Unit 1: Foundations & Applications of AI; AI Problem Modeling & Search Concepts - Practice Quiz

1 Which of the following best describes intelligence in a general sense?

2 What does the abbreviation AI stand for?

3 Artificial Intelligence primarily aims to enable machines to do which of the following?

4 Which of the following is a key characteristic of an AI system?

5 Which discipline contributes the study of learning and reasoning in humans as a foundation of AI?

6 Which field provides the logic and computation foundations for AI?

7 An AI system designed to perform only one specific task, such as recognizing faces, is called:

8 Which type of AI would be able to perform any intellectual task a human can do?

9 Which of the following is a common AI technique used for learning patterns from data?

10 Using AI to detect diseases from medical X-ray images is an application in which domain?

11 A chatbot that understands and responds to customer text messages uses which area of AI?

12 Enabling a computer to identify objects in a photograph is a task belonging to which AI field?

13 Which of the following is a popular open-source deep learning framework developed by Google?

14 PyTorch is primarily used for which of the following purposes?

15 Which of the following is a key principle of Responsible AI?

16 The ability to explain how an AI system reaches its decisions is known as:

17 In a state space representation, the initial state refers to:

18 In search problems, an operator (or action) is used to:

19 Which of the following is a common characteristic of AI problem spaces?

20 Which of the following is a common challenge in AI problem solving?

21 A robot adjusts its cleaning path after detecting a new obstacle it has never encountered before. Which aspect of intelligence does this behavior most directly demonstrate?

22 A system that perceives its environment and takes actions to maximize its chance of achieving a goal is best described as which of the following?

23 An AI email filter improves its spam detection accuracy as more emails are labeled by users. Which characteristic of AI does this illustrate?

24 Which discipline primarily contributes the concepts of probability and decision-making under uncertainty to the foundations of AI?

25 The period during which funding and interest in AI sharply declined due to unmet expectations is commonly referred to as which of the following?

26 A chess engine that plays world-class chess but cannot perform any other task is an example of which type of AI?

27 Which statement best distinguishes General AI from Narrow AI?

28 A bank wants to predict whether a loan applicant will default (yes/no). Which type of machine learning problem is this?

29 Grouping customers into segments without any predefined labels is best solved using which technique?

30 A hospital system that analyzes medical images to flag potential tumors is applying AI primarily in which subfield?

31 A virtual assistant that understands typed customer questions and generates relevant text replies primarily uses which AI capability?

32 Which statement about TensorFlow and PyTorch is most accurate?

33 PyTorch is often preferred by researchers largely because of which feature?

34 A hiring model consistently rejects qualified candidates from a specific demographic group. This is primarily an example of which Responsible AI concern?

35 Which practice most directly supports the 'transparency' principle of Responsible AI?

36 In formulating a puzzle as a search problem, what does the 'state' typically represent?

37 In the 8-puzzle, moving a tile into the blank space corresponds to which element of a search problem?

38 A problem where the outcome of an action is not guaranteed and may vary is best described as having which characteristic?

39 In a data-centric AI approach, improving model performance is achieved primarily by which of the following?

40 A model performs excellently on training data but poorly on unseen data. This challenge is known as which of the following?

41 For the 8-puzzle, which formulation correctly bounds the reachable state space and explains why?

42 A problem space is described as decomposable, ignorable, and having predictable outcomes. Which combination of consequences is correct?

43 A system defeats world champions at Go, protein folding, and chess using the same core algorithm retrained per task, but cannot transfer knowledge between them without retraining. How is it best classified?

44 In A* search, an admissible heuristic dominates (i.e., for all , both admissible). What is guaranteed?

45 A researcher needs fine-grained control over the computation graph, dynamic control flow that changes per input (e.g., variable-length recursion), and easy Python-native debugging. Historically, which characteristic distinguished PyTorch's approach?

46 A hiring model achieves equal false positive rates across groups but unequal positive predictive value. This illustrates which fundamental result?

47 Which pairing of a founding discipline with its specific contribution to AI is most accurate?

48 In a data-centric (as opposed to model-centric) paradigm, a team observes plateaued accuracy. Which intervention aligns with the data-centric philosophy?

49 A model performs excellently on validation data drawn from the same distribution but fails in deployment months later. This is best characterized as which challenge?

50 An agent maintains internal state, learns from experience, and selects actions to maximize a performance measure under uncertainty. Which characteristic set does this most precisely reflect?

51 A diagnostic imaging model reports 99% accuracy on a dataset where 99% of patients are healthy. Why is this metric misleading, and what is preferable?

52 Hill climbing repeatedly gets stuck on the same non-optimal peak for a given problem. Which strategy most directly addresses the cause rather than a symptom?

53 The Turing Test is often cited as a definition of AI. Which critique most precisely captures its central limitation as a definition of intelligence?

54 A search problem is defined by initial state, actions, transition model, goal test, and path cost. If path costs vary and we need optimality, which uninformed algorithm is appropriate and why?

55 The 'AI winters' of the 1970s and late 1980s are best explained by which combination of causes?

56 Consider a problem that is not decomposable, has irrecoverable steps, and unpredictable outcomes. Which real-world task best matches all three properties?

57 A team must deploy a trained model to low-latency mobile and embedded devices with quantization support. Which TensorFlow component is designed for this purpose?

58 Explainability techniques like SHAP and LIME are applied to a black-box model. Which statement is the most accurate caveat?

59 Under the rational agent framing versus the human-like framing of intelligence, which distinction is most precise?

60 The 'combinatorial explosion' in search-based problem solving refers to which specific difficulty, and which technique most directly mitigates it?