AKTU MCA Neural Network (KCA042) Question Paper 2021-22

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

Section A

Q1. Attempt all questions in brief · 2 × 10 = 20 marks

1. Define error correction learning.
2. What is the neuron importance in neural network?
3. How activation function works?
4. Differentiate between Aggregation and Activation function.
5. Define single layer network.
6. Differentiate between local minima and global minima.
7. How recurrent network works?
8. What do you mean by principal component analysis?
9. Define soft computing with example.
10. What do you mean by special networks?

Section B

Q2. Attempt any three of the following · 10 × 3 = 30 marks

1. Discuss the relevant computational properties of the Human Brain?
2. What is perceptron? Write the differences between Single Layer Perceptron(SLP) and Multilayer Perceptron(MLP).
3. What is RBF? Explain RBF properties with example.
4. Illustrate the independent component analysis with proper example.
5. Differentiate between complex valued NN and complex valued BP.

Section C

Q3

Attempt any one part of the following · 10 × 1 = 10 marks

1. Define knowledge representation and explain it with proper example.
2. What is Supervised learning and how it is differ from unsupervised learning?

Q4

Attempt any one part of the following · 10 × 1 = 10 marks

1. Discuss the bench mark problem in neural network.
2. Illustrate about the McCulloch-Pitts neuron model with diagram.

Q5

Attempt any one part of the following · 10 × 1 = 10 marks

1. Write the algorithm of generalized delta rule(Back Propagation Algorithm) and explain with example.
2. Explain Multi-layer neural network with proper diagram.

Q6

Attempt any one part of the following · 10 × 1 = 10 marks

1. Discuss in brief about Kohonen self-organizing feature maps architecture.
2. Explain the architecture of Learning vector quantization.

Q7

Attempt any one part of the following · 10 × 1 = 10 marks

1. Explain support vector machine and when this technique is required?
2. Discuss about the Hybrid soft computing techniques with example.

Short on time? See the most repeated AKTU Neural Network questions across all years.

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.