UNIT I

Quiz
A perceptron is:
(a) a single layer feed-forward neural network with preprocessing
(b) an autoassociative neural network
(c) a double layer autoassociative neural network

An autoassociative network is:

(a) a neural network that contains no loops
(b) a neural network that contains feedback
(c) a neural network that has only one loop

4-input neuron has weights 1, 2, 3 and 4. The transfer function is linear with the
constant of
proportionality being equal to 2. The inputs are 4, 10, 5 and 20 respectively. The
output will be:
(a) 238
(b) 76
(c) 119

Which of the following is true?

(i) On average, neural networks have higher computational rates than conventional
computers.
(ii) Neural networks learn by example.
(iii) Neural networks mimic the way the human brain works.
(a) all of them are true
(b) (ii) and (iii) are true
(c) (i), (ii) and (iii) are true

Which of the following is true for neural networks?

(i) The training time depends on the size of the network.
(ii) Neural networks can be simulated on a conventional computer.
(iii)Artificial neurons are identical in operation to biological ones.
(a) all of them are true.
(b) (ii) is true.
(c) (i) and (ii) are true.

1) Define ANN and Neural computing.

2) Distinguish between Supervised and Unsupervised Learning.
3) List some applications of ANNs.
4) What are the design parameters of ANN?
 5) Explain the three classifications of ANNs based on their functions. Explain
them in brief.
6) What are the basic computational needs for Hardware implementation
of ANN?
7) Explain the linear seprability.
8) Explain the neural networks and perception model

UNIT II

What are the advantages of neural networks over conventional computers?

(i) They have the ability to learn by example
(ii) They are more fault tolerant
(iii)They are more suited for real time operation due to their high 'computational'
rates
(a) (i) and (ii) are true
(b) (i) and (iii) are true
(c) all of them are true

Which of the following is true?

Single layer associative neural networks do not have the ability to:
(i) perform pattern recognition
(ii) find the parity of a picture
(iii)determine whether two or more shapes in a picture are connented or not
(a) (ii) and (iii) are true
(b) (ii) is true
(c) all of them are true

ANN is composed of large number of highly interconnected processing

elements(neurons) working in unison to solve problems.
A.True B. False

Artificial neural network used for

A.Pattern Recognition
B.Classification
C.Clustering
D.All of these

A Neural Network can answer

A.For Loop questions
B.what-if questions
C.IF-The-Else Analysis Questions
D.None of these
Ability to learn how to do tasks based on the data given for training or initial
experience
A.Self Organization
B.Adaptive Learning
C.Fault tolerance
D.Robustness

1) Draw the basic topologies for (a) Nonrecurrent and (b) Recurrent Networks
and distinguish between them.
2) Give some examples for Nonrecurrent and Recurrent ANNs. Specify the
learning law used by each ANN.
3) Draw the model of MP (McCulloch Pitts) neuron and state its characteristics.
4) Explain the training of grossberg layer and kohonen layer.
5) Explain the architecture of Hopfield nets and its energy function.
6) Brief note on statistical training method and bolts man machine.
7) Explain the architecture of counter propagation network
 UNIT III

Feature of ANN in which ANN creates its own organization or representation of

information it receives during learning time is
A.Adaptive Learning
B.Self Organization
C.What-If Analysis
D.Supervised Learniing

In artificial Neural Network interconnected processing elements are called

A.nodes or neurons
B.weights
C.axons
D.Soma

Each connection link in ANN is associated with ________ which has information
about the input signal.
A.neurons
B.weights
C.bias
D.activation function

Internal state of neuron is called __________, is the function of the inputs the
neurons receives

A.Weight
B.activation or activity level of neuron
C.Bias
D.None of these

Neuron can send ________ signal at a time.

A.multiple
B.one
C.none
D.any number of

1) Describe the feature of ART network.

