2 Marks Questions

Class: III - Year, B. Tech Semester: I Academic

Year: 2021-22
Course Title: Artificial Intelligence Course Code: 19A05502T Credits:
3 Batch: 2019-2022 Program/Dept.:
CSE Section: CSE-A&B Regulation:
R-19 Faculty: Dr D Pramodh Krishna
UNIT- 1

1 .Define Artificial Intelligence (AI).

The study of how to make computers do things at which at the moment, people are better.
Systems that think like humans
Systems that act like humans
Systems that think rationally
Systems that act rationally
2. Define Artificial Intelligence in terms of rational acting.
A field of study that seeks to explain and emulate intelligent behaviors in terms of computational processes-
Schalkoff. The branch of computer science that is concerned with the automation of intelligent behavior-
Luger & Stubblefield.
3. Define Artificial in terms of rational thinking.
The study of mental faculties through the use of computational models-Charniak & McDermott. The study
of the computations that make it possible to perceive, reason and act-Winston
4. What is meant by Turing test?
To conduct this test we need two people and one machine. One person will be an interrogator (i.e.)
questioner, will be asking questions to one person and one machine. Three of them will be in a separate
room.Interrogator knows them just as A and B. so it has to identify which is the person and machine.
The goal of the machine is to make Interrogator believe that it is the person’s answer. If machine succeeds
by fooling Interrogator, the machine acts like a human. Programming a computer to pass Turing test is very
difficult.
5. What is called materialism?
An alternative to dualism is materialism, which holds that the entire world operate according to physical
law. Mental process and consciousness are therefore part of physical world, but inherently unknowable
they are beyond rational understanding.
6. What are the capabilities, computer should posses to pass Turing test?
Natural Language Processing
Knowledge representation
Automated reasoning
Machine Learning
7. Define Total Turing Test?
The test which includes a video signals so that the interrogator can test the perceptual abilities of the
machine. To pass the total Turing Test, the computer will need computer vision to perceive objects, and
robotics to manipulate objects and move about.
8. What are the capabilities computers needs to pass total Turing test?
Natural Language Processing
Knowledge representation
Automated reasoning
Machine Learning
Computer Vision
Robotics
9. Define Rational Agent.
It is one that acts, so as to achieve the best outcome (or) when there is uncertainty, the best expected
outcome.
10. Define Agent.
An Agent is anything that can be viewed as perceiving (i.e.) understanding its environment through sensors
and acting upon that environment through actuators.
11. Define an Omniscient agent.
An omniscient agent knows the actual outcome of its action and can act accordingly; but omniscience is
impossible in reality.
12. What are the factors that a rational agent should depend on at any given time?
1. The performance measure that defines degree of success.
2. Ever thing that the agent has perceived so far. We will call this complete perceptual history the percept
sequence.
3. When the agent knows about the environment.
4. The action that the agent can perform.
13. List the properties of environments.
o Fully Observable Vs Partially Observable
o Deterministic Vs Stochastic
o Episodic Vs Sequential
o Static Vs Dynamic
o Discrete Vs Continuous
o Single Agent Vs Multi agent
a. Competitive Multi agent
b.Co – operative Multi agent
14. List the various type of agent programs.?
Simple reflex agent program.
Agent that keep track of the world.
Goal based agent program.
Utility based agent program
15. Give the structure of agent in an environment?
Agent interacts with environment through sensors and actuators. An Agent is anything that can be viewed
as perceiving (i.e.) understanding its environment through sensors and acting upon that environment
through actuators.
16. Define Percept Sequence.
An agent’s choice of action at any given instant can depend on the entire percept sequence observed to
elate.
16. Define Agent Function.
It is a mathematical description which deals with the agent’s behavior that maps the given percept sequence
into an action.
17. What is important for task environment?
PEAS → P- Performance measure
E - Environment
A- Actuators
S – Sensors
Example
Interactive English tutor performance measure maximize student’s score on test.
Environment
Set of students testing Agency
Actuators
Display exercises suggestions, corrections.
Sensors
Keyboard entry
18. How agent should act?
Agent should act as a rational agent. Rational agent is one that does the right thing, (i.e.) right actions will
cause the agent to be most successful in the environment.
19. How to measure the performance of an agent?
Performance measure of an agent is got by analyzing two tasks. They are How and When actions.
20. Define Ideal Rational Agent.
For each possible percept sequence, a rational agent should select an action that is expected to maximize
its performance measure, given the evidence provided by the percept sequence and whatever built in
knowledge the agent has.
 UNIT- 2
1. Define problem solving agent.
Problem solving agent is one kind of goal based agent, where the agent should select one action from
sequence of actions which lead to desirable states.
2 List the steps involved in simple problem solving technique.
i. Goal formulation
ii. Problem formulation
iii. Search
iv. Solution
v. Execution phase

