AKTU Machine Learning Techniques (BCDS062) 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 × 7 = 14 marks

1. Differentiate between supervised and unsupervised learning.
2. What is the role of the hypothesis in a learning system?
3. Define hyper plane in the context of SVM.
4. Differentiate between linear and logistic regression.
5. What is inductive bias?
6. What is gradient descent?
7. Define the Markov Decision Process (MDP).

Section B

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

1. Compare Naïve Bayes classifier and Bayesian belief networks.
2. Discuss the properties that make SVM effective for high-dimensional data with example.
3. Explain how k-NN works. What are its advantages and limitations?
4. Describe the basic architecture of a convolution neural network (CNN) with help of diagram.
5. Explain the GA cycle of reproduction with a neat diagram.

Section C

Q3

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

1. How Machine Learning algorithms help in detecting fraudulent activities in finance sector? Also give some real-time software used.
2. Compare regression, classification and clustering in machine learning along with suitable real-life applications.

Q4

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

1. Discuss entropy and information gain in detail. Why are they important in decision tree learning? Illustrate with a numerical example.
2. Discuss the concept of Radial Basis Function (RBF) networks. Provide the mathematical formulation and architecture.

Q5

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

1. Explain the working of instance-based learning. Use diagrams to show how classification is done using k-NN.
2. Explain the concept of SVM kernels. Compare different SVM kernels with mathematical formulation and application suitability. Also, explain how SVM determines the optimal hyper plane.

Q6

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

1. Explain the architecture and functioning of a Multilayer Perception (MLP). How does it differ from a single-layer perceptron?
2. Discuss the concept of CNN architecture. Explain the role of different layers such as convolution, pooling, activation, and fully connected layers.

Q7

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

1. What is Deep Q-learning? How does it improve over traditional Q- learning? Explain with an architecture diagram.
2. Compare Genetic Algorithms and Reinforcement Learning in terms of learning paradigm, memory, and exploration strategy.

Short on time? See the most repeated AKTU Machine Learning Techniques questions across all years.

Other years

More AKTU Machine Learning 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.