AKTU MCA Soft Computing (BMC032) Question Paper 2025-26

Note: Attempt all Sections. If require any missing data; then choose suitably.

Section A

Q1. Attempt all questions in brief · 2 × 7 = 14 marks

1. List the constituents of soft computing.
2. Define swarm intelligence.
3. Compute weighted sum for three inputs 1, 2, 3 with weights 0.2, 0.3, 0.4.
4. What are the applications of the Kohonen self - organizing feature map (SOFM)?
5. A perceptron has threshold 1 and net input 1.5. Find the output.
6. Differentiate fuzzy logic and crisp logic.
7. Find offspring using one - point crossover on 11001 and 10110 (cut point = 2).

Section B

Q2. Attempt any three of the following · 7 × 3 = 21 marks

1. Define binary step activation function . A neuron has inputs x 1 =2, x 2 =3, weights w 1 =0.4, w =0.5, and bias 0.2. Calculate the neuron output using binary step activation.
2. Illustrate how supervised, unsupervised, and reinforcement learning differ in artificial neural networks .
3. Given two fuzzy sets:
   A= {(x , 0.2), (x , 0.5), (x , 0.7), (x , 1.0)}
B= {(x , 0.6), (x , 0.4), (x , 0.8), (x , 0.3)}
   Compute the following:
   (i) Union 𝐴 ∪ 𝐵 .
   (ii) Intersection 𝐴 ∩ 𝐵 .
   (iii) Complement of 𝐴
4. Given a genetic algorithm population with chromosomes A = 1100 (fitness 12), B = 1010 (fitness 20), C = 1110 (fitness 30), and D = 1001 (fitness 18), perform one generation of evolution using roulette wheel selection, single - point crossover, and bit - flip mutation.
5. Compare Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) algorithms with their suitable application areas. P.T. O.

Section C

Q3

Attempt any one part of the following · 7 × 1 = 7 marks

1. Define sigmoid activation . Let a neuron has inputs (1, 2, 3), weights (0.1, 0.2, 0.3), and bias 0.5. Find the final output using sigmoid activation.
2. Explain neuro - fuzzy hybrid systems with architecture.

Q4

Attempt any one part of the following · 7 × 1 = 7 marks

1. Compare hard computing and soft computing with suitable examples.
2. For an ant colony optimization system with paths A = 0.2, B = 0.5, C = 0.3 and 20 ants, determine (i) S election probabilities, (ii) E xpected ant distribution, and (iii) P heromone update after evaporation.

Q5

Attempt any one part of the following · 7 × 1 = 7 marks

1. Perform o ne complete forward propagation iteration for a multilayer perceptron with inputs x 1 =0.5, x 2 =0.8, initial weights w 11 =0.2, w 12 =0.4, w 21 =0.3, w 22 =0.1, hidden biases b 1 =0.1, b 2 =0.2, output weights v 1 =0.3, v 2 =0.5, output bias b=0.1, learning rate η=0.1, and target output y=1 using sigmoid activation.
2. Explain Tabu Search algorithm and its components.

Q6

Attempt any one part of the following · 7 × 1 = 7 marks

1. Explain radial basis function (RBF) neural networks and their characteristics.
2. A fuzzy set with medium speed is defined using a triangular membership function with parameters a = 40, b = 60, and c = 80. A crisp input speed is x=60 km/h. Find the membership value of x using the triangular membership function.

Q7

Attempt any one part of the following · 7 × 1 = 7 marks

1. Define α - cut in fuzzy set theory and determine the α - cuts for the fuzzy set with membership values {0.2, 0.5, 0.7, 0.9} for α = 0.5 and α = 0.8.
2. Compare genetic algorithm with traditional optimization techniques.

Other years

More AKTU Soft Computing papers on LearnAIFast.

This paper is reproduced for study purposes only. Copyright belongs to AKTU. Source: the question paper bank of ABES Institute of Technology, an AKTU-affiliated college. If you own the copyright and want it removed, email learnwithskillnest@gmail.com and we will take it down.