ARTIFICIAL

INTELLIGENCE
KCA-301
 UNIT 1
Artificial Intelligence: Introduction to artificial
intelligence, Historical development and
foundation areas of artificial intelligence, Tasks
and application areas of artificial intelligence.
Introduction, types and structure of intelligent
agents, Computer Vision, Natural language
processing.
 Introduction To AI
• Artificial Intelligence is composed of two
words Artificial and Intelligence, where Artificial defines "man-
made," and intelligence defines "thinking power", hence AI means "a
man-made thinking power.“
• "It is a branch of computer science by which we can create intelligent
machines which can behave like a human, think like humans, and able
to make decisions."
• It is believed that AI ,there were Mechanical men in early days which
can work and behave like humans.
 Why Artificial Intelligence?
• With the help of AI, you can create such software or devices which
can solve real-world problems very easily and with accuracy such as
health issues, marketing, traffic issues, etc.
• With the help of AI, you can create your personal virtual Assistant,
such as Google Assistant, Siri, etc.
• With the help of AI, you can build such Robots which can work in an
environment where survival of humans can be at risk.
• AI opens a path for other new technologies, new devices, and new
Opportunities.
 Goals of Artificial Intelligence
• Replicate human intelligence

• Solve Knowledge-intensive tasks

• An intelligent connection of perception and action

• Building a machine which can perform tasks that requires human

intelligence such as:
– Proving a theorem

– Playing chess

– Plan some surgical operation

– Driving a car in traffic

• Creating some system which can exhibit intelligent behavior, learn new
 Foundation of Artificial Intelligence (What
Comprises to Artificial
Intelligence?)
Artificial Intelligence is not just a part of computer science
even it's so vast and requires lots of other factors which can
contribute to it. To create the AI first we should know that
how intelligence is composed, so the Intelligence is an
intangible part of our brain which is a combination of
Reasoning, learning, problem-solving perception, language
understanding, etc.
To achieve the above factors for a machine or software Artificial
Intelligence requires the following discipline:

o Mathematics
o Biology
o Psychology
o Sociology
o Computer Science
o Neurons Study
 Advantages of Artificial Intelligence
• High Accuracy with less errors: AI machines or systems are prone to less errors
and high accuracy as it takes decisions as per pre-experience or information.
• High-Speed: AI systems can be of very high-speed and fast-decision making,
because of that AI systems can beat a chess champion in the Chess game.
• High reliability: AI machines are highly reliable and can perform the same action
multiple times with high accuracy.
• Useful for risky areas: AI machines can be helpful in situations such as defusing a
bomb, exploring the ocean floor, where to employ a human can be risky.
• Digital Assistant: AI can be very useful to provide digital assistant to the users
such as AI technology is currently used by various E-commerce websites to show
the products as per customer requirement.
• Useful as a public utility: AI can be very useful for public utilities such as a self-
driving car which can make our journey safer and hassle-free, facial recognition for
security purpose, Natural language processing to communicate with the human in
human-language, etc.
 Disadvantages of Artificial Intelligence
• High Cost: The hardware and software requirement of AI is very costly as it requires
lots of maintenance to meet current world requirements.
• Can't think out of the box: Even we are making smarter machines with AI, but still
they cannot work out of the box, as the robot will only do that work for which they are
trained, or programmed.
• No feelings and emotions: AI machines can be an outstanding performer, but still it
does not have the feeling so it cannot make any kind of emotional attachment with
human, and may sometime be harmful for users if the proper care is not taken.
• Increase dependency on machines: With the increment of technology, people are
getting more dependent on devices and hence they are losing their mental capabilities.
• No Original Creativity: As humans are so creative and can imagine some new ideas
but still AI machines cannot beat this power of human intelligence and cannot be
creative and imaginative.
Application of AI
 Artificial Intelligence (AI) at Present
• "It is the ability of machines or computer-controlled robot to perform
task that are associated with intelligence." So, AI is computer science,
which aims to develop intelligent machines that can mimic human behavior.
• Based on capabilities, AI can be divided into three types that are:

• Narrow AI: It is capable of completing dedicated tasks with intelligence.

