AI Question Bank

Q 1 :- What is artificial intelligence (AI) ?

Ans :- Artificial intelligence is the simulation of human intelligence
processes by machines, especially computer systems. Specific applications
of AI include expert systems, natural language processing, speech
recognition and machine vision.

Q 2. Introduction to AI applications and AI techniques

Ans:- Artificial Intelligence (AI) has a wide range of applications across
various industries, revolutionizing the way we live and work.

AI techniques
Natural Language
Processing (NLP)
Vision
Healthcare
Vehicles
E-commerce and Recommendation
Systems
Gaming
Predictive
Analytics
Q 3. Production systems.
Ans:- A production system in AI is a framework that assists in developing
computer programs to automate a wide range of tasks. It significantly impacts
the creation of AI-based systems like computer software, mobile applications,
and manufacturing tools.
Components of a Production System:
Working Memory:
Production Memory (Rule Base):
Condition (Antecedent):
Action (Consequent):
Control Strategy:

Make By :- Youtuber Technical Saurabh

 AI Question Bank

Q 4. Reasoning – forward & backward chaining Intelligent

agents.
Ans:- Control Strategy decides which rule to apply next during the
process of searching for a solution to a problem. If we choose another
control strategy, say, choose a rule randomly from the applicable rules
then definitely it causes motion and eventually will lead to a solution.

Forward Chaining (Data-Driven):

Backward Chaining (Goal-Driven):
Hybrid Control Strategies:
Reactive Control:
Proactive Control:
Rule-Based Control:
Learning-Based Control:
Hierarchical Control

Q 5. Reasoning – forward & backward chaining Intelligent

Ans :- Forward chaining is a method of reasoning in artificial
intelligence in which inference rules are applied to existing data to
extract additional data until an endpoint (goal) is achieved.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Initialization:
Rule Application:
Iterative Process:
Termination:

Backward Chaining: Backward chaining is a concept in artificial intelligence

that involves backtrackingfrom the endpoint or goal to steps that led to the
endpoint.

Goal Specification
Rule Application
Iterative Process
Termination

Q. 6 :- Agents and environments –

Ans :- An agent is anything that can perceive its environment
through sensors andacts upon that environment through effectors.
A human agent has sensory organs such as eyes, ears, nose,
tongue and skin parallel to the sensors, and other organs such as
hands, legs, mouth, for effectors.
A robotic agent replaces cameras and infrared range finders for the
sensors,and various motors and actuators for effectors.

Agent Terminology
 Performance Measure of Agent
 Behavior of Agent
 Percept
 Percept Sequence
 Agent Function

Make By :- Youtuber Technical Saurabh

 AI Question Bank

Q 7. Good Modelling in AI.

Ans:- Good modeling in artificial intelligence (AI) is essential for building
effective and accurate AI systems that can perform tasks, make
predictions, and solve problems.
Domain Understanding:
Data Collection and
Preprocessing:
FeatureEngineering:
Model Selection:
Regularisation
Interpretability and Explainability

Q 8. The nature of Environments in AI.

Ans :- An "environment" refers to the external context or surroundings
in which an AI agent operates. The environment provides sensory
inputs to the agent, and the agent's actions can affect the
environment.
Perception:
Static vs. Dynamic:
Deterministic vs. Stochastic:
Episodic vs. Sequential:
Partially Observable:
Adversarial Environments:
Time Constraints:
Uncertainty and Noise:
Simulated vs. Real-World
Environments:

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 9. Structure of agents in AI.
Ans :- An intelligent agent is a combination of Agent Program and
Architecture.
Intelligent Agent = Agent Program + Architecture

Agent Program is a function that implements the agent mapping from

percepts to actions. There exists a variety of basic agent program
designs.
1. Simple reflex agents
2. Model based reflex agent
3. Goal-based agents
4. Utility-based agents

Q 10. Problem Solving in AI.

