Over 50 Multiple Choice Questions with Answers on Artificial Intelligence

Understanding Artificial Intelligence

Artificial Intelligence (AI) is a rapidly growing field in computer science, revolutionizing industries by creating intelligent machines. It is omnipresent in today's world and has applications ranging from chess-playing computers to self-driving cars. The ultimate objective of AI is to create machines that can think and make decisions like humans, based on certain factors.

The meaning of "Artificial Intelligence" is derived from the words "Artificial" meaning man-made and "Intelligence" meaning the power to think. Therefore, AI is a machine that can think like humans, creating a "man-made thinking machine."

The key goals of AI are as follows:

  • Solve knowledge-intensive tasks
  • Replicate human intelligence to make meaningful decisions
  • Build a machine that can perform tasks that require human intelligence
  • Create a machine that demonstrates intelligent behavior and can learn from previous experiences/data

In the field of AI, it's also essential to understand various concepts and terminologies. Test your knowledge with AI MCQs.

Identifying the "Father of Artificial Intelligence"

In the field of artificial intelligence, John McCarthy is recognized as the "Father of Artificial Intelligence".

He is among the pioneers of computer science who coined the term "artificial intelligence".

Usage of Blind Search

Blind Search algorithm is best suitable for a small search space where it does not requires any domain knowledge, unlike the Real-Life Simulation and Advanced Game Theory. Therefore, the correct answer is option B: Small Search Space.



Number of Categories Artificial Intelligence is Classified Into

Artificial Intelligence is classified into 3 categories: Sensing, Reasoning, and Acting.

Identifying Intelligent Machines

In the context of machinery, a machine that is capable of making autonomous decisions based on external factors is called an intelligent machine. Such machines are designed to evaluate their environment and make changes to their actions without needing human intervention. Therefore, the correct answer to the given question is option B - "Intelligent".


There is no code required for this task.

Common Language for Artificial Intelligence

Python has become the most commonly used language for Artificial Intelligence(AI) and Machine Learning(ML) tasks. Although programming can be performed in any language, Python's wide range of libraries and tools make it the preferred choice for AI-related development.

# Example of using some AI modules in Python
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

Application of Artificial Intelligence

Out of the given options, 'Database Management System' is not an application of artificial intelligence. However, 'Computer Vision', 'Natural Language Processing' and 'Digital Assistants' are all viable fields of study in Artificial Intelligence.

//Sample code for Computer Vision applied in creating object detection.

import cv2

# Load the trained Cascade Classifier 
faceCascadeClassifier = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')

# Read the image from local storage
img = cv2.imread('test_image.jpg')

# Converting the image into grayscale
grayImg = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Detecting faces in the image
faces = faceCascadeClassifier.detectMultiScale(grayImg, scaleFactor = 1.1, minNeighbors = 5)

# Looping over each detected face, putting a boundary box around them
for (x, y, w, h) in faces:
    cv2.rectangle(img, (x, y), (x+w, y+h), (255, 0, 0), 2)

# Displaying the image with detected faces
cv2.imshow('Detected Faces', img)

Proposition Symbols in AI

In Artificial Intelligence, the two proposition symbols are "true" and "false".


Hence, option D is the correct answer.

Identifying Logical Symbols in AI

In Artificial Intelligence, the following symbols are considered logical symbols: Negation, Conjunction, Disjunction, Implication, and Biconditional symbols. Therefore, the correct answer to the given question is option D: All of the above.

Identifying Informed Search Methods

All three options mentioned, i.e., Best First Search, A* Search, and Memory Bound Heuristic Search, are examples of informed search methods used in Artificial Intelligence.