The current stage of AI is narrow AI.
• General AI: Artificial General Intelligence or AGI defines the machines
that can show human intelligence.
• Super AI: Super AI refers to self-aware AI with cognitive abilities that
surpass that of humans. It is a level where machines can do any task that a
human can do with cognitive properties.
 Future of Artificial Intelligence
• The future of Artificial Intelligence is bright in India, with many
organizations opting for AI automation.
• Automation in operational vehicles has created a buzz in the logistics
industry as it is expected that automated trucks/vehicles may soon be
used.
• Due to the bright scope of Artificial Intelligence in the future, the
number of AI start-ups is expected to increase in the coming years
 Jobs in AI
• Computational Philosopher - A computational philosopher concerned with
teaching human ethics and values in AI algorithms. For example, if a robot is being
developed for household chores, it should be designed to listen and follow orders
from its employer.
• Robot Personality Designer - A dedicated Robot Personality Designer designs the
digital personality of a machine/robot.
• Robot Obedience Trainer - A robotic obedience trainer teaches the machine/robot
to follow instructions and obey obstacles. With more and more robots being
introduced in homes, military strategies, etc., the future of Artificial Intelligence is
bright.
• Autonomous Vehicle Infrastructure Designer - An autonomous vehicle designer
develops digital interfaces that help them work independently. The scope of a bright
artificial intelligence future can fuel the development of autonomous vehicles in
various industries.
• Algorithmic Trainer / Click Worker - They work with AI algorithms and train
them to recognize instructions, emotions, moods, images, speech, etc. They train AI
algorithms to interact with their surroundings and take appropriate actions
autonomously.
 Continue…………
• AI Cyber Security Expert - An AI Cyber Security expert develops algorithms that
can identify the theft/risk associated with the system and take actions to eliminate it
autonomously. As new types of cyber attacks evolve every day, AI is being used in
cyber security to detect them. The future of Artificial Intelligence (AI Cyber
Security) is also bright in the Asia Pacific region.
• According to a report published by Forbes, AI job opportunities are continuously
increasing at 74% annually. It is a no-brainer that today, AI is one of the most in-
demand technologies, and it has an impact in almost every field. As a result, the
demand for AI professionals continues to grow. As the number of job opportunities
increases, it is the best time to explore your career in AI.
 Future impact of AI in different sectors
Healthcare:
• AI will play a vital role in the healthcare sector for diagnosing diseases quickly and more
accurately. New drug discovery will be faster and cost-effective with the help of AI. It will also
enhance the patient engagement in their care and also make ease appointment scheduling, bill
paying, with fewer errors. However, apart from these beneficial uses, one great challenge of AI
in healthcare is to ensure its adoption in daily clinical practices.
Cyber security:
Undoubtedly, cyber security is a priority of each organization to ensure data security. There are
some predictions that cyber security with AI will have :
• With AI tools, security incidents will be monitored.
• Identification of the origin of cyber-attacks with NLP.
• Automation of rule-based tasks and processes with the help of RPA bots.
• However, being a great technology, it can also be used as a threat by attackers. They can use AI
in a non-ethical way by using automated attacks that may be intangible to defend.
 Continue………..
Transportation:
• The fully autonomous vehicle is not yet developed in the transportation sector, but
researchers are reaching in this field. AI and machine learning are being applied in the
cockpit to help reduce workload, handle pilot stress and fatigue, and improve on-time
performance. There are several challenges to the adoption of AI in transportation,
especially in areas of public transportation. There's a great risk of over-dependence on
automatic and autonomous systems.

E-commerce:
• Artificial Intelligence will play a vital role in the e-commerce sector shortly. It will
positively impact each aspect of the e-commerce sector, ranging from user experience
to marketing and distribution of products. We can expect e-commerce with automated
warehouse and inventory, shopper personalization, and the use of chatbots in future.
 Continue………
Employment:
• Nowadays, employment has become easy for job seekers and simple
for employers due to the use of Artificial Intelligence. AI has already
been used in the job search market with strict rules and algorithms
that automatically reject an employee's resume if it does not fulfill the
requirement of the company. It is hoping that the employment process
will be driven by most AI-enabled applications ranging from marking
the written interviews to telephonic rounds in the future.
 Languages used in Artificial Intelligence
1. Python
• Python is one of the most powerful and easy programming languages that anyone can
start to learn. Python is initially developed in the early stage of 1991. Python also comes
with some default sets of standards libraries and also provides better community support
to its users. Further, Python is a platform-independent language and also provides an
extensive framework for Deep Learning, Machine Learning, and Artificial Intelligence.
• Python is also a portable language as it is used on various platforms such as Linux,
Windows, Mac OS, and UNIX.
• Python is an ideal programming language used for Machine Language, Natural
Processing Language (NLP), and Neural networks, etc. Due to the flexible nature of
Python, it can be used for AI development. It contains various pre-existing libraries
such as Pandas, SciPy etc. Further, Python also contains simple syntax and easy
coding, which makes Python the first choice of AI developers and programmers.
Languages used in Artificial Intelligence
Features of Python
• It is easy to learn than any other programming language.
• It is also a dynamically-typed language.
• Python is an Object-oriented language.
• It provides extensive community support and a framework for ML
and DL.
• Open-source.
• Large standard sets of libraries.
• Interpreted language.
 Languages used in Artificial Intelligence
2. Java
• Similar to Python, Java is also a platform-independent language as it can also be easily
implemented on various platforms. Further, Java is an object-oriented and scalable
programming language. The best thing about Java is once it is written and compiled on one
platform, then you do not need to compile it again and again. This is known as WORA (Once
Written Read/Run Anywhere) principle.

