Professional Documents
Culture Documents
.in
rs
de
ea
yr
.m
w
w
,w
ty
or
www.myreaders.info
ha
kr
ab
Expert Systems
Artificial Intelligence
Expert system, topics - Introduction, expert system components
and
human
interfaces,
expert
system
characteristics,
expert
base
rules,
Inference
engine
representing
semantic
:
and
network,
Forward
using
domain
frames;
chaining
data
knowledge,
Working
memory;
driven
approach,
system
shells
Shell
components
and
description;
fo
.in
rs
de
ea
w
.m
yr
Expert System
ab
or
ty
,w
Artificial Intelligence
ha
kr
Topics
2 hours)
Slides
03-16
1. Introduction
2. Knowledge Acquisition
3. Knowledge Base
26
5. Inference Engine
27-32
33-34
35
36-37
38
fo
.in
rs
de
ea
yr
ha
kr
ab
or
ty
,w
.m
Expert System
at
fo
.in
rs
de
ea
or
ty
,w
.m
yr
1. Introduction
Expert
systems
kr
ab
non-algorithmic
are
computer
expertise
for
applications
solving
certain
which
types
embody
of
some
problems.
For
ha
example, expert systems are used in diagnostic applications. They also play
chess,
real
make
time
financial
systems,
planning
decisions,
configure
underwrite
insurance
policies,
computers,
and
perform
monitor
many
User
Domain
Expert
User Interface
Expertise
Knowledge
Engineer
Encoded
Expertise
System
Engineer
Inference
Engine
Knowledge
Base
Working
Storage
The individual components and their roles are explained in next slides.
04
fo
.in
rs
de
ea
yr
or
ty
,w
.m
kr
ab
ha
Working storage :
solved;
The code at the core of the system which
Inference engine :
derives recommendations from the knowledge base and problemspecific data in working storage;
User interface :
The
fo
.in
rs
de
ea
yr
or
ty
,w
.m
Many
expert
kr
ab
system shells.
systems
are
built
with
products
called
expert
ha
builds
the
fo
.in
rs
de
ea
or
ty
,w
.m
yr
kr
ab
and generally
ha
to
expand
and
update
knowledge
base
on
continuing basis.
Make logical inferences based on knowledge stored
fo
.in
rs
de
ea
yr
.m
w
w
,w
ty
kr
ab
or
ha
expert
an electrical circuit.
Quality of advice offered by an expert system is dependent on
the amount of knowledge stored.
Capability to assign Confidence Values
fo
.in
rs
de
ea
yr
.m
w
w
,w
ty
Applications
Best suited for those dealing with expert heuristics for solving
ab
or
problems.
ha
kr
Not a suitable choice for those problems that can be solved using
fo
.in
rs
de
ea
ab
or
ty
,w
.m
yr
ha
kr
The ability of the system to reason with rules and data which are
not precisely known;
Data Driven Reasoning or Forward Chaining
An
inference
technique
which
uses
IF-THEN
rules
to
deduce
The way in which the problem specific data in the system is stored
and accessed;
User Interface
fo
.in
rs
de
ea
or
ty
,w
.m
yr
Goal-Driven Reasoning
Goal-driven reasoning, or backward chaining, is an efficient way to solve
kr
ab
problems. The algorithm proceeds from the desired goal, adding new
ha
assertions found.
Data
a=1
b=2
Rules
Conclusion
d=4
If A and C
Then
Rule 2:
If A and E
Then
Rule 3:
If B
Then
Rule 4:
If G
Then
Problem : prove
If A and B true
11
Then D is true
fo
.in
rs
de
ea
or
ty
,w
.m
yr
Uncertainty
Often the Knowledge is imperfect which causes uncertainty.
kr
ab
To work in the real world, Expert systems must be able to deal with
ha
uncertainty.
is known.
There are different ways in which these numbers can be defined, and
how they are combined during the inference process.
12
fo
.in
rs
de
ea
or
ty
,w
.m
yr
kr
ab
ha
solution and looks for rules which will move that state closer to a final
solution. The Algorithm proceeds from a given situation to a desired
goal, adding new assertions found.
Data
a=1
b=2
Rules
Conclusion
d=4
might
be
selected.
The
rule
breaks
the
sub-problems.
Example :
KB contains Rule set :
Rule 1:
If A and C
Then
Rule 2:
If A and E
Then
Rule 3:
If B
Then
Rule 4:
If G
Then
Problem : prove
If A and B true
13
Then D is true
problem
into
fo
.in
rs
de
ea
or
ty
,w
.m
yr
Data Representation
Expert system is built around a knowledge base module.
kr
ab
ha
to computer.
knows.
