Scribd
Upload
439 views

Important Questions Soft Computing (1)

Uploaded by

jatin
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
439 views

Important Questions Soft Computing (1)

Uploaded by

jatin
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 9

Previous semester Question Papers 2023

MST 1

Q1. Describe the advantages of combining different soft computing techniques

Q2. Identify different Types of neural networks used in soft computing

3. Interpret the hebbian learning rule

4. Differentiate supervised and unsupervised learning in neural networks

5. Classify the various types of soft computing techniques

Section B

6. Explain with next diagram supervised and unsupervised learning in NN

7. Point out the merits and demerits of BPN

MST 2

1. Describe the significance of convolutional layers and pooling layers in CNN

2. Explain linearly separable problem briefly with example

3. Identify few activations function which are used in single and multilayer networks to calculate the
output

4. Discuss the advantage of auto encoder over Principal component analysis for dimensionality
reduction

5. Explain the working of Gated Recurrent Network

6Show the graphical representation of sigmoid function and differentiate of the sigmoid function and
comment of the result

7. A hetero associative network is trained by hebbs outer product rule for input vector

Unit 1 Questions

1. What is soft in soft computing?


2. Difference between hard and soft computing giving an example?
3. Describe five applications of Soft computing?
4. Discuss the main Domain of Soft computing?
5. How neural networks can be used to solve real-time problems. Give any real-time
application where NN are used.
6. What are different types of Neural Networks?
7. How ANN is trained? What is the role of the loss function in training a neural network?
8. What are the activation functions
9. How neural networks can be used to solve real-time problems. Give any real-time
application where NN are used.
10. What are different types of Neural Networks?
11. What are the activation functions? How do activation functions introduce non-linearity
into neural networks?
12. What is the best activation function that is used in most of the real-time problems?
13. Which activation function can give output in the range between 0 -1.
14. What are the challenges associated with vanishing and exploding gradients, and how do
different activation functions address these issues?
15. How do we initialize the neural networks?
16. Discuss the different types of Neural Network Architectures
17. What are the broad types of learning in Neural Network
18. Discuss the learning laws or rules
19. Explain the Back Propagation network (BPN) and how it helps in minimization of error
20. Discuss the training algorithm of BPN and use of stochastic gradient method in
minimization of error
21. Explain the concept of Adaline and Madaline with their architectures.
22. Discuss the implementation of Adaline with taking data from Nand Gate

Explain the perceptron model and architecture in detail. Also write the algorithm of the
same

23. Implementation of perceptron model with the AND gate

Unit 2 Question

1. What is generalized delta rule and the updating of hidden layer and output layer?
2. What are the various applications of neural networks?
3. State few activation functions which are used in single and multilayer network. 4.
4. What is a loss function in the context of neural networks?
5. Explain the concept of a cost function in machine learning, and how is it related to
the loss function?
6. Distinguish between Hopfield and iterative auto associative networks.
7. What are linearly separable problems?
8. Compare LSTM and gated recurrent units.
9. What is a Long Short-Term Memory (LSTM) network, and how does it address
the vanishing gradient problem?
10. Show the linearization of sigmoid function.
11. Compare and Contrast stateful and stateless LSTMs.
12. Define recurrent neural networks.
13. Define Associative memory.
14. Describe the significance of convolutional layer and pooling layer.
15. Describe Bidirectional associative memory.
16. Distinguish between recurrent and non-recurrent networks.
17. Explain Hopfield memory in brief.
18. Compare auto associative net and Hopfield net.
19. Explain self-organization in brief.
20. Distinguish between binary and bipolar sigmoid Function.
21. Write in brief about convolution layer.
22. Write some applications of CNN.
23. Illustrate denoising Auto encoders.
24. Write a short note on sparse auto encoders.
25. Explain Suitability of various activation functions with respect to applications.
26. Illustrate the operations of pooling layer in CNN with simple example.
27. Justify the advantages of auto encoders over principal component analysis for
dimensionality reduction.
28. Explain the working of gate recurrent unit.
29. Show graphical representation of sigmoid activation function.
30. Illustrate the significance of sigmoid activation function.
31. Graphically, sketch the different Activation functions used in NN.
32. Distinguish between Auto associative and heteroassociative Memory.
33. Describe rectified linear units and their generalized form.
34. Differentiate between Relu and Tanh Activation functions.
35. Explain the Algorithm of discrete Hopfield network and its Architecture.
36. Analyse the roll of rectified linear units in hidden layers.
37. Describe the characteristics of continuous Hopfield network.
38. Illustrate Encoder – Decoder sequence –to-sequence Architecture.
Q37. Find out the Net Input yin and final output Y of the network given below:

Q38. Calculate the net input for the network with bias included:
Q39 . Obtain the output of the neuron Y for the network using the activation function.

a) Binary Sigmoidal b) Bipolar Sigmoid

Solutions:
Unit 3 Questions

1. What are the limitations of fuzzy systems?


2. Explain the methods of fuzzifications.
3. What is core and boundary of membership function?
4. Explain in detail the operations of fuzzy set
5. Explain various operation on crisp relations
6. What is Centre of gravity method of defuzzification?
7. Explain with the help of block diagram the various components of Fuzzy logic system
8. Distinguish fuzzy set and crisp set
9. What’s the difference between fuzzy logic and binary logic
10. Explain in detail any one defuzzification method with example
11. What is the purpose of fuzzification layer
12. Discuss the methods of aggregation of fuzzy rules.
13. Define fuzzy logic and its importance in our daily life. What is the role of crisp sets in
fuzzy logic?
14. Explain fuzzy implications ?Discuss the fuzzy controller
15. What are advantages and disadvantages of GA?
16. Outline the advantages of GA over Conventional algorithms
17. Mention various types of cross over and mutation techniques
18. State the difference selection methods of GA
19. Name and Explain the role of Genetic operators in GA
20. Define mutation and various types of mutation in GA
21. Explain in detail different search techniques in GA
22. Discuss in detail about the various operations of GA and search space

You might also like