ARTIFICIAL INTELLIGENCE

UNIT-1
INTRODUCTION

Dr. Himanshu Rai (Asst. Professor)

Department of Computer Science & Engineering
United College of Engineering & Research,
Prayagraj
 Text Books
1) S. Russell and P. Norvig, “Artificial Intelligence: A Modern Approach”, Prentice Hall,
Third Edition, 2009.
2) I. Bratko, “Prolog: Programming for Artificial Intelligence”, Fourth edition, Addison-
Wesley Educational Publishers Inc., 2011.
3) M. Tim Jones, “Artificial Intelligence: A Systems Approach(Computer Science),
Jones and Bartlett Publishers, Inc. First Edition, 2008.
4) Nils J. Nilsson, "The Quest for Artificial Intelligence”, Cambridge University Press,
2009.
5) William F. Clocksin and Christopher S. Mellish, “Programming in Prolog: Using
the ISO Standard”, Fifth Edition, Springer, 2003.
6) Gerhard Weiss, ”Multi Agent Systems”, Second Edition, MIT Press, 2013.
7) David L. Poole and Alan K. Mackworth, “Artificial Intelligence: Foundations of
Computational Agents”, Cambridge University Press, 2010.
 Unit 1 : Introduction

 Introduction
 Definition
 Future of Artificial Intelligence
 Characteristics of Intelligent Agents
 Typical Intelligent Agents
 Problem Solving Approach to Typical AI problems.
 Lecture 1: History, Introduction and Definition

 Year 1943 : Warren McCulloch and Walter Pits proposed a model of artificial neurons.
 Year 1949: Donald Hebb proposed weight updating rule for modifying the connection strength
between neurons.
 Year 1950: Alan Turing publishes "Computing Machinery and Intelligence“, a test to check
the machine's ability to exhibit intelligent behavior equivalent to human intelligence.
 Year 1955: An Allen Newell and Herbert A. Simon created the "first artificial intelligence
program“ Which was named as "Logic Theorist". This program had proved 38 of 52
Mathematics theorems.
 Year 1956: The word "Artificial Intelligence" first adopted by American Computer scientist
John McCarthy at the Dartmouth Conference.
 Year 1966: Joseph Weizenbaum created the first chatbot , which was named as ELIZA.
 Year 1972: The first intelligent humanoid robot was built in Japan which was named as
WABOT-1.
 ----Continue

 The first AI winter (1974-1980):The duration between years 1974 to 1980 was the first AI
winter duration. AI winter refers to the time period where computer scientist dealt with a
severe shortage of funding from government for AI researches. During AI winters, an interest
of publicity on artificial intelligence was decreased.
 Year 1980-87: After AI winter duration, AI came back with "Expert System". Expert systems
were programmed that emulate the decision-making ability of a human expert.
 The second AI winter (1987-1993) :
 Year 1997: IBM Deep Blue beats world chess champion, Gary Kasparov, and became the first
computer to beat a world chess champion.
 Year 2002: for the first time, AI entered the home in the form of Roomba, a vacuum cleaner.
 Year 2006: Companies like Facebook, Twitter, and Netflix also started using AI.
 Deep learning, big data and artificial general intelligence (2011-present)
 Year 2011: IBM's Watson won jeopardy, a quiz show.
 --Continue

 Year 2012: Google has launched an Android app feature "Google now”.
 Year 2014: Chatbot "Eugene Goostman" won a competition in the infamous "Turing test“.
 Year 2018: The "Project Debater" from IBM debated on complex topics with two master
debaters and also performed extremely well. Google has demonstrated an AI program
"Duplex" which was a virtual assistant and which had taken hairdresser appointment on call,
and lady on other side didn't notice that she was talking with the machine.
 Now AI has developed to a remarkable level. The concept of Deep learning, big data, and data
science are now trending like a boom.
 Introduction

“The science and engineering of making intelligent machines,

especially intelligent computer programs”

-John McCarthy
 AI is study of how human brain think, learn, decide and work when it tries to solve
a problem.
 Finally this study outputs intelligent software systems.
• Aim of AI is to improve computer functions which are related to human knowledge
for example learning, reasoning and problem solving.
• AI is an approach to make a computer, a robot, or a product to think how smart
human thinks.
 AI Intelligence is intangible. It is composed of
-Reasoning
-Learning
- Problem Solving
- Perception
- Linguistic Intelligence
 Definition

