Home › AKTU PYQ › Deep Learning › PYQ Questions › Unit 1

Deep Learning Unit 1 – Introduction to Neural Networks: AKTU previous year questions

27 AKTU questions from Unit 1 (Introduction to Neural Networks) asked in 2023–2026, tagged by marks, year and topic. In short: about 30 marks of every paper come from this unit; the most asked topic is Training a Network (Loss, Backprop, SGD) (10 times). The latest ones are listed below; on the page you can filter them by 2-mark or long questions, topic and repeats.

Unit 1 previous year questions

  • Define model in machine learning. (2 marks, 2026, Introduction to Machine Learning)
  • What is the difference between linear regression and logistic regression? (2 marks, 2026, Linear Models (SVM, Perceptron, Logistic Regression))
  • Derive the mathematical expression for the output of a single hidden-layer neural network. Explain the role of activation functions. (7 marks, 2026, Neural Networks & Shallow Networks)
  • Explain the backpropagation algorithm in detail. Derive the weight update rule for a multilayer perceptron. (7 marks, 2026, Training a Network (Loss, Backprop, SGD))
  • Discuss the significance of activation functions in the Universal Approximation Theorem. (7 marks, 2026, Universal Function Approximation)
  • Discuss the differences between a perceptron and a support vector machine in terms of learning. (2 marks, 2025, Linear Models (SVM, Perceptron, Logistic Regression))
  • What is a loss function, and why is it essential for training a neural network? (2 marks, 2025, Training a Network (Loss, Backprop, SGD))
  • Discuss the differences between a perceptron and a support vector machine in terms of decision boundary formation. (2 marks, 2025, Linear Models (SVM, Perceptron, Logistic Regression))
  • Discuss how the choice of a loss function affects model performance for a classification problem. (2 marks, 2025, Training a Network (Loss, Backprop, SGD))
  • Define and explain the role of a loss function in neural networks. (2 marks, 2025, Training a Network (Loss, Backprop, SGD))
  • What is stochastic gradient descent? (2 marks, 2025, Training a Network (Loss, Backprop, SGD))
  • Derive the gradient of the logistic regression loss function with respect to its parameters. How does regularization impact its optimization process? (10 marks, 2025, Training a Network (Loss, Backprop, SGD))

Most asked Unit 1 topics

  • Training a Network (Loss, Backprop, SGD) – asked 10 times
  • Linear Models (SVM, Perceptron, Logistic Regression) – asked 8 times
  • Neural Networks & Shallow Networks – asked 5 times

Unit 1 question pattern

  • 2-mark questions: 13 asked in 2023–2026
  • 7-mark questions: 3 asked in 2023–2026
  • 10-mark questions: 11 asked in 2023–2026
  • About 30 marks from Unit 1 in every paper

Unit 1 questions year by year

  • 2026: 5 Unit 1 questions asked (25 marks across that year's papers)
  • 2025: 15 Unit 1 questions asked (102 marks across that year's papers)
  • 2023: 7 Unit 1 questions asked (30 marks across that year's papers)