Intelligent tutor systems
Upcoming SlideShare
Loading in...5
×
 

Like this? Share it with your network

Share

Intelligent tutor systems

on

  • 1,710 views

A cognitive overview of ITS

A cognitive overview of ITS

Statistics

Views

Total Views
1,710
Views on SlideShare
1,710
Embed Views
0

Actions

Likes
1
Downloads
59
Comments
0

0 Embeds 0

No embeds

Accessibility

Categories

Upload Details

Uploaded via as Microsoft PowerPoint

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment
  • CAI are just simply the branch algorithms – student’s behaviour not considered Can explain the procedure used to solve a problem – can present multiple solutions – difference between saying what happened and explaining why it was the right thing to do Builds a distinct model of what the student knows Coach is passive, providing help only when asked – Tutor observes a student and decides when to offer help
  • This is an ideal model – not every implementation follows this system Describe the cycle What is saved between sessions? Cumulative record from one problem to another of what the student knows – perhaps some info about what the tutor couldn’t understand about the student’s behavior [exceptions are saved, which later are used to generalize the concept]
  • ACT* is a general theory of cognition developed by John Anderson and colleagues at Carnegie Mellon Univeristy that focuses on memory processes Declarative memory takes the form of a semantic net linking propositions, images, and sequences by associations Procedural memory (also long-term) represents information in the form of productions; each production has a set of conditions and actions based in declarative memory All knowledge begins as declarative information; procedural knowledge is learned by making inferences from already existing factual knowledge
  • The conditions of productions contains patterns that must match the info held in students working memory Limited size of working memory Learner becomes more skilled at a domain by acquiring new productions that encode special rules for solving problems in that domain New productions are formed only during problem solving – formal instruction is made part of problem solving Immediate feedback to students
  • 68 production rules to be precise Can solve a problem using these production rules when the problem encoded as working set elements is provided to the Tutor Buggy productions to track what the student might have got wrong In case of more than one error, Tutor may set sub goals and handle those sub goals first
  • The pedagogical plan consists of tutorial agenda and tutorial questions that can be used alone, or in combination, to generate a tutorial strategy Use heuristic to decide what to focus the conversation on The human tutors and learners have a remarkably incomplete understanding of each other’s knowledge base and that many of each other’s contributions are not deeply understood… Most tutors have only an approximate assessment of the quality of student contributions Agenda is a stack of what Tutor wants to talk about The tutorial model can ask the following kinds of tutorial questions illustrated with an example of how the question can be phrased: Q_symb : Symbolize a given quantity (“Write an expression for the distance Anne has rowed?”) Q_compute: Find a numerical answer (“Compute the distance Anne has rowed?”) Q_explain: Write a symbolization for a given arithmetic quantity. This is the articulation step. (“How did you get the 120?”) Q_generalize: Uses the results of a Q_explain question (“Good, Now write your answer of 800-40*3 using the variables given in the problem (i.e., put in ‘m’)”) Q_represents_what: Translate from algebra to English (“In English, what does 40m represent?” (e.g., “the distance rowed so far”)) Q_explain_verbal: Explain in English how a quantity could be computed from other quantities. (We have two forms: The reflective form is “Explain how you got 40*m” and the problem solving form is “Explain how you would find the distance rowed?”) Q_decomp: Symbolize a one-operator answer, using a variable introduced to stand for a sub-quantity. (“Use A to represent the 40m for the distance rowed. Write an expression for the distance left towards the dock that uses A.”) Q_substitute: Perform an algebraic substitution (“Correct, that the distance left is given by 800-A. Now, substitute “40m” in place of A, to get a symbolization for the distance left.”)
  • ICAI say that “Here are my rules. Use them!” CAI say “Here are my programs. Learn from them!”
  • Do you know the answer ?? :D

Intelligent tutor systems Presentation Transcript

  • 1. Intelligent Tutor Systems
  • 2. Before We Start …
  • 3. Intelligent ???
    • ICAI – Intelligent Computer Aided Instructions
    • Ability to solve the problems they present
    • Individualization
    • Tutor and not a Coach
  • 4. Components Of ITS
  • 5. ACT*
  • 6. Features of ACT*
    • Set of rules in which each rule represents a unit of skill
    • Productions are goal directed
    • Knowledge Compilation
    • Limited Working Memory
  • 7. Example : Symbolization
    • Goal: Write an algebraic expression given a real world problem context
    • Tutor’s Pedagogical Content Knowledge
      • Domain knowledge
      • General tutoring rules
      • Content specific strategies
  • 8. To Build A Good Tutor
    • Study what makes the domain difficult including discovering what types of errors students make
    • Construct a theory of how students solve these problems
    • Observe experienced human tutors to find what pedagogical knowledge content they have
  • 9. Ms. Lindquist’s Architecture
  • 10. Cognitive Student Model
    • If-Then rules on working set elements
    • Buggy productions
    • If the correct answer is 5g + 7(30 - g)
    • Student model reports full diagnosis to Tutor Model
  • 11. Tutor Model
    • Again implemented using production rules
    • Choose the pedagogical plan for the received diagnosis
    • Focusing heuristic
    • Tutorial Agenda
    • Tutorial Questions
    • Tutorial Strategies
  • 12. Concrete Articulation Strategy
  • 13. Introduced Variable Strategy
  • 14. Explain In English Strategy
  • 15. Principles For Design Of Tutors
    • Represent student competence as a production set
    • Communicate the goal structure underlying the problem solving
    • Provide instruction in problem solving context
    • Promote an abstract understanding of the problem solving knowledge
    • Minimize working memory load
    • Provide immediate feedback on errors
    • Adjust the grain size of instruction with learning
    • Facilitate successive approximations to the target skill
  • 16. Still Only A Lot Of Promises
    • Education has not been turned upside down
    • CAI still better than ICAI
  • 17. Just To Wake Everyone Up …