 Artificial (man-made) & Intelligence(power of thinking)

 It means man-made thinking power

“It is a branch of computer science by which we can create intelligent machines

which can behave like humans, think like humans and able to make decision”

AI is machine’s ability to perform cognitive function as human do ,such as

perceiving, learning, reasoning and solving problems.
 Advantages

 Reduction in human errors

 Useful in risky areas
 High reliability
 Fast
 Digital assistant
 Faster decision
 Available 24*7

Disadvantages
 High cost
 can’t replace human
 Lack of creativity
 Risk of unemployment
 No feeling and emotions
 Lecture 2:Types of AI

 Type-1:Based on Capability
 Artificial Narrow Intelligence (ANI)
 Artificial General Intelligence (AGI)
 Artificial Super Intelligence (ASI)
 Type-2 : Based on Functionality
 Reactive Machines
 Limited Memory
 Theory of Minds
 Self- Awareness
 Type -1 : Based on Capability

 Artificial Narrow Intelligence

 Artificial Narrow Intelligence (ANI) also known as “Weak” AI.
 AI that exists in our world today.
 Narrow AI is AI that is programmed to perform a single task.
 whether it’s checking the weather, being able to play chess, or analyzing raw data
to write journalistic reports.
 Type -1 : Based on Capability

 Artificial General Intelligence

 Artificial General Intelligence (AGI) also known as “Strong” AI.
 It can perform variety of functions
 It is concept of machine with general intelligence that mimic human
intelligence or behaviours with ability to learn and apply it to solve any
problem.
 Type -1 : Based on Capability

 Artificial Super Intelligence(ASI)

 It is more capable than a human.
 ASI is hypothetical, means AI that doesn't mimic or understand human
intelligence and behaviours; ASI where machines become self-aware and surpass
capability of human intelligence and ability.
 ASI is purely speculative at this moment.
 Type -2 : Based on Functionality

 Reactive Machines
 These machines are most common form of AI applications.
 Such AI systems do not store or experiences for future actions.
 These machines focus only on current scenario and react on it as per best possible
action.
 Example : Deep Blue and IBM's chess playing super computer.
 Type -2 : Based on Functionality

 Limited Memory
 Limited memory machines can retain data for short period of time.
 While they can use this data for specific period of time. They cannot add
it to its library of their experiences.
 Many self-driving cars use limited memory model they store data such as
 Speed of nearby cars
 Distance of such cars
 The speed limits and other information that can help them navigate
on roads
 Type -2 : Based on Functionality

 Theory of Mind
 AI should understand human emotions, beliefs and should able to interact
socially.

 There are lot of efforts are going on to develop such machines.

 Type -2 : Based on Functionality

 Self-Awareness
 Self-awareness AI is future of artificial intelligence.
 These machines will be super intelligent and they will have
their own consciousness, sentiments and self-awareness.
 These machines will be more smarter than human mind.
 Hypothetical at this point.
 AI Applications

 Chatbots
 AI in healthcare
 Handwriting recognition
 Speech recognition
 Natural language processing
 AI in gaming
 AI in finance
 AI in robotics
 AI in security
 AI in social media
 AI in education
 Lecture 3 : Future of Artificial Intelligence

 Till now we are in era of narrow AI

 When machines become as intelligent as human then we say it as strong AI.
 It we be able to under stand and take decision like human.
 Similar to human, machines will be able to design another machine.
 Last level of AI is artificial super intelligence or singularity.
 On the basis of trends in development it is certain that singularity may arrive.
 When will AI Exceed Human Performance

 Advances in AI, will transform modern life by reshaping transportation, health,

science, military etc.
 Researchers predict AI will outperform humans in many activities in next 10
years and beyond :
 Translating languages by 2024
 Writing high-school level essay by 2026
 Driving a truck by 2027
 Working in retail by 2031
 Writing a bestselling book by 2049
 Surgery by 2053
 They believe , there is 50% chance of AI outperforming humans in next 45 years
and automating all human jobs in next 120 years
 Lecture 4: Intelligent agents

 Intelligent agents are autonomous entities that observe their

environment through sensors and act upon it using actuators. They
are designed to achieve specific goals or perform certain tasks
without continuous human intervention. The concept of intelligent
agents has been central to the development of various AI
applications, ranging from simple rule-based systems to complex
learning and adaptive systems.They may be simple or complex.
 A thermostat is considered an example of an intelligent agent, as is
a human being, as is any system that meets the definition.
 Characteristics of Intelligent Agents
 Autonomy: Intelligent agents operate without the need for constant
human guidance. They make decisions based on their programming,
goals, and the information they gather from their environment.