Features of Java
• Portability
• Cross-platform.
• Easy to learn and use.
• Easy-to-code Algorithms.
• Built-in garbage collector.
• Better user interaction.
 Languages used in Artificial Intelligence
3. Prolog
• Prolog is one of the oldest programming languages used for Artificial Intelligence
solutions. Prolog stands for "Programming in Logic", which was developed by
French scientist Alain Colmerauer in 1970.
• For AI programming in Prolog, developers need to define the rules, facts, and the
end goal. After defining these three, the prolog tries to discover the connection
between them.
• Prolog may not be a great programming language to build something big, but it's a
great language to study and think about problems in more logical ways rather than
procedural.
Features of Prolog
• Supports basic mechanisms such as
• Pattern Matching,
• Tree-based data structuring, and
• Automatic backtracking.
• Prolog is a declarative language rather than imperative.
 Languages used in Artificial Intelligence
4. Lisp
• Lisp was originally created as a practical mathematical notation for programs but
eventually became a top choice of developers in the field of AI.
• Although Lisp programming language is the second oldest language after Fortran, it is still
being used because of its crucial features.
• It has various deficiencies, such as lack of well-known libraries, not so-human-friendly
syntax, etc. Due to this reason, it is not preferred by the programmers.
Features of LISP
• The program can be easily modified, similar to data.
• Make use of recursion for control structure rather than iteration.
• Garbage Collection is necessary.
• We can easily execute data structures as programs.
 Languages used in Artificial Intelligence
5. R
• R is one of the great languages for statistical processing in programming. However,
R supports free, open-source programming language for data analysis purposes. It
may not be the perfect language for AI, but it provides great performance while
dealing with large numbers.

Features of R programming
• R is an open-source programming language, which is free of cost, and also you can
add packages for other functionalities.
• R provides strong & interactive graphics capability to users.

• It enables you to perform complex statistical calculations.

• It is widely used in machine learning and AI due to its high-performance

capabilities.
 Languages used in Artificial Intelligence
6. Julia
• Julia is one of the newer languages on the list and was created to focus on performance computing in
scientific and technical fields. Julia includes several features that directly apply to AI programming.

Features of Julia
• Common numeric data types.
• Arbitrary precision values.
• Robust mathematical functions.
• Tuples, dictionaries, and code introspection.
• Built-in package manager.
• Dynamic type system.
• Ability to work for both parallel and distributed computing.
• Macros and metaprogramming capabilities.
• Support for multiple dispatches.
• Support for C functions.
 Languages used in Artificial Intelligence
7. C++
• C++ language has been present for so long around, but still being a top and popular
programming language among developers. It provides better handling for AI models
while developing.
• Although C++ may not be the first choice of developers for AI programming, various
machine learning and deep learning libraries are written in the C++ language.

Features of C++
• C++ is one of the fastest languages, and it can be used in statistical techniques.
• It can be used with ML algorithms for fast execution.
• Most of the libraries and packages available for Machine learning and AI are written
in C++.
• It is a user friendly and simple language.
Types of Artificial Intelligence:
Artificial Intelligence can be divided in various types, there are mainly two types of main
categorization which are based on capabilities and based on functionally of AI. Following
is flow diagram which explain the types of AI.
 AI type-1: Based on Capabilities
1. Weak AI or Narrow AI:
o Narrow AI is a type of AI which is able to perform a dedicated task with
intelligence. The most common and currently available AI is Narrow AI in
the world of Artificial Intelligence.
o Narrow AI cannot perform beyond its field or limitations, as it is only
trained for one specific task. Hence it is also termed as weak AI. Narrow AI
can fail in unpredictable ways if it goes beyond its limits.
•
Apple Siri is a good example of Narrow AI, but it operates with a limited
pre-defined range of functions.
o IBM's Watson supercomputer also comes under Narrow AI, as it uses an
Expert system approach combined with Machine learning and natural
language processing.
o Some Examples of Narrow AI are playing chess, purchasing suggestions on
e-commerce site, self-driving cars, speech recognition, and image
recognition.
2. General AI:
o General AI is a type of intelligence which could perform any
intellectual task with efficiency like a human.
o The idea behind the general AI to make such a system which
could be smarter and think like a human by its own.
o Currently, there is no such system exist which could come under
general AI and can perform any task as perfect as a human.
o The worldwide researchers are now focused on developing
machines with General AI.
o As systems with general AI are still under research, and it will
take lots of efforts and time to develop such systems.
3. Strong AI:
o Strong AI is a level of Intelligence of Systems at
which machines could surpass human intelligence,
and can perform any task better than human with
cognitive properties. It is an outcome of general AI.
o Some key characteristics of strong AI include
capability include the ability to think, to reason, solve
the puzzle, make judgments, plan, learn, and
communicate by its own.
o Super AI is still a hypothetical concept of Artificial
Intelligence. Development of such systems in real is
still world changing task.
 Artificial Intelligence type-2: Based on functionality

