AKTU MCA Neural Network (KCA042) Question Paper 2024-25

Note: Attempt all Sections. In case of any missing data; choose suitably.

Section A

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

1. What are the features of neural networks?
2. Differentiate between supervised and unsupervised learning in artificial neural networks.
3. What are main components of McCulloch-Pitts neuron model?
4. Explain why a single-layer perceptron cannot solve nonlinearly separable problems.
5. Why moment based heuristic is used in back propagation?
6. Differentiate between local minima and global minima back propagation learning algorithm.
7. What is a recurrent neural network (RNN)?
8. What do you mean by principal component analysis (PCA)?
9. What is meant by hybrid soft computing techniques?
10. Write down the application of Soft computing.

Section B

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

1. What does "competitive learning" mean in the context of ANNs?
2. What is Hebbian learning and how is it applied in Hebb networks?
3. Explain Multi-layer neural network with proper diagram.
4. Describe the architecture and training algorithm of Kohonen’s Self- Organizing Feature Map (SOM).
5. Explain the basic concept and working of Support Vector Machines (SVM).

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. Explain the statistical nature of the learning process in artificial neural networks (ANNs).

Q4

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

1. Discuss the various activation functions. Explain them schematically.
2. Compare gradient descent and least mean square (LMS) algorithms in perceptron training.

Q5

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

1. Explain the backpropagation algorithm in multilayer networks. How does it address the problem of local minima?
2. What is a Radial Basis Function (RBF) network? Explain its architecture, training procedure, and approximation capabilities.

Q6

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

1. Explain the architecture and learning algorithm of Learning Vector Quantization (LVQ).
2. Compare and contrast Principal Component Analysis (PCA) and Independent Component Analysis (ICA).

Q7

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

1. Explain the Cognitron network and its biological inspiration. How does its hierarchical structure differ from a multilayer perceptron (MLP)?
2. Describe the architecture of a hybrid neuro-fuzzy system

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.