K2infocom — Modern Learning Platform

Question Set

All 80 Questions

Read through the questions below or download the full PDF instantly — free of charge.

🧠

Section 1 — AI Fundamentals

Questions 1–10

10 Qs

01What is Artificial Intelligence and how does it differ from human intelligence?Basic

02Explain the difference between Narrow AI, General AI, and Super AI with examples.Basic

03What are the main branches of AI? Briefly describe each.Basic

04What is the Turing Test and what are its limitations?Medium

05Explain the concept of an intelligent agent and its components (PEAS framework).Medium

06What is the difference between supervised, unsupervised, and reinforcement learning?Basic

07How does Machine Learning differ from traditional rule-based programming?Basic

08What is a knowledge base and how is it used in expert systems?Medium

09Describe the search problem in AI. What is BFS vs DFS in the context of state space?Medium

10What are ethical concerns in AI — bias, fairness, and explainability?Advanced

📊

Section 2 — ML Algorithms

Questions 11–25

15 Qs

11What is Linear Regression? How do you interpret its coefficients?Basic

12Explain Logistic Regression and when you would use it over Linear Regression.Basic

13What is the Bias-Variance Tradeoff? How does it affect model performance?Medium

14Explain the Decision Tree algorithm. How does it choose the best split?Medium

15What is Random Forest? How does it improve over a single Decision Tree?Medium

16Explain the K-Nearest Neighbours algorithm and its pros/cons.Basic

17What is the Support Vector Machine (SVM)? Explain the concept of the hyperplane and margin.Medium

18What are kernel functions in SVM? Name common kernels and when to use them.Advanced

19Explain the Naïve Bayes classifier and the concept of conditional independence.Medium

20What is K-Means Clustering? How does the algorithm converge?Basic

21What is the difference between Bagging and Boosting? Give examples of algorithms for each.Medium

22Explain the XGBoost algorithm. What makes it faster than traditional Gradient Boosting?Advanced

23What is Principal Component Analysis (PCA)? When is it used?Medium

24What is regularization? Explain L1 (Lasso) vs L2 (Ridge) regularization.Medium

25What is the Expectation-Maximisation (EM) algorithm and how does it relate to GMMs?Advanced

🔗

Section 3 — Deep Learning

Questions 26–37

12 Qs

26What is a Neural Network? Describe the role of an activation function.Basic

27Explain Forward Propagation and Backpropagation in a neural network.Medium

28What is Gradient Descent? Compare SGD, Mini-Batch GD, and Batch GD.Medium

29What is a Convolutional Neural Network (CNN)? Explain convolution, pooling, and fully connected layers.Medium

30What is Transfer Learning? Give examples of pre-trained models and when to use them.Medium

31Explain RNNs and the problem of vanishing gradient. How do LSTMs solve it?Advanced

32What is Dropout? How does it prevent overfitting in deep networks?Medium

33What is Batch Normalization and why is it important in deep learning?Medium

34Explain the Transformer architecture — self-attention, multi-head attention, positional encoding.Advanced

35What are GANs (Generative Adversarial Networks)? Describe the Generator and Discriminator roles.Advanced

36What are common weight initialisation strategies and why do they matter?Medium

37What is an Autoencoder? How is it used for anomaly detection?Advanced

💬

Section 4 — Natural Language Processing

Questions 38–47

10 Qs

38What is tokenisation? Explain word-level vs subword tokenisation (BPE, WordPiece).Medium

39What is TF-IDF? How is it used to represent text numerically?Basic

40What is Word2Vec? Explain the CBOW and Skip-gram approaches.Medium

41What is Named Entity Recognition (NER) and what are its real-world applications?Basic

42Explain Sentiment Analysis. What models can be used for it?Basic

43What is BERT and how does it differ from GPT in training objectives?Advanced

44What is attention mechanism in NLP? How does self-attention work?Advanced

45What are Large Language Models (LLMs)? How are they trained (pre-training + fine-tuning)?Advanced

46What is text summarisation? Differentiate extractive vs abstractive approaches.Medium

