SimStudent: A computational model of learning for Intelligent Authoring and beyond Noboru Matsuda Human-Computer Interaction Institute Carnegie Mellon.

Slides:



Advertisements
Similar presentations
Polynomial Inequalities in One Variable
Advertisements

What can CTAT do for you? Overview of the CTAT track Vincent Aleven, Bruce McLaren and the CTAT team 3rd Annual PSLC LearnLab Summer School Pittsburgh,
The Network of Dynamic Learning Communities C 107 F N Increasing Rigor February 5, 2011.
Educational data mining overview & Introduction to Exploratory Data Analysis Ken Koedinger CMU Director of PSLC Professor of Human-Computer Interaction.
* is a cluster of specific instructional strategies that involve students working collaboratively to reach common goals;
Collaborative Warrior Tutoring Tom Livak Neil Heffernan 8/24/06.
WHERE ARE THE COOKIES? A presentation by Jessica Hill.
An Individualized Web-Based Algebra Tutor D.Sklavakis & I. Refanidis 1 An Individualized Web-Based Algebra Tutor Based on Dynamic Deep Model Tracing Dimitrios.
Supporting (aspects of) self- directed learning with Cognitive Tutors Ken Koedinger CMU Director of Pittsburgh Science of Learning Center Human-Computer.
Fostering Algebraic Thinking October 26  December 2  6-hour Assignment after Session 2  January 20 Presented by: Janna Smith
Learning from Observations Copyright, 1996 © Dale Carnegie & Associates, Inc. Chapter 18 Spring 2004.
A C OMPUTATIONAL M ODEL OF A CCELERATED F UTURE L EARNING THROUGH F EATURE R ECOGNITION Nan Li Computer Science Department Carnegie Mellon University Building.
Projects March 29, Project Requirements Think Aloud –At least two people OR Difficulty Factors Assessment –Ideally >25 (at least one class), but.
LEARNING FROM OBSERVATIONS Yılmaz KILIÇASLAN. Definition Learning takes place as the agent observes its interactions with the world and its own decision-making.
Relational Data Mining in Finance Haonan Zhang CFWin /04/2003.
1 Learning from Behavior Performances vs Abstract Behavior Descriptions Tolga Konik University of Michigan.
Toward the extraction of production rules for solving logic proofs Tiffany Barnes, John Stamper Computer Science.
Our Explorations with CTAT!
B EAUCLERC E LEMENTARY S CHOOL Florida Standards Assessments.
7.6 Function Operations. Review: What is a function? A relationship where every domain (x value has exactly one unique range (y value). Sometimes we talk.
Building Intelligent Tutoring Systems with the Cognitive Tutor Authoring Tools (CTAT) Vincent Aleven and the CTAT team 7th Annual PSLC Summer School Pittsburgh,
Marcos Almeida Sue Young Chung Matthew Easterday Andrea Knight Scott Robertson Carnegie Learning Assistments Interface.
The Role of Visual Representations in Learning Mathematics John Woodward Dean, School of Education University of Puget Sound Summer Assessment Institute.
Dates:Tuesdays, Jan 7 – Feb 11
PSLC DataShop Introduction Slides current to DataShop version John Stamper DataShop Technical Director.
CALIFORNIA MATHEMATICS STANDARDS ALGEBRA Students identify and use the arithmetic properties of subsets of integers, rational, irrational, and real.
Quincy BrownKallen Tsikalas Research Questions & Hypotheses Theoretical Assumptions: Good, Bad & Ugly Using CTAT to test hypotheses The Interface Beneath.
A Framework for Inquiry-Based Instruction through
Introduction to the Cognitive Tutor Authoring Tools (CTAT) and Example-Tracing Tutors Bruce McLaren Systems Scientist, Co-Manager of the CTAT Project Team.
20-753: Fundamentals of Web Programming 1 Lecture 1: Introduction Fundamentals of Web Programming Lecture 1: Introduction.
بسم الله الرحمن الرحیم. Ehsan Khoddam Mohammadi M.J.Mahzoon Koosha K.Moogahi.
© 2001 Business & Information Systems 2/e1 Chapter 8 Personal Productivity and Problem Solving.
Lead Black Slide Powered by DeSiaMore1. 2 Chapter 8 Personal Productivity and Problem Solving.
Simulated Student: Building Cognitive Model by Demonstration Noboru Matsuda School of Computer Science Carnegie Mellon University.
Noboru Matsuda Human-Computer Interaction Institute
1 USC Information Sciences Institute Yolanda GilFebruary 2001 Knowledge Acquisition as Tutorial Dialogue: Some Ideas Yolanda Gil.
Spring 2011 Tutor Training Modern Learning Theories and Tutoring Designed and Presented by Tem Fuller.
CT & TuTalk: CT Percent Tutor + Metacognitive TuTalk Prompts Dr. Baba Kofi Weusijana Yvette Aqui
711: Intelligent Tutoring Systems Week 1 – Introduction.
+ Summer Institute for Online Course Development Institute – Assessment Techniques Presentation by Nancy Harris Dept of Computer Science.
Copyright © 2015, 2011, 2007 Pearson Education, Inc. 1 1 Chapter 7 Rational Expressions and Equations.
Preparation for the PSAT. Expectations at the High School Maturity Responsibility Accountability Get Involved Study Habits.
SimStudent: Building a Cognitive Tutor by Teaching a Simulated Student Noboru Matsuda Human-Computer Interaction Institute Carnegie Mellon University.
Algebra 7-1 and 7-2. Monomials DEFINITION: Monomial: a number, variable or the product of a number and 1 or more variables with nonnegative integer exponents.
Data mining with DataShop Ken Koedinger CMU Director of PSLC Professor of Human-Computer Interaction & Psychology Carnegie Mellon University.
6.6 Function Operations.
1 Learning through Interactive Behavior Specifications Tolga Konik CSLI, Stanford University Douglas Pearson Three Penny Software John Laird University.
Mass Producing Example- Tracing Tutors Bruce McLaren Human-Computer Interaction Institute Carnegie Mellon University.
George Goguadze, Eric Andrès Universität des Saarlandes Johan Jeuring, Bastiaan Heeren Open Universiteit Nederland Generation of Interactive Exercises.
A M ACHINE L EARNING A PPROACH FOR A UTOMATIC S TUDENT M ODEL D ISCOVERY Nan Li, Noboru Matsuda, William Cohen, and Kenneth Koedinger Computer Science.
Data Mining Lab Student performance evaluation. Rate of learning varies from student to student May depend on similarity of the problem Is it possible.
INTRODUCTION TO COMPUTER PROGRAMMING(IT-303) Basics.
TUESDAY 2.Solve the following equations. a. b. 3.Graph the line. 10x 5 -36x 14 -6r 7 = 13 + r -13 r = – x = -3x + x -8 = -2x x = 4.
Polynomial & Rational Inequalities
Inquiry learning and SimQuest
The Laws of Exponents.
Introduction to Standard Deviation
Teachers as Authors of Computer Based Tutoring Systems Dr
7.6 Function Operations.
Drill & Practice Programs
The Laws of Exponents.
Vincent Aleven & Kirsten Butcher
Simulated Student: Building Cognitive Model by Demonstration
2.6 Section 2.6.
10.6 Function Operations.
7.6 Function Operations.
The Laws of Exponents.
Function Operations.
1.5 Function Operations.
Habit Formation/ behaviourism
Presentation transcript:

