Back to Subject
View Notes Subjective

Unit 1 - Practice Quiz

INT428

1 Which of the following best defines Artificial Intelligence in its broadest sense?

A. The ability of a robot to move physically.
B. The simulation of human intelligence processes by machines, especially computer systems.
C. A database management system that stores large amounts of data.
D. A hardware component that increases processing speed.

2 Which test, proposed in 1950, is designed to determine a machine's ability to exhibit intelligent behavior equivalent to, or indistinguishable from, that of a human?

A. The Lovelace Test
B. The Turing Test
C. The Chinese Room Argument
D. The McCarthy Protocol

3 Which of the following is considered a foundational discipline contributing to the development of AI?

A. Philosophy
B. Mathematics
C. Neuroscience
D. All of the above

4 What is the primary characteristic of Narrow AI (ANI)?

A. It possesses consciousness and self-awareness.
B. It can perform any intellectual task that a human being can do.
C. It is designed and trained for a specific task.
D. It can evolve its own code without human intervention to become superintelligent.

5 The historic conference generally recognized as the birthplace of Artificial Intelligence as a field occurred in 1956 at:

A. MIT
B. Stanford University
C. Dartmouth College
D. Bletchley Park

6 Periods in AI history characterized by reduced funding and interest due to unmet expectations are known as:

A. AI Summers
B. AI Winters
C. The Singularity
D. The Dark Ages

7 Which type of AI theoretical capability refers to a machine with the ability to understand, learn, and apply knowledge across a wide variety of tasks, similar to a human?

A. Artificial Narrow Intelligence (ANI)
B. Artificial General Intelligence (AGI)
C. Reactive Machines
D. Expert Systems

8 In the context of AI applications, what does NLP stand for?

A. Neural Language Programming
B. Natural Language Processing
C. Network Logic Protocol
D. Natural Learning Process

9 Which modern AI toolkit, developed by Google, is widely used for building deep learning models?

A. PyTorch
B. TensorFlow
C. Scikit-learn
D. OpenCV

10 PyTorch is a popular deep learning framework primarily developed by:

A. Google
B. Microsoft
C. Meta (Facebook) AI Research
D. IBM

11 Which of the following is a key component of Responsible AI?

A. Maximizing processing speed at all costs
B. Ensuring fairness and mitigating bias
C. Hiding the decision-making process from users
D. Using unverified data sources

12 In AI Problem Solving, a problem is often formally defined by:

A. A database schema and SQL queries.
B. A state space, an initial state, a goal state, and operators.
C. A set of IF-THEN rules only.
D. The hardware architecture of the GPU.

13 The set of all possible states reachable from the initial state by any sequence of actions is called the:

A. Search Tree
B. State Space
C. Solution Path
D. Heuristic Map

14 In an AI search problem, the Path Cost is:

A. The computational time required to find the solution.
B. The amount of memory used by the algorithm.
C. A numerical value associated with a path, usually the sum of step costs.
D. The number of nodes expanded during the search.

15 An environment where the agent's sensors give it access to the complete state of the environment at each point in time is called:

A. Partially Observable
B. Fully Observable
C. Stochastic
D. Dynamic

16 If the next state of the environment is completely determined by the current state and the action executed by the agent, the environment is:

A. Stochastic
B. Deterministic
C. Episodic
D. Continuous

17 Chess is an example of which type of environment?

A. Stochastic, Single-agent
B. Deterministic, Multi-agent
C. Continuous, Multi-agent
D. Partially Observable, Single-agent

18 What is the primary goal of Computer Vision?

A. To generate human-like speech.
B. To enable computers to interpret and understand the visual world.
C. To optimize database search queries.
D. To create physical robots that can walk.

19 In the context of AI workflows, Data Preprocessing involves:

A. Designing the neural network architecture.
B. Cleaning, normalizing, and transforming raw data into a usable format.
C. Deploying the model to a production server.
D. Selling the data to third-party vendors.

20 Which of the following is a specific application of AI in the Healthcare domain?

A. High-frequency trading algorithms
B. Predictive maintenance for manufacturing
C. Early detection of diseases via medical imaging analysis
D. Spam filtering in email

21 A generic search algorithm that explores the search space without any domain-specific knowledge (heuristics) is called:

A. Informed Search
B. Uninformed (Blind) Search
C. Adversarial Search
D. Reinforcement Learning

22 In A* search, the cost function is defined as . What does represent?

A. The actual cost from the start node to node .
B. The estimated cost from node to the goal.
C. The total path cost found so far.
D. The number of nodes visited.

23 Which of the following describes a Data-Centric AI approach?

A. Holding the data fixed and iteratively improving the model architecture.
B. Systematically engineering the data to improve quality while keeping the model relatively fixed.
C. Using the smallest possible dataset to save storage.
D. Avoiding the use of labeled data entirely.

24 What is the Curse of Dimensionality in AI problem solving?

A. The fear that AI will take over the world.
B. The difficulty of solving problems as the number of features (dimensions) increases, leading to sparse data.
C. The limitation of 2D screens to represent 3D objects.
D. The cost of buying high-dimensional storage.

