Scribd
Upload
145 views2 pages

Soft Computing Important Questions

The document outlines important questions related to Soft Computing, categorized into two sections: 2-mark questions and 5-mark questions. It covers fundamental concepts such as fuzzy logic, perceptrons, genetic algorithms, and neural networks, along with numerical problems and explanations of various algorithms and systems. The content is designed to assess understanding and application of soft computing principles.

Uploaded by

Swatee Swagatika Sahoo
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
145 views2 pages

Soft Computing Important Questions

The document outlines important questions related to Soft Computing, categorized into two sections: 2-mark questions and 5-mark questions. It covers fundamental concepts such as fuzzy logic, perceptrons, genetic algorithms, and neural networks, along with numerical problems and explanations of various algorithms and systems. The content is designed to assess understanding and application of soft computing principles.

Uploaded by

Swatee Swagatika Sahoo
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Soft Computing Important Questions

Section A: 2-Marks Questions (10)

1. Define Soft Computing. How does it differ from Hard Computing?

2. What is a membership function in fuzzy logic?

3. Define Perceptron.

4. Write the formula for weight update in the delta learning rule.

5. What is crossover in Genetic Algorithms?

6. What is defuzzification? Name two techniques.

7. List two activation functions used in neural networks.

8. Differentiate between exploitation and exploration in Genetic Algorithms.

9. Write the rule for AND operation in fuzzy logic.

10. What is the output of a sigmoid function for input = 0?

Section B: 5-Marks Questions (12)

1. (Numerical) Given a fuzzy set A = { (x1, 0.2), (x2, 0.5), (x3, 0.8) }, calculate the centroid using the

centroid method of defuzzification.

2. (Numerical) For a perceptron with weights w1 = 0.4, w2 = -0.7 and inputs x1 = 1, x2 = 0, threshold

= 0.2, calculate the output using step activation function.

3. Explain the architecture of a fuzzy inference system with a neat block diagram.

4. Describe the working of Backpropagation Algorithm.

5. Explain the process of fuzzification and defuzzification with examples.

6. (Numerical) Perform one iteration of a Genetic Algorithm using the following:

- Chromosomes: 1001, 1100

- Crossover point: 2

- Mutation at bit position 3

7. Explain the differences between Mamdani and Sugeno fuzzy inference systems.
8. Describe the working of Hebbian Learning with an example.

9. (Numerical) Given input vector [1, -1], initial weights [0.5, -0.5], target output = 1, learning rate =

0.1, use perceptron learning rule to update weights.

10. What is a Neuro-Fuzzy system? Explain with an example architecture.

11. Compare Genetic Algorithms and Neural Networks on the basis of learning style, application,

and optimization.

12. Explain different types of membership functions and their significance in fuzzy systems.

You might also like