// Example of using A* Search algorithm in Python

def astar_search(start, goal, heuristic_func):
    A* search algorithm.
    start: starting state
    goal: goal state
    heuristic_func: heuristic function to calculate the estimated cost of reaching the goal
    frontier = PriorityQueue()
    frontier.put(start, 0)
    came_from = {}
    cost_so_far = {}
    came_from[start] = None
    cost_so_far[start] = 0

    while not frontier.empty():
        current = frontier.get()

        if current == goal:

        for neighbor in get_neighbors(current):
            new_cost = cost_so_far[current] + cost_between(current, neighbor)
            if neighbor not in cost_so_far or new_cost < cost_so_far[neighbor]:
                cost_so_far[neighbor] = new_cost
                priority = new_cost + heuristic_func(goal, neighbor)
                frontier.put(neighbor, priority)
                came_from[neighbor] = current

    return came_from, cost_so_far

Artificial Intelligence System - Developed by Daniel Bobrow

In 1964, Daniel Bobrow created an Artificial Intelligence system named STUDENT. It was written in Lisp Language and it is considered one of the earliest AI-based systems.

Out of the given options, the correct answer is STUDENT.

Types of AI Agents

In the field of artificial intelligence, there exist several types of AI agents. The most common ones include:

  • Simple Reflex Agent
  • Model-Based Reflex Agent
  • Goal-Based Reflex Agent
  • Utility-Based Agent
  • Learning Agent

Therefore, the answer to the question is All of the above, as all 5 types of AI agents listed are valid.

Types of Recognition in AI

In AI, there are three main types of recognition:

1. Biometric Identification

This type of recognition involves the use of physical characteristics to identify individuals. Examples include fingerprint scans, retinal scans, and facial recognition technology.

2. Content-Based Image Retrieval

This type of recognition involves using image recognition technology to search and retrieve images similar to a given query image. It is often used in applications such as reverse image search engines.

3. Handwriting Recognition

This type of recognition involves converting handwritten text into digital text. It is often used in applications such as converting handwritten notes into digital text for easy storage and retrieval.

Procedural Domain Knowledge in a Rule-Based System

In a rule-based system, Procedural Domain Knowledge is represented in the form of Production Rules. It guides the system on how to take specific actions based on certain conditions or events. Meta-Rules and Control Rules are other types of rules that are used in rule-based systems but do not represent procedural knowledge.

Common Types of Approaches in Artificial Intelligence (AI)

Artificial Intelligence (AI) has been classified into various approaches depending on the nature and characteristics of the system being developed or the application of the technology. The following are common types of approaches in AI:

<p>1. Strong AI Approach: This is also referred to as Artificial General Intelligence (AGI). It involves building intelligent machines that can perform any intellectual task that a human can do.</p>

<p>2. Weak AI Approach: This approach focuses on building intelligent machines that can carry out specific tasks. It is also known as narrow AI or applied AI.</p>

<p>3. Applied AI Approach: This approach is focused on developing practical applications that can solve real-world problems.</p>

Hence, the correct answer is All of the above as all the given options are different types of AI approaches used in different scenarios.

Original Name of The Turing Test

Do you know what was the original name of The Turing Test?

The Turing Test was originally called 'The Imitation Game' by its creator.

Understanding the Systolic Array Architecture

In computer architecture, there are four main classifications of computer systems based on the number of processors they have and how they are connected. These classifications are SISD, SIMD, MIMD, and MISD. Among them, the MISD architecture is also known as systolic arrays.

To answer the given question, we can say that the correct option is D: None of the above, as MISD is the architecture that is also known as systolic arrays.

Algorithm Used in Game Trees to Make Win/Loss Decisions

In game trees, win/loss decisions are made using the Min/Max algorithm, which is preferred over other search-based algorithms like DFS, BFS, and heuristic search due to its optimality. The Min/Max algorithm helps in finding the optimal moves that a player can make in a game, considering all possible moves of the opponent. This algorithm reduces the number of computations required for decision-making and helps the player make optimal decisions that maximize their chances of winning the game.

Approaches for solving a problem of state-space search

There are two correct approaches for solving a problem of state-space search:

  1. Forward from the initial state
  2. Backward from the goal

Therefore, the correct answer is option (C) - Both A and B.

AI Workstations and LISP Machines

In the field of computer science, machines that run the programming language LISP are commonly referred to as AI workstations. This is because LISP is a language that was developed specifically for artificial intelligence research.