Ans:- The aim of Artificial Intelligence is to develop a system which
can solve the various problems on its own. But a system must
predict and convert the problem in its understandable form.
Types of Problems in AI
1. Ignorable Problems
2. Recoverable Problems
3. Irrecoverable Problems

Q 11. Problem solving agents

Ans :- The problem-solving agent performs precisely by defining
problems and several solutions. So we can say that problem solving is a
part of artificial intelligence. such as a tree, B-tree.

1. Problem Formulation:
2. Search Space:
3. State Representation:
4. Search Algorithms:
5. Heuristics:
6. Evaluation and Scoring:

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 12. Searching for solutions in AI
Ans :- Searching is a step by step procedure to solve a search-problem
in a given search space. A search problem can have three main factors:

Q 13. Uniformed search strategies.

Ans :- Uninformed searches, also known as blind searches, are
search algorithms that explore a problem space without using any
specific knowledge.

1. Breadth First Search

2. Depth First search
3. Uniform Cost Search

Q 14. Avoiding repeated states.

Ans :- Avoiding repeated states is a critical consideration in AI search
algorithms to ensure efficiency and prevent infinite loops.

Closed List (Explored Set):

Hashing or State Representation:
Cycle Checking:
Pruning or Cutting Off
Branches Depth-
Make By :- Youtuber Technical Saurabh
 AI Question Bank
Limited Search:
Memoization:
Tabulation:
Duplicate Detection:
Use of Data Structures:
Bidirectional Search

Q 15. Searching with partial information in AI.

Ans :- Searching with partial information, also known as search under
uncertainty or in partially observable environments, is a common
challenge in artificial intelligence (AI).
 Partial Observability:
 Belief State:
 Markov Decision Processes (MDPs):
 Hidden Markov Models (HMMs):
 Bayesian Networks:
 Particle Filters:
 Information Gathering Strategies:

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 16. SEARCH FUNCTION STRATEGIES IN AI

Informed search :- Informed search is a type of search algorithm

is a fundamental concept that deals with how information and
knowledge about the world can be structured and stored in a way that
allows AI systems to reason.

1. Propositional Logic vs. First-Order Logic:

2. Elements of First-Order Logic:
3. Axioms and Inference Rules:
4. Example of First-Order Logic Statements:
5. Use in AI:

Informed search strategies :- informed search in AI is a type of

search algorithm thatuses additional information to guide the search
process.

Heuristic function :- A heuristic function estimates the approximate

cost of solving a task. Determining the shortest driving distance to a
particular location can be one example.

Local search :- In AI, local search involves solving problems with

discrete states such as hill-climbing and simulated annealing.

Optimization problem :- An optimization problem is a mathematical

problem that involves findingthe best solution from a set of possible
solutions.

local search in continuous spaces :- Local search algorithms in

continuous spaces are optimization techniques used to find the optimal
solution within a continuous domain.

Online search agent :- Online search agent interleaves computation

and action: first. it takes an action, then it observes the environment and
Online search is a necessary idea for unknown environments.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
known and unknown environments :- In a known environment, the
results for all actions are known to the agent. While in unknown
environment, agent needs to learn how it works in order to perform an
action.
Constraint satisfaction problems (CSP) :-
CSP is a specific type of problem-solving approach that involves
identifying constraints that must be satisfied and finding a solution
that satisfies all the constraints.

Backtracking search and Local search for CSP :-

Backtrackers are sometimes called constructive because they
construct solutions from partial consistent assignments of domain
values to variables.

Structure of problems :- A good problem structure will help you

clarify the problem statement, identify the key issues and hypotheses,
prioritize the analysis and data collection.

Adversarial search :- Adversarial search is a method applied to a

situation where you are planning while another actor prepares against you.
Your plans therefore, could be affected by your opponent's actions.

Games in ai :- There are two main approaches to game playing in AI,

rule- based systems and machine learning-based systems. Rule-based
systemsuse a set of fixed rules to play the game.