1. Reactive Machines
o Purely reactive machines are the most basic types of Artificial
Intelligence.
o Such AI systems do not store memories or past
experiences for future actions.
o These machines only focus on current scenarios and react
on it as per possible best action.
o IBM's Deep Blue system(supercomputer developed by
IBM specifically for playing chess) is an example of
reactive machines.
o Google's AlphaGo is also an example of reactive machines.
2. Limited Memory
o Limited memory machines can store past experiences or
some data for a short period of time.
o These machines can use stored data for a limited time
period only.
o Self-driving cars are one of the best examples of Limited
Memory systems. These cars can store recent speed of
nearby cars, the distance of other cars, speed limit, and
other information to navigate the road.
3. Theory of Mind
o Theory of Mind AI should understand the human
emotions, people, beliefs, and be able to interact socially
like humans.
o This type of AI machines are still not developed, but
researchers are making lots of efforts and improvement
for developing such AI machines.

4. Self-Awareness
o Self-awareness AI is the future of Artificial Intelligence.
These machines will be super intelligent, and will have
their own consciousness, sentiments, and self-awareness.
o These machines will be smarter than human mind.
o Self-Awareness AI does not exist in reality still and it is a
hypothetical concept.
 AI Agents
• Artificial Intelligence is defined as the study of rational agents. A
rational agent may take the form of a person, firm, machine, or
software to make decisions.
• An AI system is made up of an agent and its environment. Agents
work in their environment, and the environment may include other
agents. The agents sense the environment through sensors and act on
their environment through actuators. An AI agent can have mental
properties such as knowledge, belief, intention, etc.
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.
 Intelligent Agents:

There are software programs that work in background to

carryout specific, predictable, repetitive task for an
individual user. Alan Turing suggested that a system or
agent can be said to be intelligent when the agent’s
performance cannot be distinguished from that of a
human performing the same task.

An intelligent agent is a software entity which senses its

environment and then carries out some set of operations
on behalf of a user with some amount of autonomy and to
do so , it employs some knowledge or representation of
the end user’s goal.
For Example:
1. A human agent has eyes, ears ,noses etc as sensors while
hands, legs, mouths are actuators.
2. Software agents receives keystrokes, files, packets are
sensory inputs and acts on the environment by
displaying on the screen, writing files and sending
packets over the network.
 Intelligent Agents:

Following are the main four rules for an AI agent:

Rule 1: An AI agent must have the ability to perceive the

environment.
Rule 2: The observation must be used to make decisions.
Rule 3: Decision should result in an action.
Rule 4: The action taken by an AI agent must be a rational
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.

Goals of Agents:
1. High Performance
2. Optimized Result
3. Rational Action

Agent -> Percept -> Decision -> Actions

 Types of Agents
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:

o Simple Reflex Agent

o Model-based reflex agent
o Goal-based agents
o Utility-based agent
o Learning agent
 Types of Agents
1. Simple reflex agent:
• Simple reflex agents ignore the rest of the concept history and act only based on the
current concept.
• The agent function is based on the condition-action rule. A condition-action rule is a
rule that maps a state, that is, a condition, to an action. If the condition is true, then
action is taken; otherwise, not.
• This agent function succeeds only when the environment is fully observable.

The problems with simple reflex agents are:

• Very limited intelligence.

• There is no knowledge of the non-perceptual parts of the state.

• It is usually too large to generate and store.

• If a change occurs in the environment, the rules collection needs to be updated.

 Types of Agents
2. Model-based reflex agents:
• It works by searching for a rule whose position
matches the current state. A model-based agent can
handle a partially observable environment using a
model about the world.
• Agent keeps track of internal state which is adjusted
by each percept and that depends on percept history
Updating the state requires information about:
• how the world develops independently of the agent,
and
• How the agent's actions affect the world.
 Types of Agents

3. Goal-based agents
• These types of agents make decisions based on how far
they are currently from their goals (details of desired
conditions). Their every action is aimed at reducing its
distance from the target. This gives the agent a way to
choose from a number of possibilities, leading to a
target position. The behavior of a target-based agent can
be easily changed. Goal based agents based on
 Types of Agents
4. Utility-based agents