So the correct answer to the given question is: AI Workstations.

Interactions of AI Agent with its Environment

An AI agent interacts with its environment by perceiving it with the help of sensors it has and acting upon it using actuators. Thus, option A is the correct answer. The sensors help an AI agent to gather input data and information from its environment. This input data is then processed to make decisions about the actions the AI agent needs to take. Finally, these decisions are translated into physical actions by actuators to influence the environment around the AI agent.

Understanding the Work of Task Environments and Rational Agents

In the field of artificial intelligence, Task environments and Rational agents play crucial roles. The task environment refers to the problem that needs to be solved, while the rational agent refers to the corresponding solution for that problem.

Therefore, it can be said that the task environment and rational agents work together to provide a problem and its corresponding solution. In other words, the task environment provides an issue, and rational agents provide the necessary approach to solve that problem.

It is essential to understand the roles of task environments and rational agents while working on AI projects as they form the basis of problem-solving in the field.

Number of Observing Environments

There are two types of observing environments: fully and partial.

public enum ObservingEnvironment {

Types of Quantification in AI

In AI, there are two types of quantification, which are Universal and Existential.

Universal quantification refers to statements that are true for all possible values of a variable. It uses the quantifier "For all" or "For every".

Existential quantification refers to statements that are true for at least one value of a variable. It uses the quantifier "There exists" or "There is at least one".

Understanding these quantification types is important in solving problems related to logical reasoning, knowledge representation, and natural language processing in AI.

Algorithm Memory Usage Comparison

To determine which algorithm uses the least memory, we compare DFS and BFS:

  def DFS(node):
      if(not node):
  def BFS(node):
      queue = []
      while(len(queue) != 0):
          currNode = queue.pop(0)

From looking at the code, we can infer that DFS uses lesser memory than BFS since it only stores one path at a time in the memory stack while BFS has to store the entire tree. Therefore, the answer is DFS.

Field of AI for Machines Imitating Human Intuition

One area in the field of AI is dedicated to creating machines that can imitate human intuition when dealing with vague information. This field is known as Fuzzy Logic.

//Example of Fuzzy Logic implementation in code:

function calculateTip(serviceRating, foodQuality, atmosphere) {
  let tipPercentage = 0;
  if (serviceRating >= 8 && foodQuality >= 8) {
    tipPercentage = 0.20;
  } else if (serviceRating >= 7 || foodQuality >= 7) {
    tipPercentage = 0.15;
  } else if (atmosphere >= 7) {
    tipPercentage = 0.10;
  } else {
    tipPercentage = 0.05;
  return tipPercentage;

let myTip = calculateTip(8, 9, 6);
console.log("The recommended tip percentage is: " + (myTip * 100) + "%");

//This function uses fuzzy logic to calculate a recommended tip percentage based on various ratings.

Understanding Complete Algorithms

A complete algorithm refers to an algorithm that can find a solution to a given problem within a finite amount of time. The key characteristic of a complete algorithm is that it will always find a solution if one exists. This means that the algorithm will not get stuck in an infinite loop or return a failure to find a solution when one exists.

To be a complete algorithm, it needs to fulfill two conditions. First, it should always terminate or end its execution. Second, if a solution exists, the algorithm will find it before terminating. Thus, we can say that a complete algorithm is reliable and efficient. It provides a guaranteed solution within a reasonable amount of time.

In summary, a complete algorithm is the one that can solve a problem in finite time, with an assurance of finding a solution (if it exists).

Performance Measurement of AI Agent

In AI, the performance of an agent can be measured using a learning agent. The learning agent can improve its performance over time by recognizing patterns in data and adjusting its actions accordingly. This is a powerful tool for enhancing the capabilities of AI systems, as it allows them to adapt to changing environments and improve their decision-making abilities.

In contrast, a changing agent is not used to measure performance but rather refers to an agent that can modify its environment. Both A and B are incorrect as changing agent does not relate to measuring performance and there isn't any agent called the "performance agent". Therefore, the correct answer is "None of the above".


