Unit 1

Introduction

Prepared by –
Sourajit Maity
 Introduction of AI
 AI 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”.

AI vs. Machine Learning vs.
Deep Learning
 What is Artificial
Intelligence
 Artificial Intelligence is a branch of computer science by which
we can create intelligent machines that can behave like a
human, think like humans and also able to make decisions or
draw useful conclusions about the world around us.

 According to the father of AI John McCarthy, it is

“ The Science & Engineering of making intelligent machines,

especially intelligent computer programs.”
Why Artificial Intelligence
 With the help of AI, we 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, we can create our personal virtual assistant
such as Cortona, Google Assistant, Siri etc.

 With the help of AI, we 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 task that requires

human intelligence like playing chess, driving a car etc.

 Creating some systems which can learn new things by itself,

demonstrate, explain and can advise to it’s user.
 Problems in Artificial
Intelligence
 Solving formal tasks such as Game Playing & Theorem Proving.

 Common Sense Reasoning such as reasoning about physical objects

and their relationships to each other like performing symbolic
manipulations of logical expressions etc.

 Vision Perception – Visual Perception

 Speech Recognition in machine – Natural Language Understanding

 Others – Financial Analysis, Medical Diagnosis, Engineering Design &

Planning, Scientific Analysis
 AI Techniques
 There are two parts of an AI Technique :-

a) The knowledge Representation, which is used to capture the

knowledge about the real world.

b) The Search Algorithm, which is used to find the solution to

the problem.
Various approaches to AI
 Based on Capabilities
1. Artificial Narrow Intelligence (ANI) / Weak AI /
Narrow AI :
 It has a narrow range of capabilities.

 Weak 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.

 Examples - Virtual assistants (Siri, Alexa, Cortana),

Image/facial recognition software, Email spam filters.
 Based on Capabilities
2. Artificial General Intelligence (AGI) / Deep AI /
Strong AI :
 It can able to perform any intellectual task with efficiency like a
human.
 The idea behind the general AI is to make such a system which could
be smarter and think like a human by its own.
 Strong AI can perform a variety of functions, eventually teaching itself
to solve for new problems.
 In theory, then, anything a human can do, a strong AI can do too.
 AI researchers and scientists have not yet achieved strong AI.
 Example - Self-driving cars.
 Based on Capabilities
3. Artificial Super Intelligence (ASI) / Super AI :
 It is more capable than a human.

 ASI is the hypothetical AI that doesn’t just mimic or understand

human intelligence and behaviour; ASI is where machines
become self-aware and surpass the capacity of human
intelligence and ability.

 Super AI is purely speculative at this point.

Based on Capabilities
 Based on Functionalities
1. Reactive Machines :
 These machines are the most basic form of AI applications.
 Such AI system do not store memories or past experiences for
future actions.
 These machines focus only on current scenario and react on it
as per possible best action.
 Example: Games like Deep Blue & IBM’s chess playing
supercomputer.
 Based on Functionalities
2. Limited Memory:
 Limited Memory machines can retain data for a short period of
time.

 While they can use this data for specific time period, they cannot
add it to a library of their experiences.

 Many self-driving cars use Limited Memory technology: they

store data such as the recent speed of nearby cars, the distance
of such cars, the speed limit, & other information that can help
them navigate roads.
 Based on Functionalities
3. Theory of Mind :
 Theory of mind in AI should understand the human emotions,
beliefs and be able to interact socially like humans.

 Resources are making lots of efforts and improvement for

developing such AI machines.
 Based on Functionalities
4. Self Awareness :
 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.

 These machines will be smarter