Optimal decisions :- Game theory is a theoretical framework for

conceiving socialsituations among competing players. In some respects,
gametheory is the science of strategy.

Alpha in ai :- The two-parameter can be defined as:

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Alpha: The best (highest-value) choice we have found so far atany
point along the path of Maximizer. The initial value of alpha is -∞.
Beta: The best (lowest-value) choice we have found so far at any
point along the path of Minimizer.

Beta Pruning :- Alpha-Beta Pruning is a key technique used in game-

playing AI, particularly in games with extensive search spaces like chess
andcheckers.
Imperfect decisions :- In the field of artificial intelligence (AI),
imperfect information games are those in which participants do not have
completeknowledge of the game state.

Real time decision :- Real-time decisioning marries together the

opportunities of live data and analytics within the boundaries of an
organisation's decision-making process.

Games that include an element of chance :-

Games like craps, roulette, and lotteries are easy to categorize as
games of pure chance, because the player is betting against
random numbers

Representation revisited :- It revisit the concept of knowledge

representation in AI, as it's a fundamental aspect of artificial intelligence
that plays a crucial role in enabling machines to understand and work with
information effectively.
Knowledge Representation revisited
Inference:
Flexibility:
Common Knowledge Representation
Approaches: First-Order Logic (FOL):
Semantic
Networks:
Frames:
Ontologies:
Graph Databases: Rule-Based Systems:

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 17. Syntax and Symentics For First order Logic
Ans :- First-order logic is another way of knowledge representation in
artificial intelligence. It is an extension to propositional logic.

FOL is sufficiently expressive to represent the natural language

statements in a concise way.

First-order logic is also known as Predicate logic or First-order

predicate logic. First-order logic is a powerful language that develops
information about the objects and relationship between those objects.

Syntax of First-Order logic:

The syntax of FOL determines which collection of symbols is a logical
expression in first-order logic. The basic syntactic elements of first-order
logic are symbols.

Constant 1, 2, A, John, Mumbai, cat,....

Variables x, y, z, a, b,....

Predicates Brother, Father, >,....

Function sqrt, LeftLegOf, ....

Connectives ∧, ∨, ¬, ⇒, ⇔

Equality ==

Quantifier ∀, ∃

Semantics relates the syntax to the world (relational structure). A |= ϕ

denotes that formula ϕ is true in the world A. Here „|=‟ is the semantical
relation. An interpretation of a first-order language assigns a denotation to
each non-logical symbol (predicate symbol, function symbol, or constant
symbol) in that language.

Make By :- Youtuber Technical Saurabh

 AI Question Bank

Q 18 :- Using First Order Logic ?

Ans :- Let a variable x which refers to a cat so all x can be represented in UOD as below:

∀x man(x) → drink (x, coffee).

It will be read as: There are all x where x is a man who drink coffee.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 19 :- Knowledge engineering in first order logic.

Ans:- The process of constructing a knowledge-base in first-order logic

is called as knowledge- engineering. In knowledge-engineering,
someone who investigates a particular domain, learns important concept
of that domain, and generates a formal representation of the objects, is
known as knowledge engineer.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 20 :- Inference in First order logic.
Ans :- Inference in First-Order Logic is used to deduce
new facts or
sentences from existing sentences. Before understanding the FOL
inference rule.

Substitution:

Substitution is a fundamental operation performed on terms and formulas.

It occurs in all inference systems in first-order logic. If we write F[a/x], so
it refers to substitute a constant "a" in place of variable "x".

Equality:

First-Order logic does not only use predicate and terms for making atomic
sentences but also uses another way, which is equality in FOL.
Example: Brother (John) = Smith.

Q 21 :- Resolution in AI
Ans :- Resolution is a fundamental inference rule used in artificial
intelligence (AI) and automated theorem proving. It is a method for
determining the validity of a logical statement or proving the truth or
falsehood of a proposition. Resolution is particularly important in First-
Order Logic (FOL) and Propositional Logic.

