Transcript unit v: intelligent tutoring system and its application

UNIT V: INTELLIGENT TUTORING
SYSTEM AND ITS APPLICATION
Dr. Bo Liu
South China Normal University
School of Information Technology in Education
Email: [email protected]
Outline
•
•
•
•
Intelligent tutoring system (ITS)
The central frame of intelligent
tutoring system (ITS)
Techniques of intelligent tutoring
system (ITS)
One applying case of ITS
2
Intelligent tutoring system (ITS)
•
•
•
Artificial intelligence (AI)
Intelligent tutoring system (ITS)
Representative models-MYCIN;WEST;GUIDON
3
Artificial intelligence (AI)
The only way not to succeed is not to try.
----------Edward Teller(1908-2003)
Artificial Intelligence (shorted as AI) is the study of manmade computational devices and systems which can be
made to act in a manner which we would be inclined to
call intelligent.
4
History of AI
• The 'Dark Ages', or the birth of artificial
intelligence (1943-56)
• The rise of artificial intelligence, or the era of
great expectations (1956-late 1960s)
• Unfulfilled promises, or the impact of reality
(late 1960s-early 1970s)
• The technology of expert systems, or the key
to success (early 1970s-mid-1980s)
• How to make a machine learn, or the rebirth of
neural networks (mid-1980s-onwards)
5
A summary of the main events in
the history of AI
6
7
8
9
10
11
Intelligent tutoring system (ITS)
• In 1982, Sleeman and Brown reviewed the
state of the art in computer aided instruction
and first coined the term Intelligent Tutoring
Systems (ITS) --Sleeman, D., & Brown, J. S. (1982). Introduction:
Intelligent Tutoring Systems. In D. Sleeman & J. S. Brown (Eds.), Intelligent
Tutoring Systems (pp. 1-11). New York: Academic Press.
12
Goal of ITS
• To modularize the curriculum
• To engage the students in sustained reasoning
activity
• To interact with the student based on a deep
understanding of the students behavior
• Collect data which instructors could use to tutor
and remediate students
If ITS could realize even half the impact of human tutors, the
payoff for society promised to be substantial.
13
Learning Activity I
Group discussion
•
What do you think about the current
status of ICAI and ITS? Giving your
reasons.
• Can we use ICAI and ITS in
educational field? Describing yours
perspectives.
– Time limitation: 20 Minutes
14
Representative models
• MYCIN
• WEST
• GUIDON
15
• MYCIN
• It was an early expert system developed over five or six years
in the early 1970s at Stanford University
• It was written in Lisp as the doctoral dissertation of Edward
Shortliffe
• This expert system was designed to identify bacteria causing
severe infections, such as bacteremia and meningitis, and to
recommend antibiotics, with the dosage adjusted for patient's
body weight — the name derived from the antibiotics
themselves, as many antibiotics have the suffix "-mycin".
16
WEST
WEST is an example of a coach
system. It is built on top of the
game "How the West was Won".
It is a child's game, a variation of
a game also called "Shoots and
Ladders" (Figure showing).
The game was originally available
on the PLATO system. PLATO is
the tutoring environment that was
developed by Computer
Development Corporation, CDC,
in the 1960s.
17
• GUIDON( Clancey W.J., 1987),
GUIDON is an intelligent computer-aided instructional program
for teaching diagnosis, such as medical diagnosis. The
program is general. Without reprogramming, the program can
discuss with a student any diagnostic problem that it can
solve on its own.
In instructional programs, knowledge is represented as linguistic
schemas (rules) such as:
I F the site of the culture is normally sterile and
the gram-stain of the organism is negative,
THEN there is strongly suggestive evidence that there is
significant disease associated with this occurrence of the
organism.
18
The central frame of intelligent
tutoring system (ITS)
 The basic constitutes of ITS
 The central frame of ITS
19
The basic constitutes of ITS
(1) a task environment
(2) a domain knowledge module
(3) a student model
(4) a pedagogical module
20
• The Problem-Solving Environment.
• This component of the tutor defines the problem
solving activities in which the student is engaged.
At minimum it consists of an editor that accepts
and represents student actions.
(1) The ITS problem solving environment should
approximate the real world problem solving
environment.
(2) The ITS problem solving environment should
facilitate the learning process.
21
• The Domain Expert.
• As its name suggests, the domain expert module
represents the content knowledge that the student
is acquiring. This module is at the heart of an
intelligent tutoring system and provides the basis for
interpreting student actions. Classically, the domain
module
22
• The Student Model.
• The student model is a record of the student’s
knowledge state. There are classically two
components in a student model: an overlay of the
domain expert knowledge and a bug catalog.
23
• The Pedagogical Module.
• The pedagogical module is responsible for structuring
the instructional interventions. This module may
operate at two levels (Pirolli and Greeno, 1998).
• At the curriculum level it can sequence topics to
ensure an appropriate prerequisite structure is
observed (Capell and Dannenberg, 1993)
• individualize the amount of practice at each level to
ensure the students master the material (Corbett and
Anderson, 1995b).
24
Central frame of ITS
TUTORING SYSTEM
Modeler
Predicted and
Preferred behavior
Relations and
Student Prototypes
Expert Simulator
Update Model
Knowledge Base
Explanation Data
Problem Solving
Situation
Student Model
Students Current state
Tutor
Problem
Information
Problem
Advice &Explanation
Data Request
Problem Data
Student
25
Intelligent tutoring system (ITS)
techniques
•
•
•
Knowledge expression
Logic reasoning
Expert system
26
Knowledge expression
• production rules: MYCIN,
PROSPECTION
• mathematical logics;
• frames;
• scripts;
• semantic net;
• relational database
27
Logic reasoning
We begin our exploration of the use of
mathematical logic in computer deduction
by illustrating several simple approaches
that use the propositional calculus, Then
we turn to the more powerful predicate
calculus and examine some heuristics and
strategies for trying to prove proposed
conclusions.
28
Expert
system
structure
29
One applying case of ITS
• Process of developing ITS
• Studying case posting
30
• Figure right displays the major activities in
tutor development: (I) needs assessment, (2)
cognitive task analysis, (3) tutor
implementation and (4) evaluation.
• The first step is common to all software
design. In the case of ITS design, this
involves specifying educational goals and
curriculum.
• The second stage is common to expert
systems programming, although the target is
defined more narrowly here: a cognitively
valid model of problem solving performance.
• The third phase consists of initial tutor
implementation, which is followed by a series
of evaluation activities: (1) pilot studies to
confirm basic usability and educational
impact; (2) formative evaluations of the
system under development, including (3)
parametric studies that examine the
effectiveness of system features and finally, (4)
summative evaluations of the final tutor’s
effect: learning rate and asymptotic
achievement levels.
31
Studying case posting
• Math learning system
• Whale Watcher system
32
Assignment
•
•
Describing the mechanism of an
ICAI or ITS system. You can freely
find out any one ICAI or ITS system
by yourself.
Explaining yours perspectives on
ICAI and ITS.
33