 Reactivity: They respond to changes in their environment in real-time.

This ability to react to stimuli makes them suitable for dynamic and
unpredictable environments.

 Pro-activeness: Intelligent agents are not just reactive; they can take
initiative and perform actions to achieve their goals.

 Social Ability: Some intelligent agents can communicate and

cooperate with other agents or humans to achieve complex tasks.

 Adaptability: Advanced intelligent agents can learn from their

experiences and adapt their behavior to new situations.
Agent
 Terminologies

 Percept: the agent’s perceptual inputs

 Percept sequence: the complete history of everything the agent
has perceived
 Agent function maps any given percept sequence to an action
[f: p*-> A]
 The agent program runs on the physical architecture to produce f
 Human Agent

In case of human agent

Sensors : eye, ear, nose, skin, tongue.
Actuators : mouth, arm, leg etc.
Example of Intelligent Agents
 Sensor: Sensor is a device which detects the change in the
environment and sends the information to other electronic
devices. An agent observes its environment through sensors.
 Actuators : Actuators are the component of machines that
converts energy into motion. The actuators are only
responsible for moving and controlling a system. An
actuator can be an electric motor, gears, rails, etc.
 Effectors: Effectors are the devices which affect the
environment. Effectors can be legs, wheels, arms, fingers,
wings, fins, and display screen.
 Structure of Agent

Structure of Agent = Architecture + Agent Program

Architecture : It is the machinery that the agent executes on. It is a
device with sensors and actuators, for example, a robotic car, a
camera, a PC.
Agent Program: It is an implementation of an agent function.
An agent function is a map from the percept sequence(history of all
that an agent has perceived to date) to an action.
 Rational Agent
 A rational agent is an agent which has clear preference, models
uncertainty, and acts in a way to maximize its performance measure
with all possible actions.
 A rational agent is said to perform the right things.
 AI is about creating rational agents to use for game theory and decision
theory for various real-world scenarios.
 For an AI agent, the rational action is most important because in AI
reinforcement learning algorithm, for each best possible action, agent
gets the positive reward and for each wrong action, an agent gets a
negative reward.
 Rationality

 The rationality of an agent is measured by its performance measure.

 Rationality can be judged on the basis of following points:
 Performance measure which defines the success criterion.
 Agent prior knowledge of its environment.
 Best possible actions that an agent can perform.
 The sequence of percept.
 Characteristics of Intelligent Agents

Internal characteristics are

 Learning/reasoning: An agent has the ability to learn from previous
experience and to successively adapt its own behaviour to the
environment
 Reactivity: an agent must be capable of reacting appropriately to
influences or information from its environment.
 Autonomy: an agent must have both control over its actions and internal
states. The degree of the agent’s autonomy can be specified. There may
need intervention from the user only for important decisions.
 Goal-oriented: an agent has well-defined goals and gradually influence
its environment and so achieve its own goals.
 -Continue

 External characteristics are

 Communication: an agent often requires an interaction
with its environment to fulfill its tasks, such as human,
other agents, and arbitrary information sources
 Cooperation: cooperation of several agents permits
faster and better solutions for complex tasks that exceed
the capabilities of a single agent.
 Mobility: an agent may navigate within electronic
communication networks.
 Character: like human, an agent may demonstrate an
external behavior with many human characters as
possible..
 Lecture 5: Agent Environment in AI

 An environment is everything in the world which surrounds

the agent, but it is not a part of an agent itself.

 An environment can be described as a situation in which an

agent is present.

 The environment is where agent lives, operates and provides

the agent with something to sense and act upon it.

 An environment is mostly said to be non-feministic.