(i) Purpose of Resolution:

(ii) Propositional Resolution:
(iii)First-Order Resolution:
(iv) Refutation and Proof by Contradiction:
(v) Resolution Strategies:
(vi) Limitations:

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 22 :- Knowledge representation
Ans :- Humans are best at understanding, reasoning, and interpreting
knowledge. Human knows things, which is knowledge and as per their
knowledge they perform various actions in the real world. But how
machines do all these things comes under knowledge
representation and reasoning.

o Knowledge representation and reasoning (KR, KRR) is the part of

Artificial intelligence which concerned with AI agents thinking and
how thinking contributes to intelligent behaviour of agents.
o It is responsible for representing information about the real world so
that a computer can understand and can utilize this knowledge to
solve the complex real world problems.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 23 :- Simulation and events
Ans :- Simulation and event-driven programming are important concepts
in artificial intelligence (AI) and computer science. They are used in
various AI applications, including modeling complex systems, conducting
experiments, and simulating real-world scenarios.
1. Simulation in AI:
Training and Testing:
Predictive Modeling
Gaming and Virtual Environments:
2. Event-Driven Programming:
User Interfaces:.
Real-time Systems:
Simulations:
3. Simulation with Event-Driven Programming:
Event-Based Simulation:
Event Handlers:
Time Advancement:
4. Benefits of Event-Driven Simulation in AI:
Flexibility:
Realism:
Parallelism:
Interactivity:

Q 24 :- Mental events and mental objects.

Ans :- Mental Events:
 Mental events refer to the various processes, activities, and occurrences
that take place within an individual's mind. These events encompass a wide
range of cognitive activities, thoughts, feelings, and perceptions that occur in
one's conscious or unconscious awareness.
 Examples of mental events include thinking, remembering, perceiving,
imagining, experiencing emotions, making decisions, and problem-solving.
Mental Objects:
 Mental objects, on the other hand, refer to the content or objects of thought
within the mind. These are the things, concepts, ideas, or representations
that the mind is directed toward during mental events.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 25 :- Learning / Learning Agent In AI ?
Ans :- Learning is essential for unknown Environment. Learning is
useful as a system construction method. Learning Modifiers the
agent‟s decision mechanism to improve performance.

Critic Sensors

feedback

changes
Learning Performance
element element
knowledge
learning
goals
experiments
Problem
generator

Agent Effectors

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 26 :- Inductive Learning ?
Ans :- Simplest form: learn a function from examples (tabula rasa)

f is the target function

An example is a pair x, f (x), e.g., , +1

Problem: find a(n) hypothesis h

such that h ≈ f
given a training set of examples

(This is a highly simplified model of real learning:

– Ignores prior knowledge
– Assumes a deterministic, observable “environment”
–
Assumes examples are given
Assumes that the agent wants to learn f —why?)

INDUCTIVE LEARNING METHOD

Construct/adjust h to agree with f on training set

E.g., curve fitting:

Make By :- Youtuber Technical Saurabh

 AI Question Bank

Q 27. Learning Decision Tree ?

Ans :- One possible representation for hypotheses
E.g., here is the “true” tree for deciding whether to wait:

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Decision trees can express any function of the input attributes.
E.g., for Boolean functions, truth table row → path to leaf:

Q 28 :- Ensemble Learning
Ans :- Ensemble learning helps improve machine learning results by
combining several models. This approach allows the production of better
predictive performance compared to a single model. Basic idea is to
learn a set of classifiers (experts) and to allow them to vote.
Advantage : Improvement in predictive accuracy.
Disadvantage : It is difficult to understand an ensemble of classifiers.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 29 :- Logical formulation of Learning
Ans :- Learning is to find an equivalent logical expression we can
classify examples
Each hypothesis proposes such an expression - a candidate
definition of Q
r WillWait(r) Pat(r,Some) 
Pat(r,Full) Hungry(r)Type(r,French) 

Q 30 :- Knowledge Learning In AI ?
Ans :- 'Knowledge representation in AI' is like giving computers a smart
brain. It's the magic that allows them to understand and use real-world
information to solve tricky problems. In simple terms, it's about teaching
AI to think and reason using symbols and automation.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 31 : - Learning Using Relevant Information ?
Ans :- This is a kind of Learning in which background knowledge
relates the relevance of a set of features in an instance to the general
goal predicate.
Ex :- if a see amen in the forum in Rome speaking Latin, and I know that
if seeing someone in a city speaking a language usualyy.