 These agents are similar to the goal-based agent but

provide an extra component of utility measurement
which makes them different by providing a measure
of success at a given state.
 Utility-based agent act based not only goals but also
the best way to achieve the goal.
 The Utility-based agent is useful when there are
multiple possible alternatives, and an agent has to
choose in order to perform the best action. They
choose actions based on a preference (utility) for
each state. Eg. GPS
 Types of Agents
5. Learning Agent:
• 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:
 Learning element: It is responsible for making improvements by learning
from the environment
 Critic: The learning element takes feedback from critics which describe
how well the agent is doing with respect to a fixed performance standard.
 Performance element: It is responsible for selecting external action
 Problem Generator: This component is responsible for suggesting actions
that will lead to new and informative experiences.
 Structure of AI Agents
• Structure of Intelligent Agents- We must be familiar with the
architecture and agent programs. Architecture is the machinery on which the agent
executes. It is a device with sensors and actuators, for example, a robot car, a
camera, a PC. An agent program is an implementation of an agent function. An
agent function concept is a map from the sequence (the history of all that an agent
has considered to date).
agent = architecture + agent program
• The human agent has eyes, ears, and other organs that act as sensors, and hands,
feet, mouth, and other body parts act as actuators.
 AI Agents Characteristic
“An agent is a computer software system whose characteristics are “:
Situatedness
• When an Agent receives some form of sensory input from its environment, it then
performs some actions that change its environment in some way.
Autonomy
• An agent is able to act without direct intervention from humans or other agents. This
type of agent has almost complete control over it own actions and internal state.
Adapitvity
• It is capable of reacting flexibly to changes within its environment. It is able to accept
goal directed initiatives when appropriate and is also capable of learning from it's own
experiences, environment and interaction with others.
Sociability
• The agent is capable of interacting in a peer-to-peer manner with other agents or
humans.
Design Considerations
• One of the most important aspects of intelligent agents is the design of the actual
agent. The agent needs to be able to fulfill the tasks that are required from it, i.e. to
achieve its goals.
AI Agents Characteristic

• Adaptability
• Memory
• Feedback Sensitivity
• Decision Making Ability
• Exploration
• Generalization
• Performance Improvement Over Time
 PEAS Representation
PEAS is a type of model on which an AI agent works
upon. When we define an AI agent or rational agent,
then we can group its properties under PEAS
representation model. It is made up of four words:
 P: Performance measure – It is the output we get from
an agent i.e. results obtained after agent processing
 E: Environment- All surrounding things and
conditions.
 A: Actuators- Devices like hardware /software
through which agents performs actions on
environment
 S: Sensors – Devices from which the agents perceives
observation from environment
Here performance measure is the objective for
 PEAS for self-driving cars

Let's suppose a self-driving car then PEAS representation will be:

Performance: Safety, time, legal drive, comfort

Environment: Roads, other vehicles, traffic signals, road signs,

pedestrian

Actuators: Steering, accelerator, brake, signal, horn

Sensors: Camera, GPS, speedometer, odometer, accelerometer, sonar.

Agent Performance Environment Actuators Sensors
measure

1. o Healthy o Patient o Tests Keyboard

Medical patient o Hospital o Treatments (Entry of symptoms)
Diagnose Minimized
o o Staff
cost

2. o Cleanness o Room o Wheels Camera

Vacuum o Efficiency o Table o Brushes
Cleaner Dirt detection sensor
o Battery o Wood o Vacuum
life floor Extractor Cliff sensor
o Security o Carpet
Bump Sensor
o Various
obstacles Infrared Wall Sensor

3. Part - o Percentage o Conveyor o Jointed o Camera

picking of parts in belt with Arms
Robot correct parts, Joint angle sensors.
o Hand
bins. o Bins
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, operate and provide
the agent with something to sense and act upon it.
Features of Environment

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
1. Fully observable vs Partially Observable:
• A fully observable environment is one in which the agent has complete
information about the current state of the environment. The agent has
direct access to all environmental features that are necessary for making
decisions. Examples of fully observable environments include board
games like chess or checkers.
• Real-life Example: While running a car on the road ( Environment ),
The driver ( Agent ) is able to see road conditions, signboard and
pedestrians on the road at a given time and drive accordingly. So Road is
a fully observable environment for a driver while driving the car.

• A partially observable environment is one in which the agent does not

have complete information about the current state of the environment.
The agent can only observe a subset of the environment, and some
aspects of the environment may be hidden or uncertain. Examples of
partially observable environments include driving a car in traffic.
• Real-life Example: Playing card games is a perfect example of a
partially-observable environment where a player is not aware of the
card in the opponent’s hand. Why partially-observable? Because the other
parts of the environment, e.g opponent, game name, etc are known for the
player (Agent).
• An agent with no sensors in all environments then such an environment is called as
unobservable.
2. Deterministic vs Stochastic:

• If an agent's current state and selected action can completely determine

the next state of the environment, then such environment is called a
deterministic environment. The state of the environment completely
determines the result of an agent's action. an a deterministic
environment, the agent's actions have a one-to-one correspondence with
the resulting outcomes. Examples of deterministic environments
include simple mathematical equations, where the outcome of each
operation is precisely defined.
• Real-life Example: The traffic signal is a deterministic environment
where the next signal is known for a pedestrian (Agent)

• A stochastic environment is random in nature and cannot be

determined completely by an agent.