# This code shows how a learning agent can be used to measure the performance of an AI agent

class LearningAgent:
    def __init__(self):
        self.performance = 0
    def measure_performance(self, environment):
        # Analyze data and adjust actions accordingly
        self.performance += 1
        # Return the updated performance score
        return self.performance

# Example usage
ai_agent = AI_Agent()
learning_agent = LearningAgent()

# Run the AI agent in a simulated environment
for i in range(100):
    environment = simulate_environment()
    # Measure performance using the learning agent
    performance_score = learning_agent.measure_performance(environment)
# Print the final performance score
print("Final performance score:", performance_score)

The given code is used to demonstrate how the `LearningAgent` class can measure the performance of an AI agent. The `__init__` method initializes the performance to 0 and the `measure_performance` method measures the agent's performance and updates the score accordingly. The `AI_Agent` class and the `simulate_environment` function are not defined here, as they are beyond the scope of this demonstration. Finally, the `performance_score` variable contains the final performance score of the AI agent after running it in the simulated environment for 100 iterations.

Valid Machine Learning Algorithms

There are several valid Machine Learning algorithms, including:

  1. Linear Regression
  2. K-Means Clustering
  3. Naive Bayes

All of the above mentioned algorithms are considered to be valid Machine Learning algorithms.

Overview of Machine Learning Methods

In the field of machine learning, there are various methods that allow computers to learn from data and make predictions or decisions without being explicitly programmed. These methods are broadly classified into three categories: memorization, analogy, and deduction.

Memorization: This method involves storing data in a way that the computer can recall it later to make predictions. One popular example of this is the k-nearest neighbor algorithm, which makes predictions based on the closest data points in a given set.

Analogy: This method employs algorithms that can recognize patterns by comparing them with similar patterns in the dataset. An example of this is the support vector machine algorithm.

Deduction: This method involves using logical reasoning to make predictions. One popular example is the decision tree algorithm, which uses a series of if-then statements to categorize data.

Therefore, the correct answer is D. All of the above.

Exploratory Learning - What is it?

Exploratory learning refers to a type of machine learning algorithm that falls under the category of unsupervised learning. In unsupervised learning, the algorithm does not require any external supervision to learn. Instead, it explores and identifies the patterns and relationships present in the datasets on its own. Therefore, the correct answer to the given question is "Unsupervised learning".

Designing Learning Elements: Components, Feedback, and Representation

In order to create an effective learning element, there are three key factors that must be considered: components, feedback, and representation.

Components refer to the various pieces that make up the learning element, such as text, images, videos, or interactive exercises. Each component should be carefully chosen to ensure that it supports the learning objectives and engages the learner.

Feedback is an essential aspect of any learning element. Learners need to receive timely and constructive feedback in order to gauge their progress and adjust their learning approach as needed. This can be accomplished through quizzes, assessments, or other evaluation tools.

Representation refers to the way in which information is presented to the learner. This can include the design and layout of the learning element, as well as the language and tone used. Representations should be clear, concise, and easy to understand, in order to maximize the learner's understanding and retention of the material.

By taking these three factors into account when designing learning elements, educators can create effective and engaging materials that support student learning and achievement.

Types of Machine Learning

There are three types of machine learning:

  1. Supervised learning
  2. Unsupervised learning
  3. Reinforcement learning

Therefore, the correct answer is "All of the above".

Understanding Decision Trees: How Do They Work?

In a decision tree, a decision is made by performing a series of tests on a given set of data. The tree is constructed with each node representing a test and each branch representing an outcome of that test.

The decision tree first starts with a root node, which represents the entire dataset, and then branches out to different tests. There are several different types of tests that can be performed, such as a single test, double test, or multiple sequences of tests, depending on the complexity of the decision being made.

In order to make a decision, the algorithm traverses the decision tree by following the branches that correspond to the outcomes of each test. The final endpoint of the path reached on the tree will provide the decision that was made based on the data provided.