Q 32 :- Inductive Logic Programming (ILP) ?

Ans :- Inductive logic programming is the subfield of machine learning
that uses first-order logic to represent hypotheses and data. Because
first-order logic is expressive and declarative, inductive logic
programming specifically targets problems involving structured data and
background knowledge. Inductive logic programming tackles a wide
variety of problems in machine learning, including classification,
regression, clustering, and reinforcement learning, often using “upgrades”
of existing propositional machine learning systems.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 33 :- Statistical learning Method ?
Ans :- Discover the powerful fusion of statistics and machine learning.
Explore how statistical techniques underpin machine learning models,
enabling data-driven decision-making.
 Popular Statistical Machine Learning Techniques.
 Linear Regression.
 Logistic Regression.
 Decision Trees.
 Random Forest.
 Support Vector Machines (SVM)
 K-Nearest Neighbours (KNN)

Q 34 :- Learning with Complete data ?

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 35 :- learning with Hidden Variable ?
Ans :- The next simplest case is where the model is given, but not all
variables are observed. A hidden variable or a latent variable is a
variable in a belief network whose value is not observed for any of the
examples. That is, there is no column in the data corresponding to that
variable.

Q 36 :- EM Algorithm ?
Ans:- The EM algorithm is considered a latent variable model to find the
local maximum likelihood parameters of a statistical model, proposed by
Arthur Dempster, Nan Laird, and Donald Rubin in 1977. The EM
(Expectation-Maximization) algorithm is one of the most commonly used
terms in machine learning to obtain maximum likelihood estimates of
variables that are sometimes observable and sometimes not
EM Algorithm
The EM algorithm is the combination of various unsupervised ML algorithms, such
as the k-means clustering algorithm.

Make By :- Youtuber Technical Saurabh

 AI Question Bank

Q 37 :- Instance Based Learning ?

Ans :- instance-based learning are the systems that learn the training
examples by heart and then generalizes to new instances based on
some similarity measure.
Some of the instance-based learning algorithms are :
1. K Nearest Neighbor (KNN)
2. Self-Organizing Map (SOM)
3. Learning Vector Quantization (LVQ)
4. Locally Weighted Learning (LWL)
5. Case-Based Reasoning

Q 38 :- Neural Network ?
Ans :- Artificial Neural Network" is derived from Biological neural
networks that develop the structure of a human brain. Similar to the
human brain that has neurons interconnected to one another, artificial
neural networks also have neurons that are interconnected to one
another in various layers of the networks. These neurons are known as
nodes.

Make By :- Youtuber Technical Saurabh

 AI Question Bank

Relationship between Biological neural network and artificial neural network:

Biological Neural Network Artificial Neural Network

Dendrites Inputs

Cell nucleus Nodes

Synapse Weights

Axon Output

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 39 :- Reinforcement Learning ?
Ans :- Reinforcement learning is an area of Machine Learning. It is
about taking suitable action to maximize reward in a particular situation.
It is employed by various software and machines to find the best
possible behavior or path it should take in a specific situation.
Reinforcement Learning (RL) is the science of decision making. It is
about learning the optimal behavior in an environment to obtain
maximum reward. Reinforcement learning uses a formal framework
defining the interaction between a learning agent and its environment in
terms of states, actions, and rewards.