• A stochastic environment is one in which the outcome of an action is

uncertain and involves probability. The state of the environment only
partially determines the result of an agent's action, and there is a degree
of randomness or unpredictability in the outcome.
• Examples of stochastic environments include games of chance like
poker or roulette, where the outcome of each action is influenced by
random factors like the shuffle of cards or the spin of a wheel.

• Real-life Example: The radio station is a stochastic environment where the

listener is not aware about the next song or playing a soccer is stochastic
environment.
3. Episodic vs Sequential:

o In an episodic environment, there is a series of one-shot actions,

and only the current percept is required for the action i.e. Episodic
is an environment where each state is independent of each other.
The action on a state has nothing to do with the next state .
o An episodic environment is one in which the agent's actions do not
affect the future states of the environment.
o Real-life Example: A support bot (agent) answer to a question and
then answer to another question and so on. So each question-answer
is a single episode.

o However, in Sequential environment, an agent requires memory of

past actions to determine the next best actions.
o A sequential environment is one in which the agent's actions affect
the future states of the environment. The goal of the agent is to
maximize the cumulative reward obtained over multiple
interactions.
• Examples of sequential environments include robotics
applications or video games. The agent must use techniques
like dynamic programming or reinforcement learning to learn
the optimal policy over multiple interactions.

• Real-life Example: Playing tennis is a perfect example where

a player observes the opponent’s shot and takes action.
4. Single-agent vs Multi-agent

o If only one agent is involved in an environment, and operating by itself

then such an environment is called single agent environment. This
environment is explored by a single agent. All actions are performed by a
single agent in the environment.
o Real-life Example: Playing tennis against the ball is a single agent
environment where there is only one player.
o Examples of single-agent environments include puzzles and mazes. The
agent must use search algorithms or planning techniques to find a path to its
goal state.
o However, if multiple agents are operating in an environment, then such
an environment is called a multi-agent environment.
o A multi-agent environment is one in which multiple agents interact with each
other and the environment to achieve their individual or collective goals.
Examples of multi-agent environments include multiplayer games and
traffic simulations. The agents must use game theory or multi-agent
reinforcement learning techniques to optimize their behavior.
o Real-life Example: Playing a soccer match is a multi-agent environment.
5. Static vs Dynamic:

• The Static environment is completely unchanged while an agent is

precepting the environment.
• Real-life Example: Cleaning a room (Environment) by a dry-cleaner robot
(Agent ) is an example of a static environment where the room is static
while cleaning.
• A static environment is one in which the environment does not change over
time. The state of the environment remains constant, and the agent's actions
do not affect the environment. Examples of static environments include
mathematical problems or logic puzzles. The agent can use techniques
like search algorithms or decision trees to optimize its behavior.

• A dynamic environment is one in which the environment changes over

time. The state of the environment evolves based on the actions of the agent
and other factors, and the agent's actions can affect the future state of the
environment. Examples of dynamic environments include video games
or robotics applications. The agent must use techniques like planning
or reinforcement learning to optimize its behavior in response to the
changing environment. Taxi driving is an example of a dynamic
environment whereas Crossword puzzles are an example of a static
environment.
Real-life Example: Playing soccer is a dynamic environment where players’
positions keep changing throughout the game. So a player hit the ball by observing
the opposite team.
6. Discrete vs Continuous:

o If in an environment there are a finite number of percepts and actions that

can be performed within it, then such an environment is called a discrete
environment else it is called continuous environment.
o Discrete Environment consists of a finite number of states and agents
have a finite number of actions.
o Real-life Example: Choices of a move (action) in a tic-tac game are
finite on a finite number of boxes on the board (Environment).

o While in a Continuous environment, the environment can have an

infinite number of states. So the possibilities of taking an action are also
infinite.
o Real-life Example: In a basketball game, the position of players
(Environment) keeps changing continuously and hitting (Action) the ball
towards the basket can have different angles and speed so infinite
possibilities.
o A chess game comes under discrete environment as there is a finite
number of moves that can be performed.
o A self-driving car is an example of a continuous environment.
7. Known vs Unknown
o Known and unknown are not actually a feature of an environment, but it is
an agent's state of knowledge to perform an action.
o A known environment is one in which the agent has complete knowledge
of the environment's rules, state transitions, and reward structure. The
agent knows exactly what actions are available to it, and the outcome of
each action is known with certainty. Examples of known environments
include chess or tic-tac-toe games. In a known environment, the agent can
use techniques like search algorithms or decision trees to optimize its
behavior.
o 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.
o An unknown environment is one in which the agent has limited or no
knowledge about the environment's rules, state transitions, and reward
structure. The agent may not know what actions are available to it, or the
outcome of each action may be uncertain. Examples of unknown
environments include exploration tasks or real-world applications.
o It is quite possible that a known environment to be partially
observable and an Unknown environment to be fully
observable.

