AKTU Deep Learning (KOT076) 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 is a loss function, and why is it essential for training a neural network?
2. What is stochastic gradient descent?
3. Explain the significance of the “AI Winter” in deep learning history.
4. What is the probabilistic theory of deep learning?
5. Define Linear Discriminant Analysis (LDA).
6. Explain how distance metrics are used in machine learning.
7. Define non-convex optimization.
8. What is generalization in deep learning?
9. What is WaveNet, and why is it significant for audio generation?
10. What is Word2Vec?

Section B

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

1. Illustrate how activation functions like ReLU and Sigmoid work in a shallow network.
2. Explain the role of the generator and discriminator in GANs.
3. What is the significance of the AlexNet architecture in deep learning history?
4. Explain the role of STNs in addressing spatial invariance in deep learning.
5. Describe the role of deep learning in bioinformatics applications.

Section C

Q3

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

1. Explain the purpose of backpropagation in training neural networks.
2. Describe the role of stochastic gradient descent (SGD) in optimization.

Q4

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

1. Demonstrate the working of a CNN on image classification tasks.
2. Demonstrate how batch normalization reduces internal covariate shift.

Q5

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

1. Demonstrate the effect of Xavier and He initialization on training a ConvNet.
2. Illustrate the role of residual connections in ResNet and their importance.

Q6

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

1. Explain how LSTMs address the vanishing gradient problem in RNNs.
2. Explain how RNNs are used for next-word prediction in text data.

Q7

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

1. Describe how attention mechanisms improve the performance of image captioning models.
2. Explain how semantic segmentation helps in scene understanding.

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

Other years

More AKTU Deep 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.