Types of Reinforcement:
There are two types of Reinforcement:
1. Positive:
2. Negative:

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 40 :- Passive Learning ?
Ans :-

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 41 :- Different Type of Uncertainty ?
Ans :- Types of Uncertainty in AI
Uncertainty in artificial intelligence (AI) refers to the lack of complete
information or the presence of variability in data and models.

1. Aleatoric Uncertainty:
2. Epistemic Uncertainty:
3. Parameter Uncertainty:
4. Uncertainty in Decision-Making:
5. Uncertainty in Natural Language Understanding:
6. Uncertainty in Probabilistic Inference:
7. Uncertainty in Reinforcement Learning:
8. Uncertainty in Autonomous Systems:
9. Uncertainty in Safety-Critical Systems:
10. Uncertainty in Transfer Learning:
11. Uncertainty in Human-AI Interaction:

Q 41 :- Degree Of Believe and Degree of Truth ?

Ans :- Degree of Belief:
 In Bayesian probability theory, the degree of belief represents the
subjective probability assigned to a statement.
 It reflects the agent's confidence or belief in the truth of a particular
proposition.
 Degrees of belief are updated through Bayesian inference as new
evidence becomes available.
Degree of Truth:

 The degree of truth refers to the extent to which a statement or

proposition is considered true or accurate.
 In classical logic, a statement is either true or false.
 Fuzzy logic is one approach that deals with degrees of truth.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 42 :- Various Probability Construct ?
Ans :-
Prior probability: The prior probability of an event is probability
computed before observing new information.

Conditional Probability :- Conditional probability is calculated by

multiplying the probability of the preceding event by the updated probability of
the succeeding, or conditional, event.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Probability Axioms :- The probability is the likelihood or chance of
something happening. And one of the fundamental concepts of probability
is the Axioms of probability.

Probability Distribution :- Probability Distribution of a Random

Variable (X) shows how the Probabilities of the events are distributed
over different values of the Random Variable. When all values of a
Random Variable are aligned on a graph, the values of its probabilities
generate a shape.

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Joint Probability Distribution :- A joint probability
distribution represents a probability distribution for two or more random
variables. Instead of events being labelled A and B.

Q 43 :- Baye’s Rule ?
Ans :-

Make By :- Youtuber Technical Saurabh

 AI Question Bank

Q 44 :- Shafer Theory ?
Ans :- What Dempster-Shafer Theory was given by Arthur P.
Dempster in 1967 and his student Glenn Shafer in 1976.

 Bayesian theory is only concerned about single evidence.

 Bayesian probability cannot describe ignorance.

DST is an evidence theory, it combines all possible outcomes of the

problem. Hence it is used to solve problems where there may be a
chance that a piece of different evidence will lead to some different
result.
Example: Let us consider a room where four people are present, A, B,
C, and D. Suddenly the lights go out and when the lights come back, B
has been stabbed in the back by a knife, leading to his death. No one
came into the room and no one left the room. We know that B has not
committed suicide. Now we have to find out who the murderer is.
To solve these there are the following possibilities:
 Either {A} or {C} or {D} has killed him.
 Either {A, C} or {C, D} or {A, D} have killed him.
 Or the three of them have killed him i.e; {A, C, D}
 None of them have killed him {o} (let‟s say).

Make By :- Youtuber Technical Saurabh

 AI Question Bank
Q 45 :- Fuzzy sets/logic ?
Ans :- 'Fuzzy' word means the things that are not clear or are vague.
Sometimes, we cannot decide in real life that the given problem or
statement is either true or false. At that time, this concept provides many
values between the true and false and gives the flexibility to find the best
solution to that problem.

The Fuzzy logic can be implemented in systems such as micro-

controllers, workstation-based or large network-based systems for
achieving the definite output. It can also be implemented in both hardware
or software.

Example of Fuzzy Logic as comparing to Boolean Logic

Make By :- Youtuber Technical Saurabh

 AI Question Bank

TECHNICAL SAURABH
SUBSCRIBE NOW

Make By :- Youtuber Technical Saurabh