No single knowledge representation system is optimal for all applications.
The success of expert system depends on choosing knowledge encoding
scheme best for the kind of knowledge the system is based on.
The IF-THEN rules, Semantic networks, and Frames
commonly used representation schemes.
14
fo
.in
rs
de
ea
or
ty
,w
.m
yr
User Interface
The acceptability of an expert system depends largely on the quality of
ha
kr
ab
powerful tools for communicating with the user; they require graphics
support.
15
fo
.in
rs
de
ea
or
ty
,w
.m
yr
Explanations
An important features of expert systems is their ability to explain
ha
kr
ab
themselves.
Given
that
the
system
knows
which
rules
were
those
used
rules to
during
the
the user
fo
.in
rs
de
ea
or
ty
,w
.m
yr
2. Knowledge Acquisition
Knowledge acquisition includes the elicitation, collection, analysis, modeling
ha
kr
ab
fo
.in
rs
de
ea
or
ty
,w
.m
yr
kr
ab
ha
generation
techniques,
Limited-information
and
Matrix-based
techniques,
constrained-processing
Sorting
tasks,
techniques,
Diagram-based
Include
many
types
of
interviews
(unstructured,
semi-structured
use
of
techniques.
18
protocol-based
techniques
and
knowledge
modeling
fo
.in
rs
de
ea
yr
or
ty
,w
.m
Hierarchy-generation techniques
kr
ab
ha
and decision networks. The Ladders are of various forms like concept
ladder, attribute ladder, composition ladders.
Matrix-based techniques
fo
.in
rs
de
ea
yr
.m
w
w
,w
ty
Sorting techniques
Used for capturing the way people compare and order concepts;
it
ha
kr
ab
or
diagrams
important
in
capturing
and
process
maps.
These
are
particularly
why" of
fo
.in
rs
de
ea
or
ty
,w
.m
yr
is
built
around
kr
ab
ha
expert. This
information
may
be
in the form of
by the domain
problem-solving rules,
The first two methods were illustrated in the earlier lecture slides on
knowledge representation therefore just mentioned here.
representation is described more.
21
The frame
based
fo
.in
rs
de
ea
ab
or
ty
,w
.m
yr
action
or
Situation
conclusion
ha
kr
condition
Rules
"if-then"
a1 , a 2 , . . . . . , an
Then
b1 , b2 , . . . . . , bn
where
is an action
or a conclusion.
fo
.in
rs
de
ea
or
ty
,w
.m
yr
ha
kr
ab
the
objects
HAS
Wheels
HAS
Engine
HAS
Battery
Is-A
CAR
Is-A
Honda
Civic
Is-A
Nissan
Sentra
HAS
Power
Steering
23
the
fo
.in
rs
de
ea
or
ty
,w
.m
yr
3.3 Frames
In
this
technique,
knowledge
is
decomposed
into
highly
modular
kr
ab
ha
Knowledge
relationships
consist
of
between
concepts,
situations,
attributes
of
concepts,
attributes,
the
relationships
between
concepts,
and
the
fo
.in
rs
de
ea
yr
Example :
Two frames, their slots and the slots filled with data type are shown.
Frame
Car
Frame
Car
Inheritance Slot
Is-A
Inheritance Slot
Is-A
Value
Vehicle
Value
Car
Attribute Slot
Engine
Attribute Slot
Make
Value
Vehicle
Value
Honda
Value
Value
ha
kr
ab
or
ty
,w
.m
Value
25
Value
Attribute Slot
Cylinders
Attribute Slot
Year
Value
Value
1989
Value
Value
Value
Value
Attribute Slot
Doors
Attribute Slot
Value
Value
Value
Value
Value
Value
fo
.in
rs
de
ea
or
ty
,w
.m
yr
4. Working Memory
Working memory refers to task-specific data for a problem. The contents
kr
ab
ha
kept current.
Every problem in a domain has some unique data associated with it.
User Interface
Working Memory
(Task specific data)
Inference Engine
Knowledge Base
26
fo
.in
rs
de
ea
or
ty
,w
.m
yr
5. Inference Engine
The inference engine is
kr
ab
ha
Just a knowledge base alone is not of much use if there are no facilities
for
navigating
through
and
manipulating
the
knowledge
to
deduce
The Forward chaining, Backward chaining and Tree searches are some
of the techniques used for drawing inferences from the knowledge base.
These techniques were talked in the earlier lectures on Problem Solving : Search
and Control Strategies, and Knowledge Representation. However they are
relooked in the context of expert system.