3. What are the different types of problem?

Single state problem, multiple state problems, Contingency problem, Exploration problem.
4. What are the components of a problem?
There are four components. They are
i. initial state
ii. Successor function
iii. Goal test
iv. Path cost
v. Operator
vi. state space
vii. path

5. Give example problems for Artificial Intelligence.

i. Toy problems-Ex- vacuum world,8-puzzle,8-queens problem
ii. Real world problems Ex- Airline travel problem, Traveling salesman problem
6. Give example for real world end toy problems.
Real world problem examples:
i. Airline travel problem.
ii. Touring problem.
iii. Traveling salesman problem.
iv. VLSI Layout problem
v. Robot navigation
vi. Automatic Assembly
vii. Internet searching
Toy problem Examples:
Vacuum world problem.
8 – Queen problem
8 – Puzzle problem
7. Define search tree.
The tree which is constructed for the search process over the state space is called search tree.
A search tree is generated by the initial state and the successor function that together define the state space.
In general, we may have a search graph rather than a search tree, when the same state can be reached from
multiple paths.
8. Explain depth-limited tree search algorithm
function DEPTH-LIMITED-SEARCH(problem, limit ) returns a solution, or failure/cutoff
return RECURSIVE-DLS(MAKE-NODE(problem.INITIAL-STATE), problem, limit )
function RECURSIVE-DLS(node, problem, limit ) returns a solution, or failure/cutoff
if problem.GOAL-TEST(node.STATE) then return SOLUTION(node)
else if limit = 0 then return cutoff
else
cutoff occurred?←false
for each action in problem.ACTIONS(node.STATE) do
child ←CHILD-NODE(problem, node, action)
 result ←RECURSIVE-DLS(child , problem, limit − 1)
if result = cutoff then cutoff occurred?←true
else if result != failure then return result
if cutoff occurred? then return cutoff else return failure
9. List the performance measures of search strategies.
i. Completeness
ii. Optimality
iii. Time complexity
iv. Space complexity

10. Differentiate Blind Search and Heuristic Search.

Blind search
i) No information about the path cost from the current state to goal state.
ii) Problem is solved with the information we which we know.
iii) Examples
a) Breadth first search
b) Uniform cost search
c) Depth first Search
d) Depth limited search
e) Iterative deepening search
f) Bi – Directional Search
Heuristic Search.
i) We have some information like minimum path caused to move
ii) Problem can be solved by the information which is already given.
iii) Example
a) Best first search
b) Greedy search
c) A* search
11. Define Uniform cost search.
Uniform cost search expands the node ‘n’ with the lowest path cost instead of expanding the shallowest
node.
12. Define Depth first search.
It expands the deepest node in the current fringe of the search tree.
13. What is informed search?
One that uses problem – specific knowledge beyond the definition of the problem itself and it can find
solutions more efficiently than an uninformed strategy.
14. Define Hill Climbing search.
It is a loop that continually moves in a increasing value direction up hill and terminates
when it reaches a “peak” where no neighbour has a higher value.
15. List the various informed search strategy.
Best first search –greedy search ,A* search
Memory bounded search-Iterative deepening A*search -simplified memory bounded
A*search -Iterative improvement search –hill climbing -simulated annealing.
16. Define Admissible heuristic h (n).
In A* search, if it is optimal then, h(n) is an admissible heuristic which means h(n) never
overestimates the cost to reach the goal.
17. What is triangle inequality?
It states that each side of a triangle cannot be longer than the sum of the other two slides of the
triangle.
18. What is RBFS?
It keeps track of the f-value of the best alternative path available from any ancestor of the
current node. RBFS remembers the f-value of the best leaf in the forgotten sub tree and therefore
decide whether its worth re expanding the sub tree sometimes later.
19. Give the procedure of IDA* search.
Minimize f(n)=g(n)+h(n) combines the advantage of uniform cost search + greedy search A* is
complete, optimal. Its space complexity is still prohibitive.
Iterative improvement algorithms keep only a single state in memory, but can get stuck on local
maxima. In this algorithm each iteration is a dfs just as in regular iterative deepening. The depth first
search is modified to use an f-cost limit rather than a depth limit. Thus each iteration expands all nodes
inside the contour for the current f-cost.
20. What are the variants of hill climbing?
i. Stochastic hill climbing
ii. First choice hill climbing
iii. Simulated annealing search
iv. Local beam search
v. Stochastic beam search
21.Define Greedy Best First Search.
It expands the node that is closest to the goal (i.e.) to reach solution in a quicker way. It is done by using
the heuristic function: f(n) = h(n).