 Features of Environment

As per Russell and Norvig, an environment can have various features from the point of
view of an agent:
1. Fully observable vs Partially Observable
2. Static vs Dynamic
3. Discrete vs Continuous
4. Deterministic vs Stochastic
5. Single-agent vs Multi-agent
6. Episodic vs Sequential
7. Known vs Unknown
8. Accessible vs Inaccessible
 Fully Observable vs Partially Observable

 If an agent sensor can sense or access the complete state of an environment at each
point of time then it is a fully observable environment, else it is partially observable.
 A fully observable environment is easy as there is no need to maintain the internal
state to keep track history of the world.
 An agent with no sensors in all environments then such an environment is called as
unobservable.
 --Continue

 For example, in a chess game, the state of the system, that is, the position of all the players on
the chess board, is available the whole time so the player can make an optimal decision such
environment is fully observable
 An example of a partially observable system would be a card game in which some of the cards
are discarded into a pile face down. In this case the observer is only able to view their own
cards and potentially those of the dealer.
 Deterministic vs Stochastic

 When a uniqueness in the agent’s current state completely determines the next state of the
agent, the environment is said to be deterministic.
 The stochastic environment is random in nature which is not unique and cannot be completely
determined by the agent.
 Example:
 Chess – There would be only a few possible moves for a coin at the current state and these
moves can be determined
 Self Driving Cars – The actions of a self-driving car are not unique, it varies time to time.
 Competitive vs Collaborative

An agent is said to be in a competitive environment when it competes

against another agent to optimize the output.

The game of chess is competitive as the agents compete with each

other to win the game which is the output.

An agent is said to be in a collaborative environment when multiple

agents cooperate to produce the desired output.

When multiple self-driving cars are found on the roads, they

cooperate with each other to avoid collisions and reach their
destination which is the output desired.
 Single-agent vs Multi-agent

 An environment consisting of only one agent is said to be a single-agent

environment.
 A person left alone in a maze is an example of the single-agent system.

 An environment involving more than one agent is a multi-agent environment.

 The game of football is multi-agent as it involves 11 players in each team.
 Dynamic vs Static

 An environment that keeps constantly changing itself when the agent is up

with some action is said to be dynamic.

 A roller coaster ride is dynamic as it is set in motion and the environment

keeps changing every instant.

 An idle environment with no change in its state is called a static environment.

 An empty house is static as there’s no change in the surroundings when an

agent enters.
 Discrete vs Continuous

 If an environment consists of a finite number of actions that can be deliberated in the

environment to obtain the output, it is said to be a discrete environment.

 The game of chess is discrete as it has only a finite number of moves. The number of
moves might vary with every game, but still, it’s finite.

 The environment in which the actions performed cannot be numbered ie. is not
discrete, is said to be continuous.

 Self-driving cars are an example of continuous environments as their actions are

driving, parking, etc. which cannot be numbered.
 Lecture 6 :Types of Agent

 Agents can be grouped into five classes based on their degree of perceived
intelligence and capability.
 All these agents can improve their performance and generate better action over the
time.
 These are given below:
• Simple Reflex Agent
• Model-based reflex agent
• Goal-based agents
• Utility-based agent
• Learning agent
 Simple Reflex Agent

 They ignore the rest of the percept history and act only on the basis of the current
percept.
 The agent function is based on the condition-action rule.
 A condition-action rule is a rule that maps a state i.e, condition to an action.
 If the condition is true, then the action is taken, else not.
 This agent function only succeeds when the environment is fully observable.
 For simple reflex agents operating in partially observable environments, infinite
loops are often unavoidable.
 It may be possible to escape from infinite loops if the agent can randomize its
actions.
----Continue
 --Continue

 Problems with Simple reflex agents are :

 Very limited intelligence.
 No knowledge of non-perceptual parts of the state.
 Usually too big to generate and store.
 If there occurs any change in the environment, then the collection of rules
need to be updated.
 Model-Based Reflex Agent

 It works by finding a rule whose condition matches the current situation.

 A model-based agent can handle partially observable environments by the use of
a model about the world.
 The agent has to keep track of the internal state which is adjusted by each
percept and that depends on the percept history.
 The current state is stored inside the agent which maintains some kind of
structure describing the part of the world which cannot be seen.
 Updating the state requires information about :
 how the world evolves independently from the agent
 the agent’s actions affect the world.
--Continue
Goal -Based Agent

 These kinds of agents take decisions based on how far they are currently from
their goal(description of desirable situations).
 Their every action is intended to reduce its distance from the goal.
 This allows the agent a way to choose among multiple possibilities, selecting the
one which reaches a goal state.
 The knowledge that supports its decisions is represented explicitly and can be
modified, which makes these agents more flexible.
 They usually require search and planning.
 The goal-based agent’s behavior can easily be changed.
Contd..
Initialize sensors and actuators
Load maps and traffic rules into Knowledge Base
Set Goal = "Transport passengers safely and efficiently"

while Goal is not achieved:

