Professional Documents
Culture Documents
Ann FL
Ann FL
NETWORKS
AND FUZZY
LOGIC
GEETHANJALI COLLEGE OF ENGINEERING AND TECHNOLOGY
(Name of the Subject / Lab Course) : NEURAL NETWORKS AND FUZZY LOGIC
Distribution List :
2) Sign : 2) Sign :
4) Date : 4) Date :
2) Sign : 1) Name :
3) Design : 2) Sign :
4) Date : 3) Design :
4) Date :
Approved by : (HOD ) 1) Name :Dr.S.Radhika
2) Sign :
3) Date :
2.SYLLABUS
JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY
HYDERABAD
4+1* 0 4
Introduction, Humans and Computers, Organization of the Brain, Biological Neuron, Biological and
Artificial Neuron Models, Hodgkin-Huxley Neuron Model, Integrate-and-Fire Neuron Model, Spiking
Neuron Model, Characteristics of ANN, McCulloch-Pitts Model, Historical Developments, Potential
Applications of ANN.
Introduction to classical sets - properties, Operations and relations; Fuzzy sets, Membership,
Uncertainty, Operations, properties, fuzzy relations, cardinalities, membership functions.
Neural network applications: Process identification, control, fault diagnosis and load forecasting.
2. Introduction to Neural Networks using MATLAB 6.0 - S.N.Sivanandam, S.Sumathi, S.N.Deepa, TMH,
2006
ADDITIONAL TOPICS
1. A HIGH PERFORMANCE INDUCTlON MOTOR DRIVE SYSTEM USING FUZZY LOGIC CONTROLLER
4. Neural Networks and Fuzzy Logic System by Bart Kosko, PHI Publications.
Websites
1. ieeexplore.ieee.org
2. www.sciencedirect.com/
3. www.academia.edu
1. To offer high quality graduate program in Electrical and Electronics education and to
prepare students for professional career or higher studies.
2. The department promotes excellence in teaching, research, collaborative activities
and positive contributions to society
4.Programme Educational Objectives(EEE)
PEO 2. Graduates will analyze real life problems, design Electrical systems
appropriate to the requirement that are technically sound, economically feasible
and socially acceptable.
Course objectives:
1. This course introduces the basics of Neural Networks and essentials of Artificial Neural Networks
with Single Layer and Multilayer Feed Forward Networks.
2. It deals with Associate Memories and introduces Fuzzy sets and Fuzzy Logic system components.
3. The Neural Network and Fuzzy Network system application to Electrical Engineering is also presented.
This subject is very important and useful for doing Project Work.
4. The main objective of this course is to provide the student with the basic understanding of
Logic fundamentals.
3. After going through this course student will get thorough knowledge in biological neuron and
artificial neurons.
4. Students will be able to compare analysis between human and computer, Artificial Neural
Networks models, characteristics of ANNs learning strategies, learning rules and basics of fuzzy
logic.
5. Students will be able to understand concept of classical and fuzzy sets, fuzzification and
defuzzification, with which they can be able to apply the conceptual things to the real world
electrical and electronics problems and applications.
7. Importance of the course
The world we live relies more on electronic gadgets and computers to control the behaviour of
real world resources .Example...Commerce is performed without using a single bank note
exchanged.Aeroplanes land and take off without even looking out of a window.Coordination
process can be automated using computers ,this is where Neural networks come in. Neural
networks are important for their ability to adapt.They have a unique way of storing and retreiving
information,wherein the information is distributed.The nets are capable of making memory
associations with the help of which large amount of data can be handled efficiently and
fastly.They are also fault tolarent i..e, even if a few neurons fail it will not disable the entire
system.The paradigm of neural networks, developed to emulate some of the capabilities of the
human brain as demonstrated great potential for salient features such as learning ,fault
tolerance and generalisation . This subject is very important and useful for doing Project Work
This course introduces the basics of Neural Networks and essentials of Artificial
Neural Networks with Single Layer and Multilayer Feed Forward Networks. Also deals
with Associate Memories and introduces Fuzzy sets and Fuzzy Logic system
components. The Neural Network and Fuzzy Network system application to Electrical
Engineering is also presented. This subject is very important and useful for doing Project
Work.
8. Prerequisites
Linear algebra, advanced calculus, discrete mathematics, Boolean algebra or equivalent.
Students will be able to understand properties, Operations and relations; Fuzzy sets
Students will be able to understand Operations, properties, fuzzy relations.
Professional
1 NNFL II
Core
*When the course outcome weightage is < 40%, it will be given as moderately correlated (1)
*When the course outcome weightage is >40%, it will be given as strongly correlated (2)
EHV AC
Logic fundamentals.
thorough knowledge in
biological neuron and
artificial neurons.
CO:5 Students 1 1 2 2 2 2 1 2 2 1 2 2 1 2
understand concept of
classical and fuzzy sets,
fuzzification and
defuzzification, with
which they can be able to
apply the conceptual
things to the real world
electrical and electronics
problems and
applications.
