QUESTION BANK 2023-24

SIDDHARTH GROUP OF INSTITUTIONS :: PUTTUR

Siddharth Nagar, Narayanavanam Road – 517583

QUESTION BANK (DESCRIPTIVE)

Subject with Code : Neural Networks and Fuzzy Logic (20EE0239)

Course & Branch: B.Tech - EEE Year & Sem: IV-B.Tech & I-Sem
Regulation: R20

UNIT –I
FUNDAMENTALS OF ARTIFICIAL NEURAL NETWORKS

1 a Explain organization of human brain [L1][CO1] [6M]

b Discuss the functioning of biological neuron [L2][CO1] [6M]

2 a How artificial neuron is inspired from the biological neuron? Explain. [L2] [CO1] [6M]

b Explain the basic architecture of McCulloch – Pitts neuron model. [L3] [CO1] [6M]

3 a Explain characteristics of Artificial neural network. [L2] [CO1] [6M]

b What is generalization? Explain. [L2] [CO1] [6M]

4 a For the network shown in figure, calculate the net input to the neuron? [L3] [CO1] [6M]

b How do Neural Networks Work? [L1] [CO1] [6M]

5 Explain types of activation functions used in artificial neural network [L2] [CO1] [12M]

6 a What are the advantages of neural networks over conventional [L1][CO1] [6M]
computers?
b Discuss the applications of ANN. [L2] [CO1] [6M]

7 In detail, explain an Architectures of Neural Network with suitable [L2] [CO1] [12M]
figures
8 Try to implement XOR problem with two inputs and discuss on it. [L4] [CO1] [12M]

9 a Implement a perceptron to solve simple AND problem with two inputs. [L4] [CO1] [6M]
 QUESTION BANK 2023-24

b Obtain the output of the neuron Y for the network shown in the figure [L3] [CO1] [6M]

10 a Discuss different learning mechanisms used in artificial neural [L2] [CO1] [8M]
networks
b Why thresholding function is not used as activation function in Multi- [L3] [CO1] [4M]
Layer Feed Forward Networks.

UNIT –II
SUPERVISED NETWORKS

1 a Explain Supervised learning in detail with block diagram. [L1][CO2] [4M]

b Give the perceptron weight updating rule and the learning algorithm [L3] [CO2] [8M]

2 a Justify, why single layer perceptron network could not solve even XOR [L4][CO2] [6M]
problem.

b Derive the equation for weight change for discrete perceptron network. [L3] [CO2] [6M]

3 Find the total error at the output for a given neural network. [L3] [CO2] [12M]

4 Explain input layer, hidden layer & output layer computations in [L2] [CO2] [12M]
Backpropagation Network.

5 a Explain how supervised learning happens in neural networks with [L2] [CO2] [7M]
example.
 QUESTION BANK 2023-24

b Why We Need Backpropagation? [L2] [CO2] [5M]

6 Explain the weight adjustment procedure IN MLFFN using Back [L1] [CO2] [12M]
propagation algorithm
7 a Define Learning factors. Explain the learning factors in Back [L2] [CO2] [10M]
propagation Algorithm
b What is the objective function of gradient descent? [L1] [CO2] [2M]

8 a Explain about Back Propagation learning in detail. [L2] [CO2] [6M]

b List the advantages and disadvantages of BPA [L1] [CO2] [6M]

9 a In the given Neural network, compute the total error at the output. [L3][CO2] [12M]

1 a [L1] [CO2] [6M]

0 How does Perceptron work?
b Describe about the application of Neural networks to electric load [L2] [CO2] [6M]
forecasting

UNIT –III
ASSOCIATIVE MEMORIES

1 a What is Associative Memory? Explain it in detail. [L1][CO3] [4M]

b Train auto associative memory network to find optimal weight matrix [L4][CO3] [8M]
using outer product rule to store input row vector [1 1 1 1] and [-1 1 1 -
1]. Find the weight matrix and check with test vector using [1 1 1 1 ]
and [-1 1 1 -1 ]

2 a Describe about Bidirectional Associative Memory with its [L2] [CO3] [8M]
architecture.
 QUESTION BANK 2023-24

b Why BAM is required and its limitation. [L2] [CO3] [4M]

3 a Suppose one has N=3 with the pattern pairs given by, [L4][CO3] [8M]

A1=[1 0 0 0 0 1], B1=[1 1 0 0 0]

A2=[0 1 1 0 0 0], B2= [1 0 1 0 0]

A3=[0 0 1 0 1 1], B3=[0 1 1 1 0], retrieve correct output using input

b Distinguish Auto associative & Hetero associative memories. [L2] [CO3] [4M]

4 a Write an Algorithm to store and recall of BAM [L3][CO3] [4M]

b Train auto associative memory network to find optimal weight matrix [L4][CO3] [8M]
using outer product rule to store input row vector [1 0 0 1] and [1 1 1
1]. Find the weight matrix and check with test vector using [1 0 0 1 ]
and [1 1 1 1 ]

5 a Explain about Pattern Recognition with example. [L2][CO3] [6M]

b [L2][CO3] [6M]
With example, explain how to calculate Hamming Distance
6 a With architecture and algorithm explain about Discrete Hopfield [L2][CO3] [7M]
Network.
b Compute how to store and recall two associations, A1:B1 and A2:B2. [L3][CO3] [5M]

 A1 = (1, 0, 1, 0, 1, 0), B1 = (1, 1, 0, 0)

 A2 = (1, 1, 1, 0, 0, 0), B2 = (1, 0, 1, 0)
7 Train bidirectional associative network to store input vectors S=S1, S2, [L4][CO4] [12M]
S3, S4 to the output vectors T= T1, T2. Training input and target pairs
are in binary form. Obtain the weight vectors in bipolar form.

