Professional Documents
Culture Documents
09/18/15
Introduction
A hybrid intelligent system is one that combines
at least two intelligent technologies. For example,
combining a neural network with a fuzzy system
results in a hybrid neuro-fuzzy system.
The combination of probabilistic reasoning, fuzzy
logic, neural networks and evolutionary
computation forms the core of soft computing, an
emerging approach to building hybrid intelligent
systems capable of reasoning and learning in an
uncertain and imprecise environment.
09/18/15
FS
NN GA
Knowledge representation
Uncertainty
tolerance
Imprecision
tolerance
Adaptability
Learningability
Explanation
ability
Knowledge discovery and data mining
Maintainability
* The terms used for grading are:
- bad, - rather
bad, - rather good and- good
09/18/15
09/18/15
Rule Extraction
New
Data
Rule: IF - THE N
I nference E n gine
Explanation Facilities
User Interface
User
09/18/15
09/18/15
10
Approximate reasoning
In a rule-based expert system, the inference engine
compares the condition part of each rule with data
given in the database. When the IF part of the rule
matches the data in the database, the rule is
fired and
its THEN part is executed. The
precise matching is
required (inference engine
cannot cope with noisy or
incomplete data).
Neural expert systems use a trained neural network in
place of the knowledge base. The input data
does not
have to precisely match the data that
was used in
network training. This ability is
called approximate
reasoning.
09/18/15
11
Rule extraction
Neurons in the network are connected by links,
each of which has a numerical weight
attached to it.
The weights in a trained neural network determine
the strength or importance of the
associated neuron
inputs.
09/18/15
12
-0.8
Tail
0
Rule 1
Bird
1.0
-1.6 -0.7
+1
-0.2
Beak
+1
-1.1
2.2
-1.0
Feathers
+1
2.8
-0.1
Rule 2
-2.9
1
Engine
1.0
0.0
-1.6
-1.1 1.9
Plane
Rule 3
Glider
1.0
-1.3
09/18/15
13
YRule 1 YBird 1
09/18/15
14
YRule 2 YPlane 1
YRule 3 YGlider 1
09/18/15
15
16
i 1
j 1
xi wi w j
09/18/15
17
Example:
Enter initial value for the input Feathers:
+1
KNOWN = 12.8 = 2.8
UNKNOWN = 0.8 + 0.2 +
2.2 + 1.1 = 4.3 KNOWN UNKNOWN
Enter initial value for the input Beak:
+1
KNOWN = 12.8 + 12.2 = 5.0
UNKNOWN =
0.8 + 0.2 + 1.1 = 2.1
CONCLUDE: Bird is TRUE
UNKNOWN
09/18/15
KNOWN
18
Rule 5:
IF a5 THEN b3 (0.6)
Rule 2:
IF a1 AND a4 THEN b1 (0.2)
Rule 6:
IF b1 AND b3 THEN c1 (0.7)
Rule 3:
IF a2 AND a5 THEN b2 (-0.1 )
Rule 7:
IF b2 THEN c1 (0.1)
Rule 4:
IF a3 AND a4 THEN b3 (0.9)
Rule 8:
IF b2 AND b3 THEN c2 (0.9)
Input
Layer
a1
Conjunction
Layer
1.0
R1
1.0
a2
1.0
R2
Disjunction
Layer
Conjunction
Layer
0.8
0.2
b1
1.0
R6
1.0
a3
a4
1.0
1.0
1.0
R3
Disjunction
Layer
-0.1
R4
0.9
R5
0.6
b2
b3
1.0
1.0
1.0
1.0
R7
0.7
0.1
0.9
c1
c2
R8
1.0
a5
09/18/15
1.0
19
Neuro-fuzzy systems
Fuzzy logic and neural networks are natural
complementary tools in building intelligent
systems. While neural networks
are low-level
computational
structures that perform well when
dealing with raw data, fuzzy logic deals with
reasoning on a higher level, using
linguistic
information acquired
from domain experts.
However, fuzzy systems lack the ability
to learn
and cannot adjust
themselves to a new
environment. On the other hand,
09/18/15
20
09/18/15
21
22
09/18/15
23
Neuro-fuzzy system
L ayer 1
L ayer 2
x1
x1
x1
x1
A1 A1
R1
A2
A2
R2
A3 A3
x2
x2
x2
x2
B1 B1
B2
B3
09/18/15
L ayer 3
B2
B3
L ayer 4
L ayer 5
R1
R2
R3 R3
R4 R4
R5
R5
wR3
C1
wR
C1
wR1
wR2
wR4
wR5
C2
C2
R6
R6
Computer Intelligence and Soft Computing
24
25
( 2)
0
,
if
x
parameters { a, b} as follows:
i a
2
yi( 2 ) 1
0,
09/18/15
2 xi( 2 ) a
b
b
b
xi( 2) a
2
2
b
( 2)
if xi a
2
, if a
26
a = 4, b = 6
a = 4.5, b = 6
a = 4, b = 6
0.8
0.8
0.6
0.6
0.4
0.4
0.2
0.2
09/18/15
a = 4, b = 4
27
28
29
30
09/18/15
31
09/18/15
32
33
Training patterns
0
1
1
09/18/15
34
The data set is used for training the five-rule neurofuzzy system shown below.
x1
x2
1
0.9 9
x2
0.72
0.61
0.6
wR3
wR4
0.4
wR2
0.2
0.79
0
09/18/15
w R5
0.8
wR1
10
20
Epoch
30
40
50
35
36
Given input and output linguistic values, a neurofuzzy system can automatically generate a
complete
set of fuzzy IF-THEN rules.
Let us create the system for the XOR example.
This system consists of 22 2 = 8
rules. Because
expert knowledge is not embodied
in the system
this time, we set all initial
weights between Layer 3
and Layer
4 to 0.5.
After training we can eliminate all rules whose
certainty factors are less than some
sufficiently
small number, say
09/18/15
37
x1
1
2
0.78
0.69
4
5
S
x2
6
7
0.8
wR2 wR8
0.7
0
0.62
0
0
wR5
0.5
0.4
0.3
0.2
0.1
0.80
wR3
0.6
wR4
0
0
10
wR1
20
30
40
50
Epoch
09/18/15
38
39