Read sensor data
Update Knowledge Base

if destination is reached:
Update Goal status as "achieved"
Stop vehicle
Exit loop

else if traffic signal is red:

Stop vehicle
Wait for green signal

else if obstacle is detected:

Calculate alternative path using RRT algorithm
Update Knowledge Base

else:
Plan path to destination using probabilistic roadmaps
Execute path

if emergency situation detected:

Activate emergency brakes
 Utility-Based Agents
 The agents which are developed having their end uses as building blocks are called utility-
based agents.
 When there are multiple possible alternatives, then to decide which one is best, utility-
based agents are used.
 They choose actions based on a preference (utility) for each state.
 Sometimes achieving the desired goal is not enough. We may look for a quicker, safer,
cheaper trip to reach a destination.
 Agent happiness should be taken into consideration. Utility describes how “happy” the
agent is. Because of the uncertainty in the world, a utility agent chooses the action that
maximizes the expected utility. A utility function maps a state onto a real number which
describes the associated degree of happiness.
 The agents which are developed having their end uses as building blocks are called utility-
based agents.
 When there are multiple possible alternatives, then to decide which one is best, utility-
based agents are used.
 They choose actions based on a preference (utility) for each state.
Contd...
Initialize sensors and actuators
Load historical stock data into Knowledge Base
Define Utility Function(U) = w1 * Profit - w2 * Risk - w3 * TransactionCost

while Market is open:

Read real-time stock data and news
Update Knowledge Base

for each stock in portfolio:

Calculate expected utility of buying, selling, or holding the stock
U_buy = w1 * ExpectedProfit_buy - w2 * Risk_buy - w3 * TransactionCost_buy
U_sell = w1 * ExpectedProfit_sell - w2 * Risk_sell - w3 * TransactionCost_sell
U_hold = w1 * ExpectedProfit_hold - w2 * Risk_hold - w3 * TransactionCost_hold

Choose action with maximum utility

if U_buy > U_sell and U_buy > U_hold:
Execute buy order
else if U_sell > U_buy and U_sell > U_hold:
Execute sell order
else:
Hold the stock

if Market conditions change significantly:

Re-evaluate Utility Function parameters (w1, w2, w3)
 Learning Agents
 A learning agent in AI is the type of agent that can learn from its past experiences or it
has learning capabilities.
 It starts to act with basic knowledge and then is able to act and adapt automatically
through learning.
 A learning agent has mainly four conceptual components, which are:
1. Learning element: It is responsible for making improvements by learning from the
environment
2. Critic: The learning element takes feedback from critics which describes how well
the agent is doing with respect to a fixed performance standard.
3. Performance element: It is responsible for selecting external action
4. Problem Generator: This component is responsible for suggesting actions that will
lead to new and informative experiences
Contd...
Lecture 7 :Problem Solving Approaches to Typical
AI Problems

 Problem-solving is commonly known as the method to reach the desired goal or

finding a solution to a given situation.
 In computer science, problem-solving refers to artificial intelligence techniques,
including various techniques such as forming efficient algorithms, heuristics, and
performing root cause analysis to find desirable solutions.
 In Artificial Intelligence, the users can solve the problem by performing logical
algorithms, utilizing polynomial and differential equations, and executing them using

modelling paradigms.
 Contd.....

 There can be various solutions to a single problem, which are achieved by different
heuristics.
 Also, some problems have unique solutions.
 It all rests on the nature of the given problem.
 Examples of Problems in AI
 Chess
 N-Queen problem
 Tower of Hanoi Problem
 Travelling Salesman Problem
 Water-Jug Problem
 Problem Solving Techniques

Following are some of the standard problem-solving techniques used in AI

 Heuristics
 Types of Searching Algorithms
 Evolutionary Computation
 Genetic Algorithms
Following are the four essential properties of search algorithms to compare the efficiency
of these algorithms:

Completeness: A search algorithm is said to be complete if it guarantees to return a

solution if at least any solution exists for any random input.

Optimality: If a solution found for an algorithm is guaranteed to be the best solution

(lowest path cost) among all other solutions, then such a solution for is said to be an
optimal solution.

