Software computing model question paper 2

 B.E/B.Tech Degree Examinations April/May 2024 

Sixth Semester 

Computer Science Engineering 

(Common To Information Technology) 

CCS364-Soft Computing 

(Regulation 2021) 

Part A: (2x 10 = 20 Marks) Sof computing important question

1. Explain the concept of fuzzy sets and fuzzy membership functions. 

 2. Discuss the operations on fuzzy relations. 

3. . What is a perceptron? Describe its working with an example

 4. Explain the Kohonen Self-Organizing Network and its applications. 

5. Describe chromosome encoding schemes and their importance in genetic algorithms 

6. Explain the crossover and mutation operators in genetic algorithms 

7. Discuss the ANFIS architecture and its components 

8. What is Coactive Neuro-Fuzzy Modeling? Explain its framework 

9. Describe the process of modeling a two-input sine function using soft computing techniques. 

 10. Explain how soft computing can be used for color recipe prediction.

 Part B: (5 x 13 = 65 Marks) 

11. (a) Explain fuzzy inference systems and their role in fuzzy reasoning. 

(b) Describe the process of fuzzy rules formulation and its application in fuzzy reasoning 

12. (a) Discuss the backpropagation algorithm and its significance in training neural networks. 

 (b) Explain the structure and functioning of multilayer perceptrons.

 13. (a) Describe the population initialization and selection methods in genetic algorithms 

 (b) Explain the fitness function and its role in evaluating genetic algorithms. 

14. (a) Discuss the hybrid learning approach in ANFIS and its benefits.

 (b) Explain the analysis of adaptive learning capability in neuro-fuzzy systems. 

 15. (a) Discuss the application of soft computing techniques in printed character recognition. 

 (b) Explain the use of fuzzy filtered neural networks in plasma spectrum analysis.

 Part C: 

16. (a) Numerical: Train a simple perceptron with a given dataset. Use the provided inputs and target outputs to perform one iteration of weight updates. Show all steps and calculations. 

 Dataset: - Inputs: (1, 0), (0, 1), (1, 1), (0, 0) - Target Outputs: 1, 1, 0, 0 

 Initial Weights:- Weights: (0.5, -0.5) - Learning Rate: 0.1 

 (b)  Design a genetic algorithm to optimize a function that maximizes the output of a complex system. Describe the encoding scheme, initialization method, selection process, crossover, and mutation operators. Provide a sample evaluation function and discuss the steps involved in optimizing the system.

Comments

Popular posts from this blog

Cyber Security (CCS340) model question paper

Cryptocurrency and Blockchain Technologies (CCS339) model question paper