Therefore, a decision tree reaches a conclusion by considering the results of a series of tests applied to the data it is analyzing.

What is a Hybrid Bayesian Network?

A Hybrid Bayesian Network consists of both Discrete and Continuous variables. These variables act as numerical inputs to the network.

Components of AI agents:

In order to function effectively, AI agents consist of two main components:

  1. Architecture: This refers to the overall structure or design of the agent, including the algorithms and decision-making processes used to achieve its goals.
  2. Program: This is the specific implementation of the agent, including all the code and data used to actually execute its functions.

Therefore, the correct option is option C: Both A and B.

// Example implementation of an AI agent in Python:

class AI_Agent:
   def __init__(self):
      # Define architecture and initial program data
      self.architecture = "Neural Network"
      self.program = {...}

   def perceive(self, input_data):
      # Process input data using existing program
      perception = self.program.process(input_data)
      return perception

   def act(self, perception):
      # Use architecture to determine appropriate action based on perception
      action = self.architecture.decide(perception)
      return action

   def run(self, input_data):
      # Main function to run agent on specific input data
      perception = self.perceive(input_data)
      action = self.act(perception)
      return action

External Action Selection Element in AI Agents

In AI agents, the actuator element is used for external action selection, not the performance element. Therefore, the corrected answer to the question "For external action selection, which element is used in the agent?" is: Actuator. The actuator is responsible for carrying out the actions determined by the agent's decision-making process.

Increasing Pixel Brightness on a Screen

To increase the brightness of a pixel on a screen, the amount of light incident on the screen needs to be increased. This can be achieved by adjusting the backlighting of the screen.


# Increase pixel brightness on screen
def increase_brightness(screen, backlight):

Using mirrors or sound waves cannot increase pixel brightness on a screen. The brightness of a pixel is solely determined by the amount of light incident on the screen.

Logical Expression Unification

Unification refers to the process of making two logical expressions look identical.


PEAS stands for Performance, Environment, Actuators, Sensors.

Representation of Knowledge in AI

In the field of AI, knowledge can be represented in different ways. Two popular methods for representing knowledge are Predicate Logic and Propositional Logic. Hence, the correct answer is option C - Both A and B.

Code: N/A

(Note: No code is provided as this is a theoretical question.)

Appropriate Levels for a Knowledge-Based AI Agent

There are three appropriate levels for a knowledge-based AI agent, namely the Knowledge Level, the Logical Level, and the Implementation Level. These levels help the agent to acquire and apply knowledge to complete tasks efficiently and effectively. Therefore, the correct answer is option D, "All of the above."



Plain text:

Knowledge-based AI agents need to operate at different levels to function effectively. These levels include the Knowledge Level, the Logical Level, and the Implementation Level. By doing so, the agent can acquire, store, manipulate, and apply knowledge to solve complex problems like a smart human would.

Ways to Achieve Artificial Intelligence in Real Life

In order to achieve Artificial Intelligence in real life, we can use the following approaches:

  1. Machine Learning
  2. Deep Learning

Both Machine Learning and Deep Learning are the ways to implement Artificial Intelligence in real life.

Heuristic Search Algorithms

There are several types of heuristic search algorithms that are commonly used in the field of artificial intelligence. Two of the most popular types are:

  1. Best First Search Algorithm
  2. A* Search Algorithm

Both options A and B are heuristics-based search algorithms.

Multiplying 2 Numbers in LISP

In LISP, we can use the * operator to multiply 2 numbers. The syntax is:

(* a b)

where "a" and "b" are the two numbers to be multiplied.

Therefore, the correct option is A - "a * b".

Working Principles of Inference Engines

Inference engines operate based on two modes, namely forward chaining and backward chaining. Therefore, the correct answer is option C, which states that both A and B are correct.

What is Segmentation in Image Processing?

In image processing, segmentation refers to the process of dividing an image into multiple segments or sub-regions. This division is usually based on some predefined criteria such as color, intensity, texture, or shape. The purpose of segmentation is to simplify the image by breaking it down into smaller, more meaningful parts to make it easier to analyze and understand.