Time Complexity: Time complexity is a measure of time for an algorithm to complete its
task.

Space Complexity: It is the maximum storage space required at any point during the
search, as the complexity of the problem.
Types of search algorithms:

Based on the search problems we can classify the search algorithms

into uninformed (Blind search) search and informed search (Heuristic
search) algorithms.
Uninformed/Blind Search:

•The uninformed search does not contain any domain knowledge such as closeness, the
location of the goal.
•Uninformed search applies a way in which search tree is searched without any information
about the search space like initial state operators and test for the goal, so it is also called
blind search.
•It examines each node of the tree until it achieves the goal node

Informed Search
• Informed search algorithms use domain knowledge. In an informed search, problem
information is available which can guide the search.
• Informed search strategies can find a solution more efficiently than an uninformed
search strategy.
• Informed search is also called a Heuristic search.
• A heuristic is a way which might not always be guaranteed for best solutions but
guaranteed to find a good solution in reasonable time.
 Heuristics

 The heuristic method helps comprehend a problem and devises a solution based purely
on experiments and trial and error methods.
 However, these heuristics do not often provide the best optimal solution to a specific
problem.
 Instead, these undoubtedly offer efficient solutions to attain immediate goals.
 Therefore, the developers utilize these when classic methods do not provide an efficient
solution for the problem.
 Since heuristics only provide time-efficient solutions and compromise accuracy, these
are combined with optimization algorithms to improve efficiency.
 Example: TSP

 The most common example of using heuristic is the Travelling Salesman problem.
 There is a provided list of cities and their distances.
 The user has to find the optimal route for the Salesman to return to the starting city
after visiting every city on the list.
 The greedy algorithms solve this NP-Hard problem by finding the optimal solution.
 According to this heuristic, picking the best next step in every current city provides
the best solution.
 Types of Searching Algorithms

 Informed Search
 Greedy Search
 A* Search
 Uninformed Search

 Breadth-First Search
 Depth First Search
 Uniform Cost Search
 Iterative Deepening Depth First Search
 Bidirectional Search
 Evolutionary Computation

 In computer science, evolutionary computation is a family of algorithms for global

optimization inspired by biological evolution.
 In technical terms, they are a family of population-based trial and error problem
solvers with a met heuristic or stochastic optimization character.

 In evolutionary computation, an initial set of candidate solutions is generated and

iteratively updated.
 Evolutionary computation techniques can produce highly optimized solutions in a
wide range of problem settings, making them popular in computer science.
 Genetic Algorithms

 A class of evolutionary computation methods

 A genetic algorithm is a search heuristic that is inspired by Charles Darwin's theory of
natural evolution.
 This algorithm reflects the process of natural selection where the fittest individuals are

selected for reproduction in order to produce offspring of the next generation.

 Computer vision
•Computer vision is a field of artificial intelligence (AI) that
enables computers and systems to derive meaningful information
from digital images, videos and other visual inputs — and take
actions or make recommendations based on that information.

•Examples:
•Image classification: it is able to accurately predict that a given image
belongs to a certain class.

•Object detection :

•Object tracking: follows or tracks an object once it is detected.

•Content-based image retrieval : uses computer vision to browse, search and

retrieve images from large data stores, based on the content of the images
rather than metadata tags associated with them.
Applications for computer vision
Controlling processes, e.g., an industrial robot;
 Navigation, e.g., by an autonomous vehicle or mobile robot;
 Detecting events, e.g., for visual surveillance or people counting;
 Organizing information, e.g., for indexing databases of images and
image sequences;
 Modeling objects or environments, e.g., medical image analysis or
topographical modeling;
 Interaction, e.g., as the input to a device for computer-human interaction,
and
 Automatic inspection, e.g., in manufacturing applications.
 Natural language processing
•Natural language processing (NLP) refers to the branch of computer
science—and more specifically, the branch of artificial intelligence or AI—
concerned with giving computers the ability to understand text and spoken
words in much the same way human beings can.

•Processing of Natural Language is required when you want an intelligent

system like robot to perform as per your instructions, when you want to hear
decision from a dialogue based clinical expert system, etc.

•The field of NLP involves making computers to perform useful tasks with
the natural languages humans use. The input and output of an NLP system
can be −
•Speech
•Written Text