11.Individual Time Table
LUNCH
Wednesda EM- EM-II
EM-I
y III LAB-EEE-III B1
EM-II
Thursday EM-I
LAB-EEE-III B2
EM- EE LAB-
Friday EM-I
III MECH-IIB2
EM-
Saturday EM-I
III
No Subject(T/P) Periods Per Week
1 EM-III 5
2 EM-I 5
3 EM-II LAB 6
EE LAB 6
CLASS TIME TABLE
Year/Sem/Sec: IV-B.Tech-II Semester(Version-1) Room No: LH-14 Acad Year: 2014-15, WEF: 29-12-2014
12.50-
Time 09.30-10.20 10.20-11.10 11.10-12.00 12.00-12.50 13.30-14.20 14.20-15.10 15.10-16.00
13.30
Period 1 2 3 4 5 6 7
Tuesday
TECH SEMINAR TECH SEMINAR TECH SEMINAR TECH SEMINAR PROJECT REVIEW PROJECT REVIEW PROJECT REVIEW
Wednesday PROJECT
PROJECT REVIEW PROJECT REVIEW PROJECT REVIEW PROJECT REVIEW PROJECT REVIEW PROJECT REVIEW
REVIEW
LUNCH
Thursday PROJECT
PROJECT REVIEW PROJECT REVIEW PROJECT REVIEW TECH SEMINAR TECH SEMINAR LIB/SPORTS
REVIEW
1 HV DC N. SHANTHINATH 4+1*-Periods
Applications. LCD/OH
P/BB
4 Applications LCD/OH
8 8
P/BB
30 6/3/15 Applications.
41 28/3/15 Tutorials(Unit I)
53 18/4/15 Assignment - 1
54 18/4/15 Assignment 2
55 Assignment 3
56 Assignment - 4
UNIT I
ARCHITECTURES
PART A 2MARKS
PART B 16 MARKS
1. Explain briefly the operation of biological neural network with a simple sketch.
2. Discuss supervised learning and unsupervised learning.
3. Describe preceptron learning rule and delta learning rule.
4. Write about Hebbian learning and Widrow-Hoft learning rule.
5. Describe winner-take-all learning rule and outstar learning rule.
6. Describe back propagation and features of back propagation.
7. Describe McCulloch-Pitts neuron model in detail.
8. Write about performance of back propagation learning.
9. What are the limitations of back propagation learning? Explain in detail.
10. Discuss a few tasks that can be performed by a back propagation network.
UNIT II
NEURAL NETWORKS FOR CONTROL
PART A ( 2 MARKS )
1. What do you mean by networks?
2. Draw the diagram for boltzman machine.
3. Draw the diagram for hop field networks.
4. What is meant by feedback networks?
5. What do you by transient response?
6. List out any two application of neural networks used for controlling.
7. Explain boltzman machine.
8. List out the uses of hop field networks.
9. Give any two application of boltzman machine.
PART B ( 16 MARKS )
UNIT III
FUZZY SYSTEMS
PART A ( 2 MARKS )
1. Define probability.
2. Name the three types of ambiguities.
3. Define classical set.
4. What is meant by universe of discourse?
5. With a neat sketch write about non non-conventional fuzzy set.
6. Name the different fuzzy set operations.
7. Define fuzziness.
8. Write De Morgans law.
9. Define power set.
10. Define fuzzification.
PART B ( 16 MARKS )
1. Differentiate fuzzy set from classical set and name the properties of classical (crisp) sets.
2. A = {(1/2) + (0.5/3) + (0.3/4) + (0.2/5)}, (8)
3. B = {(0.5/2) + (0.7/3) + (0.2/4) + (0.4/5)} Calculate the several operation of the fuzzy set. (8)
4. Discuss varies properties and operations on crisp relation. (16)
5. Describe fuzzy relation. (16)
6. Explain the operation of fuzzy sets with a suitable example. (16)
7. Write about conditional fuzzy proposition and unconditional fuzzy proposition. Explain fuzzy
8. associate memory (FAM) with a suitable example. (16)
9. Define defuzzification and explain the different defuzzification methods. (16)
10. Explain fuzzy Cartesian and composition with a suitable example. (16)
11. Explain the concept of fuzzy set with suitable examples. (16)
12. Explain the terms (16)
a. Fuzziness
b. Power set.
c. Union of two sets.
d. Complement of two sets.
e. Difference of two sets.
UNIT IV
PART A ( 2 MARKS )
PART B ( 16 MARKS )
1. Write the components of a fuzzy logic system and explain them. (16)
2. Explain min-max method of implication with a suitable example. (16)
3. Explain monotonic (proportional) reasoning. (16)
4. Who is a knowledge engineer? Write about extracting information from knowledge
engineer.(16)
5. Explain the various ways by which membership values can be assigned to fuzzy variables. (16)
6. Discuss the various special features of the membership function. (16)
7. With a neat sketch discuss the major components of fuzzy controller. (16)
8. Write about genetic algorithm and its application. (16)
9. Write the different deterministic form of classical decision-making theories and explain any
10. two. (16)
11. 10)Write short notes on (16)
a. Lambda-cut.
b. Knowledge base.
c. Adopticee fuzzy system.