UNIT 3
1. What is Reinforcement Learning?
Reinforcement Learning is a feedback-based Machine learning technique in which an agent learns to
behave in an environment by performing the actions and seeing the results of actions. For each good action,
the agent gets positive feedback, and for each bad action, the agent gets negative feedback or penalty.

2. Define Active Reinforcement Learning

Active reinforcement learning (ARL) is a variant on reinforcement learning where the agent does
not observe the reward unless it chooses to pay a query cost c > 0. The central question of ARL is how
to quantify the long-term value of reward information.

3. Define Passive Reinforcement Learning

In case of passive RL, the agent's policy is fixed which means that it is told what to do. ... Therefore,
the goal of a passive RL agent is to execute a fixed policy (sequence of actions) and evaluate it while that
of an active RL agent is to act and learn an optimal policy.

4. What is Natural Language Processing?

Natural Language Processing (NLP) is a branch of Artificial Intelligence (AI) that enables machines
to understand the human language. Its goal is to build systems that can make sense of text and
automatically perform tasks like translation, spell check, or topic classification

5. Define Information Retrieval.

The techniques of storing and recovering and often disseminating recorded data especially
through the use of a computerized system.

6. Define Information Extraction.

Information extraction (IE) is the task of automatically extracting structured information from
unstructured and/or semi-structured machine-readable documents, while information retrieval (IR)
is finding material (usually documents) of an unstructured nature (usually text) that satisfies an
Information.
7. What is direct utility estimation?
In this method, the agent executes a sequence of trials or runs (sequences of states-actions transitions that
 continue until the agent reaches the terminal state). Each trial gives a sample value and the agent estimates
the utility based on the samples values. Can be calculated as running averages of sample values. The main
drawback is that this method makes a wrong assumption that state utilities are independent while in reality
8. what are the Applications of Reinforcement Learning?
1. Robotics:
a. RL is used in Robot navigation, Robo-soccer, walking, juggling, etc.
Control:
. RL can be used for adaptive control such as Factory processes, admission control in
telecommunication, and Helicopter pilot is an example of reinforcement learning.
Game Playing:
. RL can be used in Game playing such as tic-tac-toe, chess, etc.
Chemistry:
. RL can be used for optimizing the chemical reactions.
Business:
. RL is now used for business strategy planning.
Manufacturing:
. In various automobile manufacturing companies, the robots use deep reinforcement learning to pick goods
and put them in some containers.
Finance Sector:
. The RL is currently used in the finance sector for evaluating trading strategies.

9. What is meant by passive and active reinforcement learning and how do we compare the two?
Both active and passive reinforcement learning are types of RL. In case of passive RL, the agent’s policy
is fixed which means that it is told what to do. In contrast to this, in active RL, an agent needs to decide
what to do as there’s no fixed policy that it can act on. Therefore, the goal of a passive RL agent is to
execute a fixed policy (sequence of actions) and evaluate it while that of an active RL agent is to act and
learn an optimal policy.
10.What is Adaptive Dynamic Programming(ADP)
ADP is a smarter method than Direct Utility Estimation as it runs trials to learn the model of the environment by
estimating the utility of a state as a sum of reward for being in that state and the expected discounted reward of
being in the next state.

Where R(s) = reward for being in state s, P(s'|s, π(s)) = transition model, γ = discount factor and Uπ(s) = utility of
being in state s'.
It can be solved using value-iteration algorithm. The algorithm converges fast but can become quite costly to
compute for large state spaces. ADP is a model based approach and requires the transition model of the
environment. A model-free approach is Temporal Difference Learning.
11.What is Temporal Difference Learning (TD)
TD learning does not require the agent to learn the transition model. The update occurs between successive states
and agent only updates states that are directly affected.

Where α = learning rate which determines the convergence to true utilities.

