Transcript No Slide Title

Adaptive Learning Systems
Associate Professor Kinshuk
Information Systems Department
Massey University, Private Bag 11-222
Palmerston North, New Zealand
Tel: +64 6 350 5799 Ext 2090
Fax: +64 6 350 5725
Email: [email protected]
URL: http://fims-www.massey.ac.nz/~kinshuk/
1
Introduction
• Adaptive learning systems with particular
focus on cognitive skills
• Accommodation of both the ‘instuction’
and ‘construction’ of knowledge
• Design based on informed educational
methodologies
2
What exactly we mean by
Adaptivity
in
Adaptive Learning Systems?
3
“Intelligence”/adaptivity
Increased user efficiency, effectiveness
and satisfaction
by
Improved correspondence between
learner, goal and system characteristics
4
Need of Intelligence/adaptivity
 Users generally work on their own
without external support.
 System is used by variety of users from
all over the world.
 Customised system behaviour reduces
meta-learning overhead for the user
and allows focus on completion of
actual task.
5
Adaptable Systems
Systems that allow the user to
change certain system
parameters and adapt the
system behaviour accordingly.
Adaptive Systems
Systems that adapt to the users
automatically based on system’s
assumptions about user needs.
6
7
How does adaptivity work?
 System monitors user’s action patterns
with various components of system’s
interface.
 Some systems support the user in the
learning phase by introducing them to
system operation.
 Some systems draw user’s attention to
unfamiliar tools.
 User errors are primary candidate for
automatic adaptation.
8
Levels of adaptation
 Simple: “hard-wired”
 Self-regulating: monitors the effects of
adaptation and changes behaviour
accordingly
 Self-mediating: Monitors the effects of
adaptation on model before putting into
practice
 Self-modifying: Capable of chaging
representations by reasoning about the
interactions
9
Problems in adaptation
 User is observed by the system, actions
are recorded, giving rise to data and
privacy protection issues.
 Social monitoring becomes possibility.
 User feels being controlled by the system.
 User is exposed to adaptation concept
favoured by the designer of the system.
 User may be distracted from the task by
sudden automatic modifications.
10
Recommendation for adaptive systems
 Means for user to (de)activate or limit
adaptation procedure
 Offering adaptation in the form of
proposal
 User may define specific parameters used
in adaptation
 Giving user information about effects of
adaptation hence preventing surprises
 Editable user model
11
Domain competence
And
computers
12
Constituents of Domain Competence
Easier to
learn from
mistakes
Reflection oriented and
abstract
Action oriented
and experiential
Know-why
Know-how
Trial and error
Difficult to
learn from
mistakes
logical processes
Know-why-not
Know-how-not
Know-when
An example of the
know-how aspect
of know-when is
the temporal
context required for
an appropriate
sequence of
operation
Know-when-not
Context oriented and both
experiential and abstract
Know-what
Know-about
Awareness oriented
13
An example of the
know-why aspect
of know-when is
the environmental
and behavioural
contexts required
for making a
decision
Constituents of Domain Competence
Know-how
 It has an operational orientation.
 It is mainly action-driven and hence predominantly experiential.
 It is difficult to inherit it from someone
else’s experience.
Know-how-not
 Learning by mistakes.
Examples : Computer simulation and virtual
reality
14
Constituents of Domain Competence
Know-why
 It has a causal orientation.
 It is mainly reflection-driven and therefore
based on abstraction.
 It can be inherited from someone else’s line
of reasoning.
Know-why-not
 Logical processes.
 Needs deeper reflection.
15
Constituents of Domain Competence
Know-when (and -where)
 It has a contextual orientation.
 It provides the temporal and spatial context
for both the know-how and know-why. It is
thus both action and/or reflection driven.
16
Constituents of Domain Competence
Know-about
 It has an awareness orientation.
 It includes above three types of knowledge
in terms of know-what.
 It also contains information about the
environmental context of this knowledge.
17
Instruction in knowledge context
Ideally, an instructional system, designed for novice
users, teach all knowledge constituents.
But, know-why is difficult to handle mainly for two
reasons:
1. It needs natural language interaction.
2. It needs use of metaphors, which are difficult to
understand for a novice user.
Know-how, on the other hand, is operational, and
can be conveyed to the user more easily, even with
symbolic representations.
18
Instruction in knowledge context
Traditional hypermedia based ITSs approach, in
general, has been to teach the know-why aspect of
knowledge with the help of explanations.
The links provide stimulus to the user to know
more about a particular topic.
System works more as a friendly librarian and
learning depends on the initiative of a student.
19
Theoretical framework best
suitable for facilitation of
cognitive skills?
Cognitive Apprentice
Framework
20
Cognitive apprenticeship framework



Modelling: Learners study the task pattern
of experts to develop own cognitive model
Coaching: Learners solve tasks by
consulting a tutorial component of the
environment
Fading: Tutorial activity is gradually
reduced in line with learners’ improving
performance
and
problem
solving
competence
21
Phases of Cognitive apprenticeship
1.
2.
3.
4.
World knowledge (initial requirement)
Observation of interactions among masters
and peers
Assisting in completion of tasks done by
master
Trying out on own by imitating
22
Phases of Cognitive apprenticeship
5.
6.
7.
Getting feedback from master
Getting advise for new things on the basis
of results of imitation, comparing given
solution with alternatives
Reflection by student,
master’s advice
23
resulting
from
Phases of Cognitive apprenticeship
8.
9.
Repetition of process from 2 to 7

Fading out guidance and feedback

Active participation, exploration and
innovation come in
Assessment of generalisation of the tasks
and concepts learnt during repetition
process
24
Example system

Cognitive apprenticeship based learning
environment (CABLE)
25
CABLE objectives
Environment should facilitate:



acquisition of basic domain knowledge;
application of the basic domain knowledge
in non-contextual and contextual scenarios
to get skills of the discipline; and
generalisation of the domain knowledge to
get competence of applying it in real world
situations.
26
CABLE architecture



Observation - for acquisition of concepts
Simple imitation - skills acquisition through
articulation of concepts
Advanced imitation - generalisation and
abstraction of already acquired concepts
and for acquisition of skills of applying
concepts in different contexts
27
CABLE architecture


Contextual observation - deeper learning
after imitation process results into the
identification of gaps in learner’s current
understanding of the domain knowledge
Interpretation of real life problems - for
acquiring competence in such narrative
problems as encountered in real life
situations
28
CABLE architecture


Mastery in skills - for repetitive training
Assessment - for measurement of overall
progress
29
CABLE
System generated
problems - random
selection of variables
Teacher generated
Teacher generated
Teacher generated rich
contextual problems for contextual problems narrative problems with model
strongly situated
for generalised
answers to simulate real life
learning & testing
learning & testing
conditions
Intelligent Tutoring Tools
Tools of the Trade
Assessment
Listen/ Observe Interactive Learning
Domain’s
Rehearsing/repairing
concepts and
misconceptions and
their purpose
missing concepts
Instruction as the
main source
Testing
Abstract
or
Single context
Learning by syntactic mapping of interface
objects is possible
Descriptive text,
illustrations and
solved examples
Use of
fine-grained
interfaces
Fine-grained
dynamic
feedback
30
Testing
Extending
Multiple contexts Greater complexity
and/or
Building skills in
Rich narrative
the use of tools
Ensures generalisation and far transfer of
knowledge
“Why ?” explanation
for the system
recommended solution
“What did I do ?”
diagnostic
feedback
Intelligent Tutoring Tools Structure
A network of inter-related variables where the
whole network remains constant.
Example, partial network of 7 out of a total of 14
variables in marginal costing.
31
Marginal costing relationships
R = VT + CT
R=Q*P
R
VT
VT = R - CT
VT = Q * VU
CT
CT = R - V T
CT = Q * C U
P=R/Q
P =VU + CU
P
Q
Q = VT / VU
Q = CT / CU
Q=R/P
C U = CT / Q
CU = P - V U
CU
VU
VU = VT / Q
VU = P - CU
32
Structure of an ITT
Knowledge Base
1. Variables
2. Relationships
3. Tolerances
Modes
- Student
- Lecturer
- Administrator
Inference Engine
Expert Model
1. Correct values
2. Derivation procedure
Random
Question
Generator
Tutoring
Module
Dynamic
Messaging
System
Feedback
(four levels)
File
Management
Marker
Lecturer’s model answer to
any lecturer generated
narrative questions
(Remote Expert Model)
(Local expert model)
Student Model
1. Student input
2. Value status (filled or blank)
3. Derivation procedure
4. Interface preferences
Input (student answer, position)
Context based
User Interface
link to textual
module
description
Add-ons
1. Calculator
2. Table Interface }Application
specific
3. Formula Interface
33
Tutoring Strategy of an ITT
 Introduction of complexity in phased
manner
 Corrective, elaborative and evaluative
aspects of student model are used for
tutoring.
 Learning process is broken down to very
small steps through suitable interfaces.
 ‘Road to London’ paradigm is adopted to
eliminate the need for diagnostic, predictive
and strategic aspects.
34
CABLE
Demo
Future work on mental
process modelling
35