UNIT V
APPLICATION OF FLC
PART A ( 2 MARKS )
1. What are the rules based format used to represent the fuzzy information?
2. What is image processing?
3. Define image and pixel.
4. State two assumptions in fuzzy control system design.
5. Name the principal design elements in a general fuzzy logic control system.
6. Draw a schematic diagram of a typical closed-loop fuzzy control situation.
7. Define sensor connected with fuzzy control system.
8. Name the two control system.
9. A simple fuzzy logic control system has some features: Name any two.
10. Write two sentences about neuro fuzzy controller.
PART B ( 16 MARKS )
ASSIGNMENT-1
4.Compare & Contrast the difference between biological neuron & artificial
neural network?
ASSIGNMENT-2
1.Define an activation function? What are the various types of neuron activation
function?
learning strategies?
4.Describe delta learning rule in detail with an example?
ASSIGNMENT-3
3.What is XOR problem? Draw & explain the architectural graph of network for
ASSIGNMENT-4
1.What is back propagation? Derive its learning algorithm with a schematic two
ASSIGNMENT-5
architecture?
network?
memory?
4.Let A & B be two relation matrices defined on the sets {1,3,5} {1,3,5}
(i) A={(3,10) (4,0.2) (5,0.3) (6,0.4) (7,0.6) (8,0.8) (10,1) (12,0.8) (14,0.6)}
(ii) B={(2,0.4) (4,0.8) (5,1.0) (7,0.6)}
(iii) C={(2,0.4) (4,1.0) (5,2.0) (7,0.8)}
ASSIGNMENT-7
0 0.8 1 0.6
Find the -cut relations for the values of =0+ , 0.1 & 0.7?
ASSIGNMENT-8
1.What is fuzzy logic controller? Explain the different types of fuzzy logic
controllers?
(i) Clustering,
c. Wij= xi f. (y-in j)
d. Wij=(tj-yj)xi
2. The squared error for particular training pattern if extended delta rule is
a. = m j=1 (tj-yj)2
b. = m j=1 (tj+yj)2
c. = mj=1 (tj)2 d.
= m j=1 (yj)2
a. k=1..a Ak Bk
Tb
. k=1..a Ak
c. k=1..a Bk T
d. k=1..aAkBk
a. i ai=0
b. i bi=0
c. i ai bi=0
d. i ai bi =1
6. The following rule allows for anarbitrary differentiable activation function to beapplied to the
output units
a. Delta
b. Extended Delta
c. Hebb
d. Hopfield
7. The updation ofthe following is done to reduce the difference between the computed output and
the target
a. Input
b. Output
c. Target
d. Weight
a. Bipolar
b. Binary
c. Real valued d.
Bilinear
9. The performance of the auto associative memory net is among the following for bipolar vectors
than the binary
vectors
a. W orst b.
Better c.
Equal
d. No way related
10. Important criterion for anassociative network is among the following it can store
a. Time to train
b. Number of patterns
c. Iterations
d. Zero elements
11. The following rule can beused for both binary as well as bipolar vectors a. Hebb
rule
b. LVQ
c. LMS
d. Winner Rule
c. W=p=1..p ST (p)
d. W =p=1..p t(p)
13. The following rule changes the weight ofthe connection to minimize the difference between the
net
a. Delta Rule
b. Hebb Rule
c. LMS Rule
d. Adaline
14. The following energy points ofthe Lyapunov surface have to be mapped to desired memory states
a. Maximu
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
b. Minimum
c. Zero
d. Only one
a. k=1..a Ak Bk T
b. k=1..a Ak
c. k=1..a Bk
Td
. k=1..a Ak Bk
16. The following matrix provides a way to encode associations as memories into a neural network
a. Hebb matrix
b. Covariance matrix
c. Bilinear matrix
d. Inverse matrix
17. The following results if the input vector pair is same as the output vector pair
a. Auto associative
b. Hetero associative
c. Bidirectional Memories
18. The following results if the input vector pair is different as the output vector pair
a. Auto associative
b. Hetero associative
c. Bidirectional Memories
19. The following rule for pattern association is aniterative learning rule a. Delta
Rule
b. Hebb Rule
c. LMS Rule
d. Adaline
a. Wj=(t-yin)xi
b. Wj=(t-yin)
c. Wj= (t-yin)xi
d. Wj=(yin)xi
21. When anaxon ofcells excite(s) cell B and repeatedly or persistently takes part in firing it, some
growth process ormetabolic change takes place in one or both cells so that A s efficacy as one ofthe