Input/Target S1 S2 S3 S4 T1 T2
1 1 0 0 0 0 1
2 1 1 0 0 0 1
3 0 0 0 1 1 0
4 0 0 1 1 1 0
8 a What are the phases involved in pattern recognition process and [L2][CO4] [12M]
Explain in detail.

b What are the applications of pattern recognition. [L2][CO4] [12M]

9 Construct and test a BAM network t associate letters E & F with [L4][CO4] [12M]
simple bipolar input output vectors. Target output for E is (-1,1) and
for F is (1,1). Display matrix size is 5*3. Input patterns are,
 QUESTION BANK 2023-24

10 Explain about types of associative memories along with architecture [L2][CO4] [12M]
and algorithm.

UNIT –IV
CLASSICAL AND FUZZY SETS

1 a Define membership function. What are the membership functions [L1][CO5] [6M]
used in fuzzy designing?

b Explain fuzzy intersection operation [L2][CO5] [6M]

2 a Compare and contrast Fuzzy vs Crisp [L2][CO5] [6M]

b Determine the union and intersection of the fuzzy sets, where A = [L3][CO5] [6M]
{(1.0.1). (2.0.5). (3, 0.8), (4, 1.0), (5.0.7). (6.0.2)} and B = {(1.1).
(2.0.8), (3.0.4), (4.0.1)}

3 Explain Operations performed on crisp sets using given datas, [L3][CO5] [12M]
X = {1, 2, 3, 4, 5, 6, 7, 8, 9}
A = {1, 2, 3, 4, 5}
B = {3, 4, 5, 6}
C = {6, 7, 8, 9}
4 What are the operations performed on fuzzy sets. Explain it in detail. [L2][CO5] [12M]

5 a Explain Cartesian product on fuzzy sets. [L2][CO5] [6M]

b Discuss how fuzzy relations are formed based on Cartesian product. [L2][CO5] [6M]

6 Give the properties of crisp sets. By using the following sets, [L3][CO5] [12M]
X = {1, 2, 3, 4, 5, 6}
A = {1, 2, 3},
B = {2, 3, 4},
C = {5, 6}
7 a Consider two fuzzy subsets of the set X, X = {a, b, c, d, e} referred to [L3][CO5] [7M]
as A and B.

A = {1/a, 0.3/b, 0.2/c 0.8/d, 0/e) and B = {0.6/a, 0.9/b, 0.1/c, 0.3/d,
 QUESTION BANK 2023-24

0.2/e}

Find:. (i) Complement. (ii) Union. (iii) Intersection iv) Difference

b Consider two fuzzy sets of the set A = {(a1, 0.2), (a2, 0.7), (a3, 0.4)} [L3][CO5] [5M]
B = {(b1, 0.5), (b2, 0.6)}
Find,the relation R (AxB)

8 a Explain the Features of Membership Functions [L2][CO5] [5M]

b Give the properties of fuzzy sets. [L2][CO5] [7M]

9 Consider a set P = P.P₁₂, P, P, of four varieties of paddy plants, set D [L3][CO5] [12M]
= {D1, D₂, D3, D4 } of the various diseases affecting the plants and
S={S1,S2,S3,S4} be the common symptoms of the diseases.
Let R be a relation on PxD and S be a relation on DxS

Obtain the association of the plants with the different symptoms of the
diseases using max-min composition
10 a What is fuzzy logic? Explain it in detail [L2][CO5] [6M]

b What is the sources fuzzy information? and explain each. [L2][CO5] [6M]

UNIT –V
FUZZY LOGIC SYSTEMS

1 a What are the basic building blocks in fuzzy logic ? [L1][CO6] [6M]

b What are the advantages of fuzzy logic control? [L1][CO6] [6M]

2 Explain fuzzy inference using Modus ponens and Modus tollens. [L2][CO6] [12M]

3 Justify, how temperature control is achieved by using fuzzy logic. [L4][CO6] [12M]

4 Explain fuzzy rule based system in fuzzy logic. [L3][CO6] [12M]

5 a Why defuzzification is important in fuzzy logic. [L3][CO6] [6M]

b What are the applications of fuzzy logic. [L2][CO6] [6M]

6 a List out different defuzzification methods available. [L1][CO6] [6M]

b Explain any one of the defuzzification method. [L2][CO6] [6M]

 QUESTION BANK 2023-24

7 a Explain Centre of gravity defuzzification method with an example. [L2][CO6] [6M]

b With an example, discuss Centre of Sums defuzzification method [L2][CO6] [6M]

8 Find crisp value corresponding to the following fuzzy output sets using [L3][CO6] [12M]
various defuzzification methods.

9 Discuss any one fuzzy logic application in electrical engineering. [L2][CO6] [12M]

10 a Explain working of Greg Viot’s Fuzzy Cruise controller. [L2][CO6] [6M]

b Design a Greg Viot’s Fuzzy Cruise controller for an autonomous car. [L4][CO6] [6M]