Out of the options given, the correct answer to the question "The process of breaking an image into parts is called?" is Segmentation.

Valid 3D Image Processing Techniques

In 3D Image Processing, the following techniques are valid:


Therefore, the correct answer is:

All of the above options are valid 3D image processing techniques.

What is Parsing used for?

Parsing is the process of building a parse tree for an input string. It is used for data interpretation. Therefore, the correct answer is "Data Interpretation". It is not used for sound recognition.

What Generation of Computers is Artificial Intelligence Associated With?

Fifth generation computers are the ones associated with artificial intelligence.

Components of an Expert System

An expert system is comprised of three main components:

1. Knowledge Base

The knowledge base is a collection of facts and rules that the expert system uses to make decisions or solve problems.

2. Inference Engine

The inference engine is the brain of the expert system. It uses logical reasoning to process the input data and to arrive at a conclusion.

3. User Interface

The user interface is the part of the expert system that communicates with the user. It enables the user to enter input data and to receive output data in a format that is easy to understand.

Therefore, the correct answer to the given question is:

All of the above

As all the above-mentioned components are crucial to the functioning of an expert system.

Optimizing Search Methods

Out of the given search methods, Depth First Search takes the least amount of memory consumption. This is because only the nodes on the current path are stored, making it more memory-efficient compared to Breadth-First Search and Optimal Search. Linear Search, on the other hand, is not a graph traversal algorithm and is typically used in arrays or lists with no memory overhead.

// Example Depth First Search implementation in Python

def DFS(graph, start, visited):

    for neighbor in graph[start]:
        if neighbor not in visited:
            DFS(graph, neighbor, visited)

    return visited

Types of AI

In the field of AI, there are various types of AI systems based on their functionality. Three main types are as follows:

1. Weak AI: also known as Narrow AI, refers to an AI system that is purpose-built and designed to perform a specific task. Examples include voice assistants like Siri and Alexa, chatbots, and image recognition software.

2. Theory of Mind AI: focuses on developing an AI system that can understand and interpret human emotions, beliefs, and thoughts. Currently, no such AI system exists, and it is still a theoretical concept.

3. Reactive Machines: These are the most basic types of AI systems that react to changes in their environment but do not learn from experience, meaning they cannot make decisions based on past experience and must be programmed to perform any specific task.

Therefore, the answer to the given question is "Reactive Machines" as they are not a type of AI based on functionality.

Understanding State Space in AI

State space in AI refers to the range of all possible problem states that can be encountered while solving a specific problem. It is a set of possible configurations that a system can exist in or a set of allowed values for all variables in a defined system.

In simpler terms, the state space is like a map of all possible scenarios that can arise while solving a problem. It includes the initial state, the goal state, and all other possible states that may arise during the problem-solving process.

Therefore, the correct answer to the given question is: Option A - State space in AI is a collection of all possible problem states.

Technical Interview Guides

Here are guides for technical interviews, categorized from introductory to advanced levels.

View All

Best MCQ

As part of their written examination, numerous tech companies necessitate candidates to complete multiple-choice questions (MCQs) assessing their technical aptitude.

View MCQ's
Made with love
This website uses cookies to make IQCode work for you. By using this site, you agree to our cookie policy

Welcome Back!

Sign up to unlock all of IQCode features:
  • Test your skills and track progress
  • Engage in comprehensive interactive courses
  • Commit to daily skill-enhancing challenges
  • Solve practical, real-world issues
  • Share your insights and learnings
Create an account
Sign in
Recover lost password
Or log in with

Create a Free Account

Sign up to unlock all of IQCode features:
  • Test your skills and track progress
  • Engage in comprehensive interactive courses
  • Commit to daily skill-enhancing challenges
  • Solve practical, real-world issues
  • Share your insights and learnings
Create an account
Sign up
Or sign up with
By signing up, you agree to the Terms and Conditions and Privacy Policy. You also agree to receive product-related marketing emails from IQCode, which you can unsubscribe from at any time.