47What is machine translation? How have Transformer models changed this field?Medium

👁️

Section 5 — Computer Vision

Questions 48–55

8 Qs

48What is image classification and how is it different from object detection?Basic

49What is data augmentation in computer vision? Give 5 examples of augmentation techniques.Basic

50Explain the YOLO (You Only Look Once) algorithm for real-time object detection.Medium

51What is image segmentation? Differentiate semantic vs instance segmentation.Medium

52What is the role of pooling layers in CNNs? Max Pooling vs Average Pooling?Basic

53Explain the ResNet (Residual Network) architecture and the concept of skip connections.Advanced

54What is Optical Character Recognition (OCR) and how do neural networks improve it?Medium

55What is the Vision Transformer (ViT) and how does it apply Transformer concepts to images?Advanced

📈

Section 6 — Model Evaluation & Metrics

Questions 56–65

10 Qs

56What is a Confusion Matrix? Define Accuracy, Precision, Recall, and F1-Score.Basic

57When would you prefer Recall over Precision? Give a real-world scenario.Medium

58What is the ROC curve and AUC? What does an AUC of 0.5 vs 1.0 mean?Medium

59What is Cross-Validation? Explain k-fold cross-validation and stratified k-fold.Medium

60What is overfitting and underfitting? How do you detect and fix each?Basic

61What is RMSE (Root Mean Square Error) and when is it more useful than MAE?Basic

62What is the Log-Loss metric and when is it used?Medium

63What is Hyperparameter Tuning? Explain Grid Search vs Random Search vs Bayesian Optimisation.Advanced

64How do you handle class imbalance in a dataset? (SMOTE, class weights, etc.)Medium

65What is the BLEU score and where is it commonly applied?Medium

🛠️

Section 7 — Feature Engineering

Questions 66–73

8 Qs

66What is Feature Engineering and why is it important in ML pipelines?Basic

67How do you handle missing values in a dataset? Discuss different strategies.Basic

68What is one-hot encoding and label encoding? When should you use each?Basic

69Explain Feature Scaling — Min-Max Normalisation vs Standardisation (Z-score).Medium

70What is feature selection? Compare filter, wrapper, and embedded methods.Medium

71What is multicollinearity and how does it affect regression models?Medium

72How do you detect and handle outliers in a dataset?Medium

73What is dimensionality reduction and what problems does it solve?Medium

☁️

Section 8 — MLOps & Model Deployment

Questions 74–80

7 Qs

74What is MLOps and why is it important for production machine learning systems?Basic

75What is model drift? Explain data drift vs concept drift and how to monitor for them.Medium

76How would you deploy an ML model as a REST API? Describe the end-to-end process.Medium

77What is model versioning and experiment tracking? Name tools used for this.Medium

78What is Docker and Kubernetes? How are they used in deploying ML models at scale?Advanced

79What is A/B testing in the context of machine learning? How do you validate a new model in production?Advanced

80What are CI/CD pipelines in ML? How do they differ from traditional software CI/CD?Advanced

📥

Want the full PDF with all 80 questions?

Download for free — perfectly formatted for print & study.

AI / ML
Question Set

8 Key AI / ML Areas

All 80 Questions

Section 1 — AI Fundamentals

Section 2 — ML Algorithms

Section 3 — Deep Learning

Section 4 — Natural Language Processing

Section 5 — Computer Vision

Section 6 — Model Evaluation & Metrics

Section 7 — Feature Engineering

Section 8 — MLOps & Model Deployment

Want the full PDF with all 80 questions?

Explore Other Sets

Get the AI / ML PDF — Free

AI / ML Question Set

8 Key AI / ML Areas

All 80 Questions

Section 1 — AI Fundamentals

Section 2 — ML Algorithms

Section 3 — Deep Learning

Section 4 — Natural Language Processing

Section 5 — Computer Vision

Section 6 — Model Evaluation & Metrics

Section 7 — Feature Engineering

Section 8 — MLOps & Model Deployment

Want the full PDF with all 80 questions?

Explore Other Sets

Get the AI / ML PDF — Free

AI / ML
Question Set