author in this research and writing  ... 
doi:10.1088/1742-6596/1157/3/032042 fatcat:lpegy3pybbfbdmapbpubhtzmxu

pyBKT: An Accessible Python Library of Bayesian Knowledge Tracing Models [article]

Anirudhan Badrinath, Frederic Wang, Zachary Pardos
2021 arXiv   pre-print
Bayesian Knowledge Tracing, a model used for cognitive mastery estimation, has been a hallmark of adaptive learning research and an integral component of deployed intelligent tutoring systems (ITS).  ...  Additionally, we conduct sanity checks of the model using experiments with simulated data to evaluate the accuracy of its EM parameter learning and use real-world data to validate its predictions, comparing  ...  Johnson, who co-developed xBKT, the predecessor to pyBKT, and Cristian Garay, who developed the initial Python and Boost adaptation of xBKT.  ... 
arXiv:2105.00385v2 fatcat:pmjk3zp2hba3noupv4hst6i7kq

Learning in the 21st Century: Concepts and Tools

Nader Rifai, Todd Rose, Graham T. McMahon, Bror Saxberg, Ulrik Juul Christensen
2018 Clinical Chemistry  
, so there is a real risk that too deep a focus on preparing for standardized tests misses the full preparation required for applying decisions and masteries in the real world.  ...  A notion of "learning engineering"-applying learning science at scale to solve real-world constrained problems and iterate with good measures to continuously improve learning-could be a promising direction  ... 
doi:10.1373/clinchem.2018.292383 pmid:30097495 fatcat:vvtofuyehbh77gzdmty2m3zdbi

Intelligent Tutoring Systems

J. R. Anderson, C. F. Boyle, B. J. Reiser
1985 Science  
Consequently, similarity of learning environments and real world environments affords greater transfer of learning.  ...  The points from the original learning curve in Figure 7 are plotted as two separate learning curves for these rules.  ... 
doi:10.1126/science.228.4698.456 pmid:17746875 fatcat:brtoolbl6nffnoc3qt72aaqshm

Extending Adaptive Spacing Heuristics to Multi-Skill Items

Benoit Choffin, Fabrice Popineau, Yolaine Bourda
2021 Zenodo  
To compare these five heuristics, we develop a synthetic experimental framework that simulates student learning and forgetting trajectories with a student model.  ...  We run multiple synthetic experiments on large cohorts of 500 simulated students and publicly release the code for these experiments.  ...  They ran both simulated and real-world experiments, in which participants had to study 30 Japanese-English word pairs for 22 minutes and to complete a test 3 days later.  ... 
doi:10.5281/zenodo.5634220 fatcat:tt6mufyxxvalremums2et3adle

The practicality and effectiveness of case study-based module on chemical thermodynamics course (ideal and real gases) as learning tool during the COVID-19 pandemic

Findiyani Asih, Sri Poedjiastoeti, Achmad Lutfi, Dian Novita, Ismono Ismono, Amalia Purnamasari
2022 Journal of Technology and Science Education  
The case study-based module on chemical thermodynamics course (ideal and real gases) was developed to fulfill the needs of undergraduate students in online learning during the COVID-19 pandemic.  ...  The case study-based module was suitable for one of learning tools, which was proven by the findings that 1) meets valid and reliable criteria, 2) meets practical criteria with support for general achievements  ...  Meanwhile, students who have better academic (mastery of concepts) can be used as peer tutors for their friends who still have difficulty understanding the material.  ... 
doi:10.3926/jotse.1654 fatcat:kll6vwlbsbbuvphp4vmpckujfe

Rule-Based Cognitive Modeling for Intelligent Tutoring Systems [chapter]

Vincent Aleven
2010 Studies in Computational Intelligence  
Cognitive Tutors using rule-based cognitive models have been proven to be successful in improving student learning in a range of learning domain.  ...  On-going work in educational data mining may lead to novel techniques for improving the cognitive fidelity of models and thereby the effectiveness of tutors.  ...  Albert Corbett and Laurens Feenstra gave very helpful comments on an early draft of the chapter.  ... 
doi:10.1007/978-3-642-14363-2_3 fatcat:r4oyeivhijebzm4apdrup6q4qy

Spanning seven orders of magnitude: a challenge for cognitive modeling

J Anderson
2002 Cognitive Science  
The unit-task level, at the boundary of the Cognitive and Rational Bands, is useful for assessing these theses.  ...  The Modeling Thesis claims that cognitive modeling provides a basis for bridging between events on the small scale and desired outcomes on the large scale.  ...  Bloom (1984) reported that students who had private human tutors performed 2 standard deviations better than control students from regular classrooms.  ... 
doi:10.1016/s0364-0213(01)00062-3 fatcat:kusaousmrzbz5o2kfg66ydqgc4

Spanning seven orders of magnitude: a challenge for cognitive modeling

John R. Anderson
2002 Cognitive Science  
The unit-task level, at the boundary of the Cognitive and Rational Bands, is useful for assessing these theses.  ...  The Modeling Thesis claims that cognitive modeling provides a basis for bridging between events on the small scale and desired outcomes on the large scale.  ...  Bloom (1984) reported that students who had private human tutors performed 2 standard deviations better than control students from regular classrooms.  ... 
doi:10.1207/s15516709cog2601_3 fatcat:cn7tjmb7xndsdgldrjxxlhd5um
« Previous Showing results 1 — 15 out of 1,126 results