While ADP adjusts the utility of s with all its successor states, TD learning adjusts it with that of a single successor
state s'. TD is slower in convergence but much simpler in terms of computation.
12.what is Q learning?
Q-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It
does not require a model of the environment (hence "model-free"), and it can handle problems with stochastic
transitions and rewards without requiring adaptations. For any finite Markov decision process (FMDP), Q-learning
finds an optimal policy in the sense of maximizing the expected value of the total reward over any and all
successive steps, starting from the current state. Q-learning can identify an optimal action-selection policy for any
given FMDP, given infinite exploration time and a partly-random policy. "Q" refers to the function that the algorithm
computes – the expected rewards for an action taken in a given state.
13. Define Language and Grammar?

A language can be defined as a set of strings. “print(2 + 2)” is a legal program in the language Python, whereas
“2)+(2 print” is not. Since there are an infinite number of legal programs, they cannot be enumerated; instead they
are specified by a set of rules called a grammar. Formal languages also have rules that define the meaning or
semantics of a program.

14. How do N-gram Language Models work?

An N-gram language model predicts the probability of a given N-gram within any sequence of words in the
language. If we have a good N-gram model, we can predict p(w | h) – what is the probability of seeing the word w
given a history of previous words h – where the history contains n-1 words.

15. What is the purpose of Adaptive dynamic programming?

Adaptive dynamic programming (ADP) learns a model and a reward function from observations and then uses
value or policy iteration to obtain the utilities or an optimal policy. ADP makes optimal use of the local constraints
on utilities of states imposed through the neighborhood structure of the environment.

16. What are the stages in Relational based systems?

i. tokenization
ii. Complex word handling
iii. Basic groups
iv. Complex phrases
v. Merges structures

17. What are the merits and demirits in Direct Utility Estimation?

Advantages

It’s easy to understand

It doesn’t require any knowledge of T,R

It eventually computes the correct average values, using just sample transitions

Disadvantages

It wastes information about state connections

Each state must be learned separately

So, it takes a long time to learn

18.What is NLP?

NLP stands for Natural Language Processing, which is a part of Computer Science, Human language, and Artificial
Intelligence. It is the technology that is used by machines to understand, analyse, manipulate, and interpret
human's languages. It helps developers to organize knowledge for performing tasks such as translation, automatic
summarization, Named Entity Recognition (NER), speech recognition, relationship extraction, and topic
segmentation.

19. what are the Advantages of NLP

NLP helps users to ask questions about any subject and get a direct response within seconds.
NLP offers exact answers to the question means it does not offer unnecessary and unwanted information.

NLP helps computers to communicate with humans in their languages.

It is very time efficient.

Most of the companies use NLP to improve the efficiency of documentation processes, accuracy of documentation,
and identify the information from large databases.

20. What are the Applications of NLP?

There are the following applications of NLP -

1. Question Answering

Question Answering focuses on building systems that automatically answer the questions asked by humans in a
natural language.

2. Spam Detection

Spam detection is used to detect unwanted e-mails getting to a user's inbox.

3. Sentiment Analysis

Sentiment Analysis is also known as opinion mining. It is used on the web to analyse the attitude, behaviour, and
emotional state of the sender. This application is implemented through a combination of NLP (Natural Language
Processing) and statistics by assigning the values to the text (positive, negative, or natural), identify the mood of the
context (happy, sad, angry, etc.)

4. Machine Translation

Machine translation is used to translate text or speech from one natural language to another natural language.

5. Spelling correction

Microsoft Corporation provides word processor software like MS-word, PowerPoint for the spelling correction.

6. Information extraction

Information extraction is one of the most important applications of NLP. It is used for extracting structured
information from unstructured or semi-structured machine-readable documents.
 UNIT – IV

1 Define Language.
Language enables us to communicate most of what we have observed
about the environment.

2. Define Formal Language.

A formal language is defined as a set of strings of terminal symbols. It is
called as words.

3. What are the processes in communication?

i. Intention
ii. Generation
iii. Synthesis
iv. Perception
v. Analysis
vi Disambiguation
vii. Incorporation

4. What are the parts in analyze?

i. Syntactic Interpretation
ii. Semantic Interpretation
iii. Pragmatic Interpretation

5. Define Semantic Interpretation.

The process of extracting the meaning of an utterance an expression in
some representation language.

6. What are the processes of Relative clause.

i. Generating Good English sentences
ii. Over generation
iii. Under generation

7. Define Parsing.
Parsing is the process of finding a parse tree for a given input string.
It is also known as syntactic analysis.

