Scribd
Upload
91 views4 pages

Neural Network and Fuzzy Logic

This document contains 20 questions related to neural networks and fuzzy logic. The questions cover topics such as threshold activation functions, biological neurons, single and multilayer neural networks, learning rules, backpropagation, Hopfield networks, adaptive resonance theory, genetic algorithms, fuzzy sets, neuro-fuzzy networks, optical neural networks, self-organizing maps, and implementing a backpropagation network. The questions range from definitions and explanations to examples and mathematical problems.

Uploaded by

Rashi Sharma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
91 views4 pages

Neural Network and Fuzzy Logic

This document contains 20 questions related to neural networks and fuzzy logic. The questions cover topics such as threshold activation functions, biological neurons, single and multilayer neural networks, learning rules, backpropagation, Hopfield networks, adaptive resonance theory, genetic algorithms, fuzzy sets, neuro-fuzzy networks, optical neural networks, self-organizing maps, and implementing a backpropagation network. The questions range from definitions and explanations to examples and mathematical problems.

Uploaded by

Rashi Sharma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

Subject – NNFL(CSE-402N)

20 Most Important Questions

Q:1(a)What do mean by threshold activation function and Bias? 5M

(b) Explain structure of Biological Neuron ? 5M

(c) Differentiate between Brain and Computer. 5M

Q:2(a)Differentiate between single layer and multilayer neural network. 8M

(b) What are the applications of Artificial Neural Network? 7M

Q:3(a) Is XOR gate linearly separable, justify your answer ? 7M

(b) What do you mean by a learning rule and what are its types? 8M

Q:4 (a)Prove that Hopfield networks are stable in nature? 7M

(b) If the net input is 0.50, calculate its output when the activation function used is (i) binary

Sigmoidal (ii) bipolar sigmoidal. 8M

Q:5(a)What do you mean by activation function? 5M

(b) Explain structure of Artificial Neuron ? 5M


(c)What do you mean by linear separability? 5M
Q:6(a)What are the different architectures of neural network? 7M
(b) Differentiate between biological and artificial neural network? 8M
Q:7 What do mean by single layer perceptron? Why do we need multilayer perceptron?
Which problem cannot be solved by single layer perceptron, explain? 15M
Q:8 (a) Explain Training algorithm of Back Propagation Network? 10M
(b)Write down short note on Hopfield Networks. 5M

Q:9(a) Explain the procedure for encoding and retrieving associations in BAM . 8M

(b) Differentiate between discrete and continous BAM? 7M


Q: 10(a) Consider a BAM network (with bipolar vectors) to map two simple letters (given by

5X3 patterns) to the following bipolar target codes

*** * *

* * *

*** * * *

* * *

*** * *

Pattern(E) Pattern(H)

(1,-1) (-1,1)

(i) Find the weight matrix with input pattern E and H.

(ii) Obtain the response of the net with E and H as input. 10M

(b) What are the characteristics of Adaptive Resonance Theory? 5M

Q: 11(a) What do you mean by simple cells and complex cells of a Neocognitron net? 7M

(b) How is electro optical matrix multipliers used to achieve more speed of operation? 8M

Q: 12 (a) What is the function of threshold device used in optical image Recognition system?
8M

(b) How is an ART net designed for both stability and plasticity? 7M

Q: 13)(a)Differentiate between crossover and mutation with the help of an example?


5M

(b)What is importance of Genetic Algorithm? 5M

(c)With a neat flowchart explain the operation of Genetic Algorithm? 5M

Q: 14 Determine alpha-level sets, strong alpha level sets, height and supports of the
following fuzzy sets with alpha cut= 0.4
Ã0= {(3, .1),(4,.2),(5,.3),(6,.4),(7,.4),(8,.8),(10,1)}
Ã1={(2,.4),(3,.6),(4,.8),(5,1),(6,.8),(7,.6),(8,1)}

Ã2={(2,.4),(4,.8),(5,1),(8,.6)} 15M

Q:15(a) Explain how will you perform union, intersection and compliment operation in fuzzy

set theory. Also give examples. 10M


(b) What do mean by Neuro Fuzzy Networks? 5M

Q:16 (a) Explain the architecture of Neuro Fuzzy Networks? 8M

(b) Differentiate between classical and fuzzy sets? 7M

Q.17(a) What are the types of optical neural networks? 8M

(b)Describe the algorithmic calculations performed on the Neocognitron network? 7M

Q.18(a) What is the procedure to compress an image using ART? 9M

(b How are electro optical matrix multipliers used to achieve more speed of operation? 6M

Q.19 (a) Consider the following full CPN using input pair X=(1,1) Y=(0,1). Perform first phase of
training (one step only). Find the activation of the cluster layer units and update the weights using
learning rates of 0.3.

0.2 0.1
X1 Z1 Y1

0.4 0.6

0.3 0.3

0.5 0.7 9M
Y2
X2 Z2

(b) What are the kohonan self organizing maps? 6M

Q. 20(a) Derive the learning rule used in the back propagation net. 7M

(b) Implement a back propagation net for the following information of the given net

2 1 0

W=[+1 1 2] , W0 =[-1], V= 1 2 2 , V0=[0 0 -1] Input pattern X=[0.6 0.8 0]

0 3 1
Target output is 0.9. Use learning rate as 0.3 and use binary sigmoid activation function. Here W
represents the connection between hidden layer and output layer. W 0 is the bias provided to the output unit
‘y’. V matrix represents connection weights between input and hidden units? 8M

You might also like