2) Write the differences between ART 1 and ART 2.
3) Draw the architecture of ART1 network and explain in detail.
4) Explain ART1 algorithm.
5) What is meant by stability plasticity dilemma in ART network?
6) What is 2/3rd rule in ART?
 7) What are the two subsystems in ART network?
8) What are the applications of ART?
9) Explain Implementation and Training of ART.

UNIT IV
Quiz

Q1. Which of the following is not true regarding the principles of fuzzy logic ?
a. Fuzzy logic is a concept of `certain degree'.
b. Fuzzy logic follows the principle of Aristotle and Buddha.
c. Japan is currently the most active users of fuzzy logic.
d. Boolean logic is a subset of fuzzy logic.

Q2. Which of the following is not true regarding the principles of fuzzy logic ?
a. Fuzzy logic is a concept of `certain degree'.
b. Fuzzy logic follows the principle of Aristotle and Buddha.
c. Japan is currently the most active users of fuzzy logic.
d. Boolean logic is a subset of fuzzy logic.

Q3. Considering a graphical representation of the `tallness' of people using its

appropriate member function, which of the following combinations are true ?
i. TALL is usually the fuzzy subset.
ii. HEIGHT is usually the fuzzy set.
iii. PEOPLE is usually the universe of discourse.
a. i, ii & iii
b. i & ii only
c. i, iii only
d. ii & iii.

Q4. What is the Fuzzy Approximation Theorem(FAT) ?

a. A fuzzy sytem can model any continous sytem
b. The conversion of fuzzy logic to probability.
c. A continous sytem can model a fuzzy system.
d. Fuzzy patches covering a series of fuzzy rules.

Q5. What is the main difference between probability and fuzzy logic ?
a. Fuzzy logic is probability in disguise.
b. Fuzzy logic is the likelihood of an event occuring and probablility is the extent of
that event.
c. Probability is ADDITIVE, meaning all its values must add up to one.
d. Probability dissipates with decreasing information.

Question Bank
1) Define fuzzy set.
2) List the fuzzy set operations.
3) Short note on fuzzy adoptive system.
4) Describe fuzzy entropy theorem.
5) Write the fuzzy substheed theorem.
6) Explain fuzzy entropy hobsethood theorem.
7) Give a brief note on fuzzy associative memory.
8) Describe Fuzzy and Neural Function Entimators.
9) Fuzzy hebb FAMS, Adaptive FAMS

UNIT V

Quiz
Q1. In an adaptive fuzzy system
i. The machine learns as more data are fed into it.
ii. Nueral network is used to find the fuzzy rules.
iii. The system creates rules without the intervention of human beings.
a. i & ii & iii
b. i & ii
c. i, iii only
d. ii & iii

Q2. What are the following sequence of steps taken in designing a fuzzy logic
machine?
a. Fuzzification->Rule evaluation->Defuzzification
b. Rule evaluation->Fuzzification->Defuzzification
c. Fuzzy Sets->Defuzzification->Rule evaluation
d. Defuzzification->Rule evaluation->Fuzzification

Q3. Fuzzy logic has rapidly become one of the most successful of today's
technologies for developing sophisticated control systems. The reason for this is:
i. Fuzzy logic resembles the human way of thinking.
ii. Fuzzy logic enables the ability to generate precise solutions from certain or
approximate information.
iii. Fuzzy logic is easy to implement.
a. i & ii & iii
b. i & ii
c. ii & iii only
d. none of the above

Q4 What Is Another Name For Fuzzy Inference Systems?

A. Fuzzy Expert System
B. Fuzzy Modelling
C. Fuzzy Logic Controller
D. All of the above

Q5. Who is the founder of fuzzy logic?

a. Aristotle
b. Buddha
c. Zader Lotfi
d. Bart Kosko

Question

1) What are the basic elements of fuzzy logic control system?

2) Explain the steps in designing fuzzy control system.
3) Comparison between fuzzy and neural system.
4) Explain kalman filter controller.
5) Explain fuzzy image transform coding.
6) Define fuzzy controller.