8. What are the types of parsing?

i. Top down parsing
ii. Bottom up parsing
9. Define Top down parsing.
It starts with root node S and search for a tree that has the words as it
leaves.
10. Define Bottom up parsing.
We start from the leaf nodes (i.e.) with the words and search for a tree
with root S.

11. What are the algorithms to have efficient parsing?

i. Left to right parsing algorithm
ii. Chart Parsing algorithm.
iii. Left corner parsing

12. Define Augmentation.

The process of adding the existing rules of a grammar instead of
introducing new rules. It is called Augmentation.

13. Define DCG.

The method of rewriting the existing rules in the grammar by the
method of augmentation is called as DCG (Define Clause Grammar).

14. Define Sub categorization.

E 2 eliminates VP by mentioning which phrases can allow which
verbs which are known as sub categorization.

15. Define Ambiguity.

The sentence that does not provide exact meaning are called ambiguous
sentence.
16. What are the types of Ambiguity?
i. Lexical Ambiguity
ii. Syntactic Ambiguity
iii. Semantic Ambiguity

17. Define Disambiguation.

The speaker’s aim is to communicate some words in utterance and
hearer work is to get back the meaning of the world from the knowledge
of situation.

18. Define Discourse understanding.

A discourage is any string of language usually one that is more than one
sentence long.
 19. What are the two sub problems in discourse understanding?
i. Reference Resolution
ii. The structure of coherent discourse.

20. What are the tasks in probabilistic language model?

i. Information retrieval
ii. Information Extraction
iii. Machine Translation

UNIT – V
1. What exactly is a ROBOT?
A robot is a machine capable of sensing and interacting with its
environment.

2. Define manipulators?
An robotics, a manipulator is a device used to manipulate materials without direct
physical contact by the operator
3. Define Active Sensor?

Active sensors involve the emission of energy by a sensor apparatus into the environment, which is then
reflected back in some manner to the robot.

▪ Ultrasonic sensing
▪ Laser range finding are two common active sensor modalities
▪ rotation counter
▪ light sensor

4. Define Passive Sensor?

Passive sensors use energy naturally present in the environment to obtain information.

▪ Computer vision is a typical form of passive sensing

▪ Passivity is useful in military applications (where detection of the robot should be avoided)
▪ Passive sensors may consume less power
▪ A passive sensor's duty-cycle can be longer
▪ A passive sensor's reaction time can be less

5. Define Sonar Sensor?

Sonar is a popular sensor in robotics that employs acoustic pulses and
their echoes to measure the range to an object. Since the sound speed
is usually known, the object range is proportional to the echo travel
time.

6. What are Scanning lidars?

A LiDAR is an electronic component, and is part of the sensor family. ... The LiDAR
 acronym means Light Detection and Ranging. This is a calculation method which allows
to determine how far obstacles are from the sensor.

7. Define Tactile Sensor?

A tactile sensor is a device. It measures the coming information in response to the physical
interaction with the environment. The sense of touch in humans is generally modeled,
i.e. cutaneous sense and the kinesthetic sense.

8. Define Proprioceptive Sensor?

Proprioceptive sensors measure the state of the robot itself (wheel position or speed, battery
charge, etc.) while exteroceptive sensors measure the state of the environment

9. Define Inertial Sensor?

The inertial sensor, also known as the inertial navigation system (INS), uses an
accelerometer and gyro to determine spacecraft attitude in relation to the inertial system.
The accelerometer is used to test the motion acceleration of the carrier, which is then
used to calculate the real-time location of the carrier.

10. Define localization?

11. Define Monte Carlo localization?

The monteCarloLocalization System object™ creates a Monte Carlo localization (MCL)
object. The MCL algorithm is used to estimate the position and orientation of a vehicle
in its environment using a known map of the environment, lidar scan data, and
odometry sensor data.

12. Define Path Planning?

Path planning is a robotics field on its own. Its solution gives a feasible collision-free path for
going from one place to another. Humans do path planning without thinking how it is done.

13.What is Strong AI?

Strong AI is a theoretical form of machine intelligence which supports the view that machines
can really develop human consciousness equal to human beings. Strong AI refers to machines
or programs with the mind of their own and which can think and accomplish complex tasks
on their own without any human interference.

14. What is Weak AI?

Weak AI, also known as narrow AI, is artificial intelligence with limited functionality. Weak AI
refers to the use of advanced algorithms to accomplish specific problem solving or reasoning
tasks that do not encompass the full range of human cognitive abilities.