AKTU · B.Tech · Important questions
AKTU Machine Learning Techniques Important Questions
The questions AKTU asks again and again in Machine Learning Techniques, found by comparing every question in 10 previous year papers from 2020-21 to 2025-26 (subject codes BCDS062, BCS055, KAI601, KCS055).
How this list is made: we compared all 238 questions in these papers and grouped the ones that ask about the same thing. Each item shows how many papers it appeared in, which years, and other ways it was worded. Topics that come back often are a strong hint, not a guarantee, so study your full syllabus too.
Most repeated long questions
From Sections B and C (7 or 10 marks, depending on the year). Unit numbers come from Section C, where each question covers one unit.
- Describe the reinforcement learning in detail with suitable examples.
- Explain the various learning models for reinforcement learning.
- Explain the Q-learning algorithm and its role in Reinforcement Learning.
- Explain various types of reinforcement learning techniques with suitable examples.
- Compare regression, classification and clustering in machine learning along with suitable real-life applications.
- Explain Naïve Bayes classifier with an example.
- Compare Naïve Bayes classifier and Bayesian belief networks.
- Explain the working of Naïve Bayes Classifier with assumptions.
- Differentiate between Naïve Bayes classifier and Bayesian belief networks. Give an application of Bayesian belief networks.
- Derive the Backpropagation algorithm for training neural networks.
- Derive the Backpropagation Algorithm for Multilayer Neural Networks.
- Explain the fundamental concepts behind the Backpropagation Algorithm and its 10 importance in training neural networks.
- Describe Markov Decision Process in reinforcement learning.
- Explain Q-Learning algorithm and Markov Decision Process.
- Explain Reinforcement Learning with Markov Decision Process.
- Explain supervised and unsupervised learning techniques.
- Compare Supervised and Unsupervised Learning Techniques with examples.
- Explain the concept of Reinforcement Learning (RL). Discuss how it differs from supervised and unsupervised learning.
- Compare and contrast supervised, unsupervised, and reinforcement learning. Provide examples where each type is applicable.
- Demonstrate K-Nearest Neighbors algorithm for classification with the help of an example.
- Describe the EM Algorithm with suitable example.
- Write a short note on the following: i. EM algorithm ii. Generalization
- Discuss Decision Tree and explain its working in detail.
- Discuss Information Gain and its role in Decision Tree Learning.
- Discuss linear regression and logistic regression in detail.
- Describe Linear Regression and Logistic Regression with differences.
- Explain CNN architecture and different types of layers.
- Discuss the concept of CNN architecture. Explain the role of different layers such as convolution, pooling, activation, and fully connected layers.
- Explain Genetic Algorithm cycle with suitable example.
- Describe Genetic Algorithm cycle including crossover and mutation.
- Explain ID3 Algorithm with an example.
- Explain the ID3 algorithm for Decision Tree learning.
- Explain Instance based learning. Compare locally weighted regression and radial basis function networks.
- What is instance based learning? How Locally Weighted Regression is different from Radial basis function networks?
- Explain hyperplane (decision boundary) in SVM. Categorize various popular kernels associated with SVM.
- Explain the GA cycle of reproduction with a neat diagram.
- Critically analyze the trade-offs between exploration and exploitation in the GA cycle of 10 reproduction.
- Explain the architecture and functioning of Convolutional Neural Networks (CNNs).
- Describe the role of Convolutional Neural Networks (CNNs), in diagnosing Diabetic 10 Retinopathy.
- Explain the different layers used in convolutional neural network with suitable examples.
- Explain the “Concept Learning” Task Giving an example
- Explain types of kernels used in Support Vector Machines.
- Discuss the properties and issues of Support Vector Machines.
- How is Bayes theorem used in machine learning? How naive Bayes algorithm is different from Bayes theorem?
- Discuss the role of Bayes theorem in machine learning. How naive Bayes algorithm is different from Bayes theorem?
- Illustrate backpropagation algorithm by assuming the training rules for output unit weights and Hidden Unit weights.
- What is Maximum Likelihood and Least Squared Error Hypothesis?
- Explain Maximum Likelihood and Least Squared Error Hypothesis with example.
- Write short notes on Probably Approximately Correct (PAC) learning model.
Most repeated short questions (2 marks)
From Section A. Learn a crisp definition plus one example or line of explanation for each.
- Define Machine Learning.
- Discuss the issues in machine learning.
- Explain the concept of machine learning.
- Define Machine Learning and list its different types.
- Discuss support vectors in SVM.
- What is a well-defined learning problem?
- Explain the concept of well-defined learning problem with suitable example.
- What constitutes a well-defined learning problem in machine learning? Give an example.
- What is gradient descent delta rule?
- Define Delta Rule .
- Compare ANN and Bayesian network.
- Compare ANN and Bayesian networks.
- Comparison of purely analytical and purely inductive learning.
- Differentiate between Lazy and Eager Learning
- Differentiate between Q learning and Deep Learning.
- What is the difference between Q learning and deep Q learning?
- What is the difference between machine learning and deep learning?
- Differentiate between linear and logistic regression.
- What is the difference between linear and logistic regression?
- Discuss overfitting and underfitting situation in decision tree learning.
- Discuss reinforcement learning.
- Define Reinforcement Learning with one example.
- What is gradient descent?
- Differentiate between Gradient Descent and Stochastic Gradient Descent.
- What is inductive bias?
- What is the role of Inductive Bias in ANN?
Unit-wise questions from recent papers
Section C questions from the latest papers (2025-26 BCS055, 2025-26 BCDS062, 2024-25 BCS055), sorted by unit. Use these to practise one unit at a time.
