AKTU Deep Learning (BAI701) Question Paper 2025-26

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. Define model in machine learning.
2. What is the difference between linear regression and logistic regression?
3. Discuss convolutional neural network (CNN)?
4. Name any two activation functions used in deep networks.
5. Describe the role of regularization during optimization.
6. Discuss the generalization in machine learning.
7. Name two applications of Word2Vec.

Section B

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

1. Derive the mathematical expression for the output of a single hidden-layer neural network. Explain the role of activation functions.
2. Describe how probabilistic models help reduce overfitting. Explain with examples.
3. Compare PCA and LDA. Explain how LDA maximizes class separability using scatter matrices.
4. Explain the optimization problem in deep learning. Why are deep learning loss surfaces highly non-convex? Discuss with suitable diagrams.
5. Describe the ImageNet dataset in detail. Explain its scale, structure, challenges, and importance in the evolution of deep learning.

Section C

Q3

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

1. Explain the backpropagation algorithm in detail. Derive the weight update rule for a multilayer perceptron.
2. Discuss the significance of activation functions in the Universal Approximation Theorem.

Q4

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

1. Compare batch normalization with layer normalization and instance normalization.
2. Explain the concept of semi-supervised learning with examples. Compare it with supervised and unsupervised learning.

Q5

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

1. Explain convolution operation mathematically, including stride, padding, and feature maps.
2. Compare AlexNet, VGG, Inception, and ResNet in terms of depth, performance, 3 and computation.

Q6

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

1. Compare RNN, LSTM, and GRU networks. Highlight their advantages and use- cases.
2. What is deep reinforcement learning? Explain its architecture involving policy networks, value networks, and environment interaction.

Q7

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

1. Explain how WaveNet differs from RNNs for sequential audio generation.
2. Explain the Word2Vec model. Discuss CBOW and Skip-Gram architectures with diagrams.

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.