8. Accessible vs Inaccessible

o If an agent can obtain complete and accurate information

about the state's environment, then such an environment is
called an Accessible environment else it is called
inaccessible.
o An empty room whose state can be defined by its temperature
is an example of an accessible environment.
o Information about an event on earth is an example of
Inaccessible environment.
 The Nature of Environments

• The most famous artificial environment is the Turing test environment, in which a
real and other artificial agents are tested on an equal basis. This is a very
challenging environment as it is extremely difficult for a software agent to perform
side-by-side with a human.
Turing Test
• The success of a system's intelligent behavior can be measured with the Turing test.
• Two persons and a machine to be evaluated participate in the test. One of the two
persons plays the role of the examiner. Each of them is sitting in different rooms.
The examiner is unaware of who is a machine and who is a human. He inquires by
typing the questions and sending them to both intelligences, for which he receives
typed responses.
• The purpose of this test is to fool the tester. If the tester fails to determine the
response of the machine from the human response, the machine is said to be
intelligent.
 PEAS Description for
Internet Shopping Agent
PEAS Description for Internet Shopping Agent

PEAS description

Performance measure: price, quality, appropriateness, efficiency

Environment: current and future WWW sites, vendors, shippers
Actuators: display to user, follow URL, fill in form
Sensors: HTML pages (text, graphics, scripts)

Environment Characteristics:

Fully observable: No
Deterministic: Partly // partially observable
Episodic: No // sequential
Static: Semi // the world changes partly while the agent is thinking
Discrete: Yes
Single-agent: No // multi-agent
 NLP (Natural Language Processing)
• Natural language processing strives to build machines that understand
and respond to text or voice data—and respond with text or speech of
their own—in much the same way humans do.

• 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.

• NLP combines computational linguistics—rule-based modeling of

human language—with statistical, machine learning, and deep learning
models. Together, these technologies enable computers to process
human language in the form of text or voice data and to ‘understand’
its full meaning, complete with the speaker or writer’s intent and
sentiment.
• NLP drives computer programs that translate text from one
language to another, respond to spoken commands, and
summarize large volumes of text rapidly— even in real time.

• NLP is used to understand the structure and meaning of human

language by analyzing different aspects like syntax, semantics,
pragmatics, and morphology. Then, computer science
transforms this linguistic knowledge into rule-based, machine
learning algorithms that can solve specific problems and
perform desired tasks.

• Take Gmail, for example. Emails are automatically categorized

as Promotions, Social, Primary, or Spam, thanks to an NLP task
called keyword extraction. By “reading” words in subject lines
and associating them with predetermined tags, machines
automatically learn which category to assign emails.
NLP TASKS

• Syntactic analysis, also known as parsing or syntax analysis,

identifies the syntactic structure of a text and the dependency
relationships between words, represented on a diagram called a
parse tree.

• Semantic analysis focuses on identifying the meaning of

language. However, since language is polysemic and ambiguous,
semantics is considered one of the most challenging areas in NLP.
Semantic tasks analyze the structure of sentences, word
interactions, and related concepts, in an attempt to discover the
meaning of words, as well as understand the topic of a text.
NLP TASKS
• Speech recognition, also called speech-to-text, is the task of
reliably converting voice data into text data. Speech recognition
is required for any application that follows voice commands or
answers spoken questions. What makes speech recognition
especially challenging is the way people talk—quickly, slurring
words together, with varying emphasis and intonation, in different
accents, and often using incorrect grammar.
• Tokenization: Tokenization is an essential task in natural
language processing used to break up a string of words into
semantically useful units called tokens. Sentence tokenization
splits sentences within a text, and word tokenization splits words
within a sentence. Generally, word tokens are separated by blank
spaces, and sentence tokens by stops. However, you can perform
high-level tokenization for more complex structures, like words
that often go together, otherwise known as collocations (e.g., New
York).
• Part of speech tagging, also called grammatical tagging, is the
process of determining the part of speech of a particular word
or piece of text based on its use and context. Some common
PoS tags are verb, adjective, noun, pronoun, conjunction,
preposition, intersection, among others.

Here’s an example:
Customer service couldn’t be better! = “customer service”
“could” “not” “be” “better”.
In this case, the example above would look like this:

“Customer service”: NOUN, “could”: VERB, “not”: ADVERB,

be”: VERB, “better”: ADJECTIVE, “!”: PUNCTUATION

PoS tagging is useful for identifying relationships between words

and, therefore, understand the meaning of sentences.
• Named Entity Recognition (NER): Named entity recognition
is one of the most popular tasks in semantic analysis and
involves extracting entities from within a text. Entities can be
names, places, organizations, email addresses, and more.
Relationship extraction, another sub-task of NLP, goes one step

further and finds relationships between two nouns. For

example, in the phrase “Susan lives in Los Angeles,” a person
(Susan) is related to a place (Los Angeles) by the semantic
category “lives in.”

• Word sense disambiguation is the selection of the meaning of

a word with multiple meanings through a process of semantic
analysis that determine the word that makes the most sense in
the given context. Depending on their context, words can have
different meanings..
Take the word “book”, for example:

 You should read this book; it’s a great novel!

 You should book the flights as soon as possible.
 You should close the books by the end of the year.

There are two main techniques that can be used for word sense
disambiguation (WSD): knowledge-based (or dictionary
approach) or supervised approach. The first one tries to infer
meaning by observing the dictionary definitions of ambiguous
terms within a text, while the latter is based on natural language
processing algorithms that learn from training data.

• Text Classification: Text classification is the process of

understanding the meaning of unstructured text and organizing
it into predefined categories (tags). One of the most popular
text classification tasks is sentiment analysis, which aims to
categorize unstructured data by sentiment.
Common Examples of NLP

 Email filters
 Virtual assistants, voice assistants, or smart speakers
 Online search engines
 Predictive text and autocorrect
 Monitor brand sentiment on social media
 Sorting customer feedback
 Automating processes in customer support
 Chatbots
 Automatic summarization
 Machine translation
 Natural language 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.”

If AI enables computers to think, computer vision enables them to

see, observe and understand.

Computer vision works much the same as human vision, except

humans have a head start. Human sight has the advantage of
lifetimes of context to train how to tell objects apart, how far
away they are, whether they are moving and whether there is
something wrong in an image.
Computer vision trains machines to perform these functions, but it
has to do it in much less time with cameras, data and algorithms.
How does computer vision work?
Computer vision needs lots of data. It runs analyses of data over and over
until it discerns distinctions and ultimately recognize images. For example, to
train a computer to recognize automobile tires, it needs to be fed vast
quantities of tire images and tire-related items to learn the differences and
recognize a tire, especially one with no defects.

Two essential technologies are used to accomplish this: a type of machine

learning called deep learning and a convolutional neural network (CNN).

Machine learning uses algorithmic models that enable a computer to teach

itself about the context of visual data. If enough data is fed through the
model, the computer will “look” at the data and teach itself to tell one image
from another. Algorithms enable the machine to learn by itself, rather than
someone programming it to recognize an image.
A CNN helps a machine learning or deep learning model “look” by breaking
images down into pixels that are given tags or labels. It uses the labels to
perform convolutions (a mathematical operation on two functions to produce a
third function) and makes predictions about what it is “seeing.” The neural
network runs convolutions and checks the accuracy of its predictions in a series
of iterations until the predictions start to come true. It is then recognizing or
seeing images in a way similar to humans.

Much like a human making out an image at a distance, a CNN first discerns
hard edges and simple shapes, then fills in information as it runs iterations of its
predictions. A CNN is used to understand single images. A recurrent neural
network (RNN) is used in a similar way for video applications to help
computers understand how pictures in a series of frames are related to one
another.
Computer vision applications

• IBM used computer vision to create My Moments for the 2018 Masters golf
tournament. IBM Watson watched hundreds of hours of Masters footage and
could identify the sights (and sounds) of significant shots. It curated these
key moments and delivered them to fans as personalized highlight reels.

• Google Translate lets users point a smartphone camera at a sign in another

language and almost immediately obtain a translation of the sign in their
preferred language.

• The development of self-driving vehicles relies on computer vision to make

sense of the visual input from a car’s cameras and other sensors. It’s
essential to identify other cars, traffic signs, lane markers, pedestrians,
bicycles and all of the other visual information encountered on the road.
Computer vision tasks

• Image classification sees an image and can classify it (a dog, an apple, a

person’s face). More precisely, it is able to accurately predict that a given
image belongs to a certain class. For example, a social media company
might want to use it to automatically identify and segregate objectionable
images uploaded by users.
• Object detection can use image classification to identify a certain class of
image and then detect and tabulate their appearance in an image or video.
Examples include detecting damages on an assembly line or identifying
machinery that requires maintenance.
• Object tracking follows or tracks an object once it is detected. This task is
often executed with images captured in sequence or real-time video feeds.
Autonomous vehicles, for example, need to not only classify and detect
objects such as pedestrians, other cars and road infrastructure, they need to
track them in motion to avoid collisions and obey traffic laws.
• 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.
THANK YOU