25 Which search algorithm uses a LIFO (Last In, First Out) stack data structure?

A. Breadth-First Search (BFS)
B. Depth-First Search (DFS)
C. Uniform Cost Search
D. A* Search

26 Breadth-First Search (BFS) is guaranteed to find the shortest path in terms of number of steps if:

A. The state space is infinite.
B. The step costs are all equal (e.g., 1).
C. The heuristic function is admissible.
D. The branching factor is 1.

27 What is an Agent in AI?

A. A secret service operative.
B. Anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators.
C. The database administrator controlling the AI.
D. The algorithm used to sort data.

28 Which of the following is an example of a Discrete state space?

A. Driving a car (steering angle, speed).
B. The game of Tic-Tac-Toe.
C. Throwing a ball (trajectory).
D. Temperature control in a room.

29 In the context of AI Evolution, what was the main limitation of early Expert Systems?

A. They were too fast for humans to understand.
B. They were brittle and could not handle uncertainty or situations outside their hard-coded rules.
C. They required GPUs which didn't exist.
D. They were based on neural networks.

30 Which AI technique tries to mimic the structure and function of the human brain?

A. Decision Trees
B. Artificial Neural Networks (ANNs)
C. Genetic Algorithms
D. Support Vector Machines

31 What is Overfitting in AI modeling?

A. When a model learns the training data too well, capturing noise and failing to generalize to new data.
B. When a model is too simple to capture the underlying pattern of the data.
C. When the dataset is too small for the model.
D. When the learning rate is set too high.

32 Which domain application utilizes AI for Fraud Detection?

A. Agriculture
B. Finance and Banking
C. Entertainment
D. Construction

33 The 8-Puzzle is often used in AI education to demonstrate:

A. Natural Language Processing
B. Computer Vision
C. State Space Search algorithms
D. Robotic locomotion

34 Which of the following describes a Stochastic environment?

A. The outcome of an action is completely predictable.
B. There is uncertainty associated with the outcome of an action (e.g., rolling dice).
C. The environment does not change while the agent is deliberating.
D. The agent is the only entity acting in the environment.

35 What is the purpose of a Validation Set in an AI workflow?

A. To train the model parameters.
B. To tune hyperparameters and evaluate the model during development.
C. To provide a final unbiased evaluation of the model.
D. To storing the raw data.

36 In the context of Explainable AI (XAI), the 'Black Box' problem refers to:

A. The physical casing of the AI server.
B. The inability to understand how complex models (like Deep Learning) arrive at a specific decision.
C. A flight recorder in autonomous planes.
D. The proprietary nature of AI software.

37 Which famous AI system defeated the world champion in the game of Go in 2016?

A. Deep Blue
B. Watson
C. AlphaGo
D. ChatGPT

38 What is a Heuristic in AI search?

A. A rule of thumb or strategy that guides the search to likely solutions, reducing search time.
B. A guaranteed algorithm that checks every possible state.
C. A type of hardware accelerator.
D. A database of past solutions.

39 Which category of AI deals with the physical interaction of machines with the world (sensors and effectors)?

A. Robotics
B. Expert Systems
C. Data Mining
D. Cloud Computing

40 In a Dynamic environment:

A. The environment can change while the agent is deliberating.
B. The environment only changes when the agent acts.
C. The environment is static and unchanging.
D. Time is not a factor.

41 The concept of Singularity in AI refers to:

A. A single line of code that solves all problems.
B. A hypothetical point in time when AI growth becomes uncontrollable and irreversible, resulting in powerful superintelligence.
C. The use of a single GPU for training.
D. An error in a mathematical calculation.

42 Which of the following is NOT a typical step in a modern AI workflow?

A. Data Collection
B. Model Training
C. Manual Calculation of weights by hand
D. Model Deployment

43 An algorithm is said to be Complete if:

A. It always finds a solution if one exists.
B. It finds the lowest cost solution.
C. It uses the least amount of memory.
D. It finishes in under 1 second.

44 The Branching Factor in a search tree refers to:

A. The depth of the tree.
B. The average number of successors (children) of a node.
C. The cost of the path.
D. The number of goal states.

45 Which Python library is widely used for data manipulation and analysis, forming the backbone of data-centric AI tasks?

A. Pandas
B. Flask
C. PyGame
D. React

46 What is the primary difference between Classification and Regression?

A. Classification predicts continuous values; Regression predicts discrete labels.
B. Classification predicts discrete labels/categories; Regression predicts continuous numerical values.
C. Classification uses images; Regression uses text.
D. There is no difference.

47 An AI system that recommends products on Amazon based on your browsing history is an example of:

A. Recommendation Engine
B. Robotic Process Automation
C. General AI
D. Computer Vision

48 In the state space graph, a Cycle (or loop) can cause:

A. The search algorithm to finish instantly.
B. The search algorithm to get stuck in an infinite loop (if not handled).
C. The heuristic to become admissible.
D. The graph to become a tree.

49 Weak AI is another term for:

A. Artificial General Intelligence
B. Artificial Narrow Intelligence
C. Superintelligence
D. Cognitive Computing

50 Which of the following is a challenge related to Data Bias?

A. The model runs too slowly.
B. The model consumes too much electricity.
C. The model makes unfair decisions based on historical prejudices present in the training data.
D. The model cannot process images.