SimStudent: A computational model of learning for Intelligent Authoring and beyond Noboru Matsuda Human-Computer Interaction Institute Carnegie Mellon University

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) 2 CTAT: Cognitive Tutor Authoring Tools Example-Tracing Tutor –Zero programming –A cognitive model specific to a particular problem –Limited generalization by editing a behavior graph Model-Tracing Tutor –Requires a cognitive model –Cognitive task analysis is hard –Writing production rules is even more challenging Performing a task is much easier…

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) 3 Next Generation Authoring Build a tutor GUI Teaching a solution SimSt. learning Rule simplify-LHS: IFis-equation( Eq ), is-lhs( Eq, Lhs ), polynomial( Lhs ), all-var-terms( Lhs ) Thensimplify( Lhs, S-lhs ), enter( S-lhs ) Production Rules Rule simplify-LHS: IFis-equation( Eq ), is-lhs( Eq, Lhs ), polynomial( Lhs ), all-var-terms( Lhs ) Thensimplify( Lhs, S-lhs ), enter( S-lhs ) Rule simplify-LHS: IFis-equation( Eq ), is-lhs( Eq, Lhs ), polynomial( Lhs ), all-var-terms( Lhs ) Thensimplify( Lhs, S-lhs ), enter( S-lhs )

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) 4 SimStudent Machine learning agent –Learns problem-solving steps by … –Observes model solutions / solving problems, and … –Outputs a set of production rules Fundamental technology –Programming by Demonstration –Inductive Logic Programming Lau & Weld (1998). Blessing (1997).

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) Authoring Strategies Authoring by demonstration –Demonstrate whole solutions –Learning from worked-out examples Demonstrated solutions as positive examples Authoring by tutoring –Interactively tutor with immediate feedback and hint –Learning by tutored problem-solving Learning by generalizing hint with taking feedback into account 5

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) Demo! 6 Authoring by Tutoring

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) Learning Production Rules in 3 parts: What-When-How If among this and that GUI elements such and such constraints hold Then do actions with the GUI elements When What How

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) Production Rule in JESS GUI elements Constraints Actions

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) 9 Background Knowledge Domain concepts to “explain” demonstrations –Operators –Feature predicates External Jess function written in Java (defrule multi-lhs … ?var22140 <- (column (cells ? ? ?var22143 ? ? ? ? ?)) ?var22143 <- (cell (value ?val0&~nil)) (test (fraction-term ?val0 )) => (bind ?val2 (denominator ?val0)) (bind ?input (mul-term-by ?val0 ?val2)) … )

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) 10 Example : Algebra domain 16 Feature predicates & 28 operators Feature Predicates for LHS conditionsOperators for RHS actions HasCoefficient HasConstTerm HasVarTerm Homogeneous IsFractionTerm IsConstant IsDenominatorOf IsNumeratorOf IsPolynomial Monomial NotNull VarTerm IsSkillAdd IsSkillSubtract IsSkillDivide IsSkillMultiply AddTerm AddTermBy Coefficient CopyTerm Denominator DivTerm DivTermBy EvalArithmetic FirstTerm FirstVarTerm GetOperand InverseTerm LastConstTerm LastTerm LastVarTerm MulTerm MulTermBy Numerator ReverseSign RipCoefficient SkillAdd SkillClt SkillDivide SkillMultiply SkillRf SkillMt SkillSubtract VarName

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) 11 Learning Results # of training tasks % Correct rule firings (10 test tasks) Authoring by tutoring Authoring by demonstration Better than

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) 12 Authoring Time Authoring by Tutoring Authoring by Demonstration Authoring by tutoring took 86 minutes Authoring by demonstration took 238 minutes A 2.8x speed-up!

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) 13 Example: Stoichiometry Tutor

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) SimStudent Projects Intelligent Authoring –Building a Cognitive Tutor as a CTAT Plug-in Student Modeling and Simulation –Controlled educational studies –Error formation study –Prerequisite conceptual knowledge study Teachable Peer Learner –Learning by teaching 14

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) SimStudent Projects Intelligent Authoring –Building a Cognitive Tutor as a CTAT Plug-in Student Modeling and Simulation –Controlled educational studies –Error formation study –Prerequisite conceptual knowledge study Teachable Peer Learner –Learning by teaching 15

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) Model of Incorrect Learning Identify errors students commonly make Weaken SimStudent’s background knowledge Let SimStudent make an induction error 16

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) Weak Prior Knowledge Hypothesis Multiple ways to make sense of examples 17 3x=5 “divide by 3” Get a coefficient and divide Get a number and divide Get a denominator and multiply 4/x=5 strong prior knowledge weak prior knowledge “divide by 4” “multiply by x”

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) Target Common Errors 18

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) Results: Learning Rate Steps Score = 0 (if there is no rule applicable) # correct rule applications / # all rule applications # training problems Step Score

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) SimStudent Projects Intelligent Authoring –Building a Cognitive Tutor as a CTAT Plug-in Student Modeling and Simulation –Controlled educational studies –Error formation study –Prerequisite conceptual knowledge study Teachable Peer Learner –Learning by teaching 20

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) Learning by Teaching SimStudent

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) Demo! 22 Learning by Teaching

SimStudent Project PSLC Summer School 2010 :: SimStudent Demo :: Noboru Matsuda (CMU) Learn more about SimStudents Project Web – Download & Tutorial – (linked from project web) Contact us! 23