Unit 1
- Explain various Machine Learning approaches such as ANN, Clustering, and Reinforcement Learning. (2025-26, BCDS062)
- Discuss issues in Machine Learning and differentiate between Data Science and Machine Learning. (2025-26, BCDS062)
- Explain the ID3 algorithm for Decision Tree learning. (2025-26, BCS055)
- Discuss inductive bias and inductive inference in decision trees. (2025-26, BCS055)
- Discuss the history of machine learning. Highlight major milestones and advancements in the field. (2024-25, BCS055)
- Compare and contrast supervised, unsupervised, and reinforcement learning. Provide examples where each type is applicable. (2024-25, BCS055)
Unit 2
- Explain Bayes Optimal Classifier and Bayesian Belief Networks. (2025-26, BCDS062)
- Describe the EM Algorithm with suitable example. (2025-26, BCDS062)
- Explain perceptron and multilayer perceptron with neat diagram. (2025-26, BCS055)
- Derive the Backpropagation algorithm for training neural networks. (2025-26, BCS055)
- Consider the following weather data to determine whether or not a person will play tennis on a given day based on weather conditions: Day Outlook Temperature Humidity Wind Play Tennis? 1 Sunny Hot High Weak No 2 Overcast Hot High Weak Yes 3 Rainy Cool Normal Weak No 4 Overcast Cool Normal Strong Yes 5 Rainy Mild Normal Weak Yes 6 Sunny Mild Normal Strong No 7 Overcast Mild High Strong Yes 8 Overcast Hot Normal Weak No Apply Naïve Bayes Classifier to predict whether the person will play or not play tennis on given condition {Outlook = Sunny, Temperature = Cool, Humidity = High, Wind = Strong} (2024-25, BCS055)
- Fit a linear regression model for the dataset ( 𝑥 , 𝑦ሻ : (1, 1.5), (2, 3.0), (3, 4.5), (4, 6.0) and predict 𝑦 for 𝑥 = 5. (2024-25, BCS055)
Unit 3
- Explain ID3 Algorithm with an example. (2025-26, BCDS062)
- Discuss k-Nearest Neighbor and Locally Weighted Regression. (2025-26, BCDS062)
- Explain the architecture of Convolutional Neural Networks (CNN). (2025-26, BCS055)
- Discuss applications of Deep Learning with suitable case studies. (2025-26, BCS055)
- Describe the concept of locally weighted regression (LWR). How does it differ from traditional regression models, and what are its practical applications? (2024-25, BCS055)
- Given the following dataset with two attributes (A and B), and a target variable (T): A 1 2 1 2 1 2 B 2 3 3 2 2 3 T Yes No Yes No Yes No Calculate the entropy before the split and after the split on attribute A. Which attribute (A or B) gives the highest information gain? (2024-25, BCS055)
Unit 4
- Derive the Backpropagation Algorithm for Multilayer Neural Networks. (2025-26, BCDS062)
- Explain CNN architecture and different types of layers. (2025-26, BCDS062)
- Explain Reinforcement Learning with Markov Decision Process. (2025-26, BCS055)
- Describe Q-Learning algorithm and its applications. (2025-26, BCS055)
- Derive the mathematical steps involved in backpropagation for training a neural network. (2024-25, BCS055)
- Explain the architecture and functioning of Convolutional Neural Networks (CNNs). (2024-25, BCS055)
Unit 5
- Explain Q-Learning algorithm and Markov Decision Process. (2025-26, BCDS062)
- Describe Genetic Algorithm cycle including crossover and mutation. (2025-26, BCDS062)
- Explain Genetic Algorithm cycle with suitable example. (2025-26, BCS055)
- Analyze the role of crossover and mutation in Genetic Algorithms. (2025-26, BCS055)
- Explain the concept of Reinforcement Learning (RL). Discuss how it differs from supervised and unsupervised learning. (2024-25, BCS055)
- Explain the components of a genetic algorithm. Discuss the role of chromosomes, genes, and the population in the GA cycle. (2024-25, BCS055)
Papers used for this list
- AKTU Machine Learning Techniques (BCDS062) question paper 2025-26
- AKTU Machine Learning Techniques (BCS055) question paper 2025-26
- AKTU Machine Learning Techniques (BCDS062) question paper 2024-25
- AKTU Machine Learning Techniques (BCS055) question paper 2024-25
- AKTU Machine Learning Techniques (KAI601) question paper 2023-24
- AKTU Machine Learning Techniques (KCS055) question paper 2023-24
- AKTU Machine Learning Techniques (KAI601) question paper 2022-23
- AKTU Machine Learning Techniques (KCS055) question paper 2022-23
- AKTU Machine Learning Techniques (KCS055) question paper 2021-22
- AKTU Machine Learning Techniques (KCS055) question paper 2020-21
How to use these questions
- Start with the questions asked in the most papers, and make short notes for each.
- Write 2–3 long answers by hand with a timer (about 12–15 minutes each), then compare them with your textbook.
- Revise all the 2-mark questions the night before the exam.
- Finish with one full paper from the list above, timed.
Full plan with AI prompts: How to prepare for AKTU exams using previous year papers. After results, check your marks with the AKTU CGPA calculator.
Frequently asked questions
Are these AKTU Machine Learning Techniques questions guaranteed to come in the exam?
No. They are the questions that repeated most in past papers, which makes them a strong hint, but AKTU can ask anything from the syllabus. Use this list to prioritise, not to skip units.
How was this important questions list made?
We compared all 238 questions from 10 AKTU Machine Learning Techniques papers (2020-21 to 2025-26) and grouped questions that ask about the same topic, then counted how many papers each appeared in.
Where can I download AKTU Machine Learning Techniques previous year papers?
Every paper used here is on LearnAIFast with all questions as text and a link to the original PDF. See the list of papers above.
More subjects: all AKTU important questions · all question papers