cells firing B is
a. Increased
b. Decreased
c. Equal
d. No way related
22. The following is process offorming association between related patterns a. Pattern
Association
b. Pattern Classification
c. Pattern Recognition
d. Pattern Clustering
23. The following nets are single layer nets in which the weights are determined tostore an asset of
pattern association
a. Hopfield
b. Associative Memory
c. Boltzmann's Machine
d. Perceptron
24. The simple and frequently used method for determining the weights for anassociative memory
neural net is
a. Hebb rule
b. LVQ
c. LMS
d. Winner Rule
25. The following rule assumes that the error signal is directly measurable a. Delta
Rule
b. Hebb Rule
c. LMS Rule
d. Adaline
26. The Delta Rule for single output unit is given bya.
Wj=(t-yin)xi
b. Wj=(t-yin)
c. Wj= (t-yin)xi
d. Wj=(yin)xi
a. Wij=(tj-yinj)xi
b. W ij=(tjxi
c. W ij= (tj-yinj)xi
d. W ij=xi
28. Whether the system is auto associative orhetero associative, the following that are to
beassociated
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
a. Input
b. Memory
c. Output
d. Control
a. OLAM
b. BAM
c. CAM
d. ART
30. The following has the restrictions on the maximum number of associations it can accurately recall
a. ART1
b. BAM
c. ART2
d. Hopfield network
31. The following BAM is implemented byinterconnecting neurons within each layer bymeans
ofadditional
weights
a. Continuous
b. Discrete
c. Adaptive
d. Competitive
d. Hopfield network
33. The following is a system that provides a mapping from a domain ofinputs to a range outputs a.
Fundamental memory
b. Main memory
c. Additional memory
d. Associative memory
34. In associative memory if xk is the input and ykis the output, and when xk ykthe process is known
as
a. Auto associative
b. No associative
c. Heteroassociative
d. Biassociative
Continuous
b. Discrete
c. Adaptive
d. Competitive
36. The following network accepts aninput vector on one set of neurons and produces a related but
different
output vector on another set
a. Hopfield
b. BAM
c. Boltzmann's machine
d. ART1
37. All BAM's are unconditionally stable for any weight network was proposed bya. Kosko
b. Rumelhart
c. McCulloh Pitts
d. Kohonen
38. In the following system, any neuron is free to change state at any time a.
synchronous
b. asynchronous
c. linear
d. nonlinear
39. The Bidirectional Associative Memory (BAM) has a neural network oftwo layers connected with
the
following system
a. Unidirectional
b. Parallel
c. Feedback
d. Feed forward
a. auto associative
b. Non-associative
c. Heteroassociative
d. ART
41. When E/t 0 the following is obtained
a. Minima
b. Maxima
c. Focus point
d. Trajectory
42. Energy function ofcontinuous Hopfield net when is a time constant is given as a. E =-0.5
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
44. When the activity ofeach neuron is formed to change with time, the net is found to converge
according
45. The following matrix has the property Wij= Wji for i j and Wij=0 for all i
a. Unit matrix
b. Symmetric matrix
c. Sparse matrix
d. Inverse matrix
a. Discrete Hopfield
b. Continuous Hopfield
c. McCulloh Pitts
d. ART-1
a. BAM
b. Discrete Hopfield
c. McCulloh Pitts
d. ART-2
c. Boltzmann's machine
a. 1
b. 0
c. Non-zero
50. Lack ofthe following connections ensure that the networks are conditionally stable
a. Input
b. Feed forward
c. Feed backward
d. Feed follow
a. Hopfield
b. BAM
c. Boltzmann's matrix
d. ART1
52.
a.
b.
c.
d.
a. R
b. Doesn't belongs to R
c. 1
d. Equal
a.
b.
c.
d.
a. R
b. Doesn't belongs to R
c. 1
d. Equal
a. Binary
c. Finite
d. Quinary
58. If the universe ofdiscourse orsets are finite, the n-ary relation can beexpressed as an
a. Resource Matrix
b. Relation Matrix c.
Region Matrix
d. Sparse Matrix
a. {(1,3),(2,3),(3,5)}
b. {(1,2),(2,3),(3,4)} c.
{(1,1),(1,3),(0,4)}
d. {(1,0),(2,0),(3,1)}
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
60. {(a,b)/a A b B is
a. Ax B
b. A B
c. A B
d. A Bc
a. A x B = B x A
b. A x B B x A c.
AxB=
d. Ax B = X
a. R o S
b. S + R
c. R S
d. R - S
b. A is subset of B
c. A is leader of B
d. A is complement of B
64. The following set ofset A is the set ofall possible subsets that are derivable from A including Null
set a. Power set
b. Subset
c. Superset
d. Null set
Null set
c. Complement set
d. Ideal set
a. Hamilton
b. Planar
c. Euler
d. Singleton
a. A is superset of B
b. A is subset of B c.
A is leader of B
d. A is complement of B
68. The following set is the which, with reference to a particular context contains all possible elements
having the
a. Universe of discourse
b. Complement
c. Singleton set
d. Null set
a. UML diagrams
b. Sets
c. Venn diagram
d. Figure
a. Gannt chart
b. DAG
c. Venn diagram
d. RAG
a. Cardinal
b. Member
c. Sibling
d. Child
a. Chromatic number
b. Cardinality
c. In degree
d. Out degree
a. x =( xi M xi)/
b. x = ( xi M-3 xi)/
c. x = ( xi M+1 xi)/
d. x = ( xi M xi )
76. In case with more than one element having maximum value firing defuzzification, the following
should betaken
c. Centroid
d. Mode value
77. The following is the largest membership grade obtained byany element in that set
a. Index
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
c. Degree
d. Member
78. In MOM defuzzification method in continuous case M could bedefined as the following where
|(x)
a. M ={ x [-C,C]
b. M = { x&isin [0,1]
c. M = { x&isin [0,0]
d. M = { x&isin [1,1]
a. Fuzzy database
Fuzzy set
d. Fuzzy relation
a. Fuzzification
b. Defuzzification
c. Crispification
d. Decryptography
b. Defuzzification
c. Crispification
d. Decryptography
a. Centre of area
b. Centre ofsums
c. Centre of gravity
d. Mean of maxima
84. Number oftimes overlapping area is counted in centroid method isa. Only
one
b. Twice
c. Thrice
a. Only one
b. Twice
c. Thrice
b. E= ij j yiyj wij xi yi + Oi yj
c. E= -0.25 ij j yiyjwij xi yi + Oi yj
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
87. E=
88. The essence ofa CAM is to map the following onto a fixed (stable) point
a. Output
b. Fundamental memory
c. Main memory
d. Additional memory
89. The energy cannot increase for both positive and negative change in yi, the value ofE isa. less
than
zero
c. Equal to zero
d. Infinity
90. In the following mode oftraining, all neurons in Hopfield networks fire at random.
a. Stable state
b. Output
c. Synchronous
d. Asynchronous
91. The change in energy is due to a change in the
a. Time of training
b. State of neuron
d. Weight
92. If the energy doesn t change with further iteraWon then the net reaches
a. State equilibrium
b. State inequilibrium
c. State annealing
d. State instability
93. The formulation ofthe following nets shows the usefulness ofnet as a content addressable
memory a. Discrete
Hop
b. Continuous Hop
c. Discrete BAM
d. Continuous BAM
a. Time
b. Energy
c. Sigmoid
d. Pressure
a. 8
b. 16
c. 32
d. 64
96. The fuzziness ofthe data can bedecreased by
a. k-means algorithm
b. DB-scan algorithm
c. Fuzzy-c-means algorithm
d. Gaussian algorithm
a. 0
b. -1
c. 1
d. Variable
Overlapping clustering
b. Exclusive clustering
c. Hierarchical clustering
d. Probabilistic clustering
101. Fuzzy Classification can beapplied
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
Fuzziness ofdata
b. Exactness of data
c. Probability of data
mining
b. Image Processing
d. Medical analysis
c. Trained data
d. Uncertain data
a. Sweetness is 0.5
a. Exact
b. Distinct
d. Only overlapping
c. Branching application
a. Only distinct
b. Only continuous
c. Only graphical
111. The output ofthe fuzzy classifier is determined bythe rule which has
c. 0 degree membership
Clustering
b. Probability
c. Statistical analysis
d. Regression
c. Exact values
d. Optimal values
115. Biggest application offuzzy classification isa. Data
mining
b. Image Processing
d. Medical analysis
a. (x)
b. P
c. 0
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
d. 1
117. B'=
a. ' O X(x,y)
b. ' U X(x,y)
c. ' || X (x,y)
d. '
118. B c (y)=
a.
b.
c.
d.
119. Absolute fuzzy quantifiers are defined over
a. R
b. 0
c. 1
d.
Approximate reasoning
b. Abductive reasoning
c. Inductive reasoning
d. Default logic
a. Fuzzy preposition
b. Fuzzy predicate
c. Binary value
d. Real value
a. x (x,y)
b. x (x)
c. x (y)
d. (x,y)
125. * (x,y)=
126. (x,y) =
c. 1- (x,y)
d. 1- (x,y)
127. (x,y) =
1- (x,y)
d. 1- (x,y)
128. c (x,y)=
c. 1- (x,y)
d. 1- (x,y)
129. The following is fuzzy set defined on Cartesian product ofcrisps set X1, X2,Xn where the ntuple
a. Fuzzy Relation
b. Crisp Relation
c. Cartesian
d. Function
130. o (x,z) =
a. a+ (x)
b. a* (x)
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
c. (x)
d. (x)-a
132. A(x) =
a. ( (x))
b. (x)
c.
d. * (x)
133. c =
a. X
b. = X
c. {}
d. Ac
134. If A={(x1,0.5), (x2, 0.7), (x3, 0)} and {(x1,0.8), (x2, 0.2), (x3, 1)} then is
135. If A={(x1,0.5), (x2, 0.7), (x3, 0)} and {(x1,0.8), (x2, 0.2), (x3, 1)} then is
136. If A={(x1,0.5), (x2, 0.7), (x3, 0)} and {(x1,0.8), (x2, 0.2), (x3, 1)} then (x2)=
a. 0.1
b. 0.5
c. 0.2
d. 0
137. The product oftwo fuzzy set and whose membership function defined as . (x)
a. (x) . (x)
b. (x) + (x)
c. (x) - (x)
d. (x) / (x)
138. If ={(x1,0.2), (x2, 0.8), (x3, 0.4)} = {(x1,0.4), (x2, 0), (x3, 0.1)} then .
139. If A={(x1,0.5), (x2, 0.7), (x3, 0)} and {(x1,0.8), (x2, 0.2), (x3, 1)} then (x1)=
a. 0.8
b. 0.5
c. 1.3
d. 1
140. If A={(x1,0.5), (x2, 0.7), (x3, 0)} and {(x1,0.8), (x2, 0.2), (x3, 1)} then (x2)=
a. 0.2
b. 0.7
c. 0.1
d. 1
141. If A={(x1,0.5), (x2, 0.7), (x3, 0)} and {(x1,0.8), (x2, 0.2), (x3, 1)} then (x1)=
a. 0.1
b. 0.5
c. 0.2
d. 0
142. The union oftwo fuzzy sets and is U is defined with membership function A U N
(x) as
a. min ( A(x),N(x))
b. max (A(x),N(x)) c.
abs ( A(x),N(x))
d. log ( A(x),N(x))
143. If A={(x1,0.5), (x2, 0.7), (x3, 0)} and {(x1,0.8), (x2, 0.2), (x3, 1)} then U (x3)=
a. 0
b. 0.1
c. 1
d. 3
144. The intersection oftwo fuzzy sets and is is defined with membership function
A N (x) as
145. If A={(x1,0.5), (x2, 0.7), (x3, 0)} and {(x1,0.8), (x2, 0.2), (x3, 1)} then U (x3)=
a. 0.1
b. 0.5
c. 0.2
d. 0
146. The complement offuzzy set is a new fuzzy set with the following membership function
148. c(x1)=
a. 0.5
b. 0.3
c. 1
d. 1.8
149. c (x2)=
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
a. 0.5
b. 0.3
c. 1
d. 1.8
150. c (x3) =
a. 0.5
b. 0.3
c. 1
d. 1.8
151. If (x) =(x) then the two fuzzy sets and are said to be a.
Equal
b. Product
c. Union
d. Intersection
152. ( )c =
a.
b. c c
c. c
d. c
153. ( )c =
a.
b. c c
c. c
d. c
154. c =
a. X
b. = X
c. {}
d. Ac
a. 0.16
b. 0.04
c. 0.49
d. 0.01
b. (c c) ( c)
c. (c ) (c c)
d. (c ) ( c)
158. a.(x) =
a. a+ (x)
b. a* (x) c.
(x)
d. (x)-a
159. A(x) =
a. ((x))
b. (x)
c.
d. * (x)
Concentration
b. Dilution
c. Dilation
d. Convolution
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
b. Dilution
c. Dilation
d. Convolution
a. b.
( c) c.
( c)
d. c c
163. If = {(x1,0.2), (x2, 0.5), (x3, 0.6)} = {(x1,0.1), (x2, 0.04), (x3, 0.5)} then =
164.c=
a. X
b. = X
c. {}
d. Ac
c. A= xiX /xi
d. A= xiX (xi ) * xi
b. A= x (x)/x
c. A= x (x)+x
d. A= x (x)*x
167. The following is associated with fuzzy set A such that the function maps every elements ofthe
universe of
a. Threshold function
b. Membership function
c. Sigmoid function
d. Hyperbolic
=1/(1+x)2
b. =(1+x)2
c. = x2
d. =1+x
169. If ={(x1,0.2), (x2 0.8)} = {(x1,0.6), (x2, 0.8)}, = {(x1,0.2), (x2, 0.8)} then
a. =
b. `
c. =
d. = 3
170. If ={(x1,0.2), (x2 0.8)} = {(x1,0.6), (x2, 0.8)}, = {(x1,0.2), (x2, 0.8)} then
a. =
b.
c. =
d. = 3
171. The following sets support a flexible sends of membership ofelements to a set a. Fuzzy set
b. Logic set
c. Certain set
d. Crisp set
172. In the following set theory anelement either belong to ordoesn t belong to a set
a. Fuzzy set
b. Logic set
c. Certain set
d. Crisp set
173. In the following set theory many degrees of membership are allowed
a. Fuzzy set
b. Logic set
c. Certain set
d. Crisp set
174. The following function values need not always be described bydiscrete values
a. Membership
b. Index
c. Position
d. Class
175. If ={(x1,0.2), (x2, 0.8)} ={(x1,0.6), (x2, 0.8)}, = {(x1,0.2), (x2, 0.8)} then
a. =
b.
c. =
d. = 3
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
176. The following logic had its roots in the theory ofcrisp sets
a. Fuzzy logic
b. Boolean logic
c. Prolog
d. ELIZA
a. Complete information
b. Partial information
c. Clear information
d. Coherent information
178. The statements of(0 /1)type ofhandling is termed as the following the domain offuzzy set theory
a. Crisp
b. Lisp
c. Prolog
d. ELIZA
a. Single valued
b. Multivalued
c. Ambiguious valued
b. Multivalued
c. Ambiguious valued
a. Crisp logic
b. Fuzzy logic
c. Bayes logic
d. Probability theory
a. Crisp logic
b. Fuzzy logic
c. Predicate logic
d. Prepositional logic
183. The following theory is anexcellent mathematical tool to handle the uncertainty arising due
to vagueness
b. Crisp logic
d. Prepositional logic
184. The following may arise due to partial information about the problem
a. Clarity
b. Uncertainty
c. Perfection
d. Unambiguity
185. Classical set theory also termed as a.
Crisp
b. Lisp
c. Prolog
d. ELIZA
Only one
b. Two
d. It depends on training
a. P=n/(log2n)
b. P=n/(log2n)
c. P=2n/(2log2n)
d. P=3n/(2log2n)
188. The Hopfield network consists ofa set ofneurons forming a multiple loop of following system.
a. Unidirectional
b. Parallel
c. Feedback
d. Feed forward
189. The magnetic mutual exchange between the alones led to the development of
a. Simulated annealing
b. McCulloh piths
c. Hopfield
d. Boltzmann's Machine
190. The following network is able to recognize unclear pictures correctly
a. Simulated annealing
b. McCulloh Pitts
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
c. Hopfield
d. Boltzmann's Machine
b. Many units
192. In Hopfield net the number ofbinary patterns that can bestored and recalled ina net with
a. P 0.15n
b. P 0.25n
c. P 0.35n
d. P 0.5n
193. The following sets have a tendency to stabilize to a local minima rather than global minima a.
Hopfield
b. BAM
c. Boltzmann's machine
d. ART1
a. Hopfield
b. BAM
c. Boltzmann's machine
d. ART1
a. Feed forward
b. Feedback
c. Feed follow
d. Adhoc
196. The asynchronous discrete time updating ofthe units allows a function known as [b]
a. Time function
b. Energy function
c. Memory for
d. Signal function
197. Energy function is also called as the following function to befound for net
a. Boltzmann s Machine
b. Lyapnuov function c.
Sigmoid function
d. Threshold function
198. The following functions proves that the net will converge to a stable set ofactuations
a. Boltzmann's Machine
b. Lyapnuov function c.
Sigmoid function
d. Threshold function
a. Feed forward
b. Feed back
c. Feed follow
d. Adhoc
200. In the following mode oftraining, all neurons in Hopfield networks fire at the same time.
a. Stable state
b. Output
c. Synchronous
d. Asynchronous
a. 2n
b. 2n
c. n2
d. n + n
b. 0
c. 5
a. {1,2,6,7}
b. {1,2,3,4}
c. {6,7}
d. {5}
204. If A={a,b,c,1,2} B={1,2,3,a,c} then A B=
a. {a,c,1,2}
b. {a,b,c}
c. {a,c}
d. {}
a. {a,b.c,1,2,3}
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
b. {a,b,c}
c. {1,2,3}
d. {}
a.
b. Ac
c. and Ac
d. A
a. Joint
b. Disjoint
c. Subsets
d. Supersets
208. If A= {a,b,c,d,e} B={b,d} then A-B=
a. {a,c,e}
b. {a,c}
c. {a}
d. {d}
a. 16
b. 4
c. 10
d. 8
210. A Ac = is
a. Commutative
b. Associative
c. Distributive
d. Law of contradiction
a. Ac Bc
b. A Bc
c. Ac B
d. Ac Bc
a. Ac Bc
b. A Bc
c. Ac B
d. Ac Bc
213. Partition on A indicated as (A) is therefore for each pair (i,j)I for ij
a. Ai Aj =
b. iJ Ai =A
c. iJ Ai =1
d. iJ Ai =0
214. The following on A is defined to a set ofnon empty subsets Ai, whose union yields the
original set A
a. Partition
b. Covering
c. Opening
d. Closing
215. The following on A is defined to a set ofnon empty subsets Ai, each ofwhich is pair wise
a. Partition
b. Covering
c. Opening
d. Closing
Rule ofaddition
b. Rule of inclusion
c. Rule of exclusion
d. Rule of application
217. If the subsets are not pair wise disjoint then the following is not applicable on the covering of
set A
a. Rule of addition
b. Rule of inclusion
c. Rule of exclusion
d. Rule of application
Commutative
b. Associative
c. Distributive
d. Idempotence
a. Commutative
b. Associative
c. Distributive
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
d. Idempotence
a. Commutative
b. Associative c.
Distributive d.
Idempotence
a. Commutative
b. Associative
c. Distributive
d. Identity
a. Commutative
b. Associative
c. Distributive
d. Law of absorption
223. If A B, BC then A C is
a. Commutative
b. Associative
c. Distributive
d. Transitive
a. Commutative
b. Associative
c. Distributive
d. Involution
a. Commutative
b. Associative
c. Distributive
226. In discrete BAM for Binary input vectors, the weight matrix can bedetermined bythe formula
227. In discrete BAM for Bipolar input vectors, the weight matrix can bedetermined bythe
formula
228. In continuous BAM for binary input vectors the weights are determined bythe formulae
j)=1/(1+exp(-yin j)
b. f(yin j)=1+(1+exp(-yin j)
c. f(yin j)=1-(1+exp(-yin j)
d. f(yin j)=1*(1+exp(-yin j)
230. If the net input is equal to the threshold value, the activation function decide to
c. Zero
d. One
231. The following memory has the capability to transfer the input smoothly and continuously into
respective output in the range between [0,1]
a. Continuous BAM
b. Discrete BAM
232. The continuous BAM uses the following function asthe activation function
233. If bias is included in calculating the net input in Y layer then f(yin j )
a. f(yin j) =bj+xiWij
b. f(yin j) =bj-xiWij
c. f(yin j) = xiWij
d. f(yin j) =bj+Wij
a. Rumelhar
b. Wilson c.
Hecht
d. Kosko
235. BAM is
d. Perceptron
236. Different forms of BAM are
a. Only binary
b. Only Bipolar
c. Only continuous
SRM Infotech - For all Types of Software Projects and Courses || Contact :: 0866 646 3006
100% Free SMS: ON<space>UandiStar to 9870807070 for Tech SMS,JNTU Alerts,JOB Alerts,
GATE,GRE
NOTIFICATIONS
a. Rumelhart
b. Neilson
c. McCulloh
d. Kosko
239. The difference between the number ofbits in two binary orbipolar vectors x1 and x2 is called
a. Hamming distance
b. Euclidean distance
c. Mean distance
d. Variance
240. The average hamming distance between the vectors is
a. 1/n [HD(x1,x2)]
b. 1/2n [HD(x1,x2)]
c. 1/3n [HD(x1,x2)]
d. 1/2 [HD(x1,x2)]
Action taken:
22. Discussion topics if any (group wise topics)
4. Learning improvements
8. Defuzzification methods.
2. www.iitk.ac.in/electrical
ADDITIONAL TOPICS
1. A HIGH PERFORMANCE INDUCTlON MOTOR DRIVE SYSTEM USING FUZZY LOGIC CONTROLLER
REFERENCE BOOKS:
1. Neural Networks James A Freeman and Davis Skapura, Pearson Education, 2002.
4. Neural Networks and Fuzzy Logic System by Bart Kosko, PHI Publications.
Websites
1. ieeexplore.ieee.org
2. www.sciencedirect.com/
3. www.academia.edu
STUDENT ROLL
HARINATH
1 37
09R11A0219 PERALI 11R11A0237 N RAJASHEKAR REDDY
ALLAKONDA SAI
3 39
11R11A0202 KUMAR 11R11A0239 NAGULA SWAMY KRANTHI KUMAR
ASHISH YADAV
4 40
11R11A0204 M 11R11A0240 NAMA SAMPATH
B KRANTHI
6 42
11R11A0206 KUMAR 11R11A0242 P K V N SAI KIRAN
BETHALA
7 43
11R11A0207 NAGARAJ 11R11A0243 PAKA SHARATH CHANDRA
BEJJENKI ANIL
8 44
11R11A0208 KUMAR 11R11A0244 PAMARTI MONIKA
CHIGURUPALLI
9 45
11R11A0209 SUSHANTH 11R11A0245 PARAMKHUSHAM PRANAY
CHINTA HEMA
10 46
11R11A0210 REDDY 11R11A0246 PERUMULA NAVEEN VARMA
D SAIRAM
11 47
11R11A0211 GOUD 11R11A0247 POLICE PATEL LAVANYA
EADARA SURAJ
12 48
11R11A0212 CHOWDARY 11R11A0248 PRATYASHA MISHRA
ELEMASETTY
13 49
11R11A0213 UDAY KIRAN 11R11A0249 RAKESH REDDY KATIPELLI
G PRADEEP
14 50
11R11A0214 KUMAR 11R11A0250 RAVALASA VENKATESH
GADIYARAM
NIKHITHA
15 51
CHANDRA
11R11A0215 LEKHA 11R11A0251 SANAGAPATI ANUSHA
GAJULAPATI
16 52
11R11A0216 RAJINI 11R11A0252 SHAIK AZHARUDDIN
GANGABATHUL
17 A VIJAYA 53
11R11A0217 GOWRI DEVI 11R11A0253 SHAIK MASTHAN VALI
GATTUPELLY
18 VAMSHIKRISHN 54
11R11A0218 A 11R11A0254 SRI PRIYA BANDARI
GONA HARI
19 55
11R11A0219 KISHORE REDDY 11R11A0255 SUGURU SHILPA
GUDURU
20 56
11R11A0220 ARCHANA 11R11A0256 T.PRASHANTH KUMAR REDDY
K. NAGENDRA
25 61
11R11A0225 BABU 12R15A0201 C V P KUMAR
K VIKRAM
26 62
11R11A0226 SRIRAM 12R15A0202 MANCHICANTI NAGESH
KANDADI
27 SANDEEP 63
11R11A0227 REDDY 12R15A0203 K INDU
KASOJU
28 BHARATH 64
11R11A0228 KUMAR 12R15A0204 YEPURI VENKATESH
KONDAPALLI
29 65
11R11A0229 SHIRISHA MANI 12R15A0205 SAGI SRIPAL
KUNTA
30 66
11R11A0230 HARIKRISHNA 12R15A0206 KETHAVATH MANTHRU
M SHARATH
31 67
11R11A0231 KUMAR 12R15A0207 BASABOINA VENKATESH
SANDEEP
34 70
11R11A0234 KUMAR M V 12R15A0210 PULUGUJJU PHANEDRA KUMAR
35 MATTA 71
11R11A0235 12R15A0211 SRI RAM ANJAIAH BHARATH KUMA
SUMANTH
REDDY
MOHAMMAD
36 72
11R11A0236 VAZID RUMAN 12R15A0212 BOMMANI ASHOK
GROUP 1
11R11A0201 A.HARITHA
11R11A0205 B.BABITHA
GROUP 2
GROUP 3
GROUP 4
11R11A0223 K KEERTHI
11R11A0224 K MOUNIKA
GROUP 5
GROUP 6
11R11A0232 M.VINOD
11R11A0233 M.SREENATH
GROUP 7
11R11A0238 N SURESH
GROUP 8
GROUP10
12R15A0201 C V P KUMAR
12R15A0203 K INDU
GROUP 12
12R15A0209 E PRASANTH