AKTU Machine Learning (KME074) Question Paper 2024-25

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

Section A

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

1. Explain the terms Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning.
2. What are the three main types of machine learning? Explain each type with an example.
3. What is the implication of the use of a single learning rate (η) for all features (x ) in gradient descent optimization?
4. Differentiate between training data and testing data in machine learning.
5. Describe dimension reduction in machine learning.
6. Define hierarchical clustering.
7. Explain the term 'loss function' in deep learning.
8. What is the meaning of Overfitting in Machine learning?
9. Use a genetic algorithm to optimize a scheduling problem and explain each step.
10. Define the term "kernel" in the context of Gaussian processes.

Section B

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

1. Describe artificial intelligence (AI) and its potential impact on modern industries.
2. What is the purpose of support vector machines (SVM), and how do they work?
3. What is the expectation-maximization algorithm? Provide a brief overview.
4. Discuss the challenges and limitations of the Backpropagation algorithm in neural network training.
5. Define Hidden Markov Models (HMM) and their applications.

Section C

Q3

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

1. What are the essential steps involved in designing a learning system? Explain each step briefly.
2. Explain the applications of machine learning in mechanical engineering. Provide at least three use cases.

Q4

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

1. Explain Bayesian Decision Theory.
2. What are bias and variance in machine learning? How do they affect model performance?

Q5

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

1. Define Principal Component Analysis (PCA) and its role in dimensionality reduction.
2. What is clustering, and how does it differ from classification?

Q6

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

1. Given stride S and kernel sizes for each layer of a (1-dimensional) CNN, create a function to compute the receptive field of a particular node in the network. This is just finding how many input nodes actually connect through to a neuron in a CNN.
2. Explain the concept of a kernel function in machine learning. How does it enable Support Vector Machines (SVM) to perform classification in higher-dimensional spaces? Provide examples of three commonly used kernel functions and their applications.

Q7

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

1. Compare and contrast Bayesian estimation with Maximum Likelihood Estimation (MLE). Highlight their advantages and disadvantages in the context of machine learning models.
2. Discuss the differences between reinforcement learning and deep learning in the context of problem-solving.

Short on time? See the most repeated AKTU Machine Learning (Open Elective) 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.