27
fo
.in
rs
de
ea
or
ty
,w
.m
yr
is
techniques
for drawing
inferences
from
Rule
ha
kr
ab
Data
Rules
Conclusion
a=1
if a = 1 & b = 2
then c = 3,
b=2
if c = 3
then d = 4
d=4
Then
Rule 2: If A and E
Then
Rule 3: If B
Then
Rule 4: If G
Then
Problem : Prove
If A and B true
[Continued in next slide]
28
Then D is true
fo
.in
rs
de
ea
yr
.m
w
w
,w
ty
Solution :
ab
or
(i)
ha
kr
fires'' is found.
First iteration :
(ii)
(iii)
(iv)
Second iteration :
(v)
(vi)
29
fo
.in
rs
de
ea
or
ty
,w
.m
yr
ha
kr
ab
The algorithm proceeds from desired goal, adding new assertions found.
A backward-chaining, system looks for the action in the THEN clause of
the rules that matches the specified goal.
Goal Driven
Data
Rules
Conclusion
a=1
if a = 1 & b = 2
then c = 3,
b=2
if c = 3
then d = 4
d=4
Then
Rule 2: If A and E
Then
Rule 3: If B
Then
Rule 4: If G
Then
Problem : Prove
If A and B true
[Continued in next slide]
30
Then D is true
fo
.in
rs
de
ea
yr
.m
w
w
,w
ty
Solution :
ab
or
(i)
ha
kr
First iteration :
(ii)
Rule 4 fires :
new sub goal to prove G is true
go backward
(iii)
(iv)
Second iteration :
(v)
Rule 3 fires :
conclusion B is true (2nd input found)
both inputs A and B ascertained
Proved
31
fo
.in
rs
de
ea
or
ty
,w
.m
yr
ha
kr
ab
Many tree searching algorithms exists but two basic approaches are
Note : Here these two search are briefly mentioned since they were
described with examples in the previous lectures.
Depth-First Search
start
completely expanded.
Find the shortest path from initial assertion to a solution.
32
fo
.in
rs
de
ea
or
ty
,w
.m
yr
Expert
kr
ab
contains
ha
with
system
shell
is
software
development
method
for
building
applications
environment.
It
A shell is associated
by
configuring
and
knowledge acquisition,
the
the
knowledge Base,
the
reasoning,
user
Knowledge
Acquisition
Subsystem
Knowledge Base
Facts, Heuristics
Inference
Mechanism
Reasoning with
Uncertainty
Explanation
Subsystem
Knowledge
Engineer
User
Interface
U
s
e
r
fo
.in
rs
de
ea
yr
.m
w
w
,w
ty
or
ab
Knowledge Base
ha
kr
provides
one
or
more
knowledge
Expert
system
representation
tool
schemes
for
In PROLOG
the
Inference
mechanisms
for
manipulating the
symbolic
information
problem.
simple
modus
The
ponens
inference
backward
mechanism
chaining
of
can
range
IF-THEN
from
rules
to
Case-Based reasoning.
Knowledge Acquisition subsystem
knowledge,
needed
to
solve
problems
and
build
the
User Interface
fo
.in
rs
de
ea
or
ty
,w
.m
yr
7. Explanation
Most expert systems have explanation facilities that allow the user to ask
kr
ab
ha
The questions are answered by referring to the system goals, the rules
being
used,
empirical,
and
or
existing
"compiled"
problem
solving.
knowledge.
They
The
are
rules
codes
typically
of
an
reflect
expert's
User
No.
System
User
Yes.
System
User
Yes
System
User
Why ?
System
User
Note : The rule gives the correct advice for a flooded car, and knows the
questions to be ask to determine if the car is flooded, but it does not contain the
knowledge of what a flooded car is and why waiting will help.
Types of Explanation
35
Explanation of
how
Explanation of
why
Explanation of
why
fo
.in
rs
de
ea
or
ty
,w
.m
yr
kr
ab
ha
the maintenance of a space shuttle for its next flight. The main applications
are stated in next few slides.
36
fo
.in
rs
de
ea
.m
yr
,w
The
ty
financial
services
are
the
vigorous
user
of
expert
system
ab
or
ha
kr
in
determining
individuals.
whether
Insurance
to
companies
make
to
loans
assess
to
the
businesses
risk
and
presented
by
the customer and to determine a price for the insurance. ES are used in
typical applications in the financial markets / foreign exchange trading.
Knowledge Publishing
This is relatively new, but also potentially explosive area. Here the
primary function of the Expert system is to deliver knowledge that
is
relevant
to
the
user's
problem.
The
two
most
widely
known
and
37
fo
.in
rs
de
ea
ty
,w
.m
yr
9. References : Textbooks
1. "Artificial Intelligence", by Elaine Rich and Kevin Knight, (2006), McGraw Hill
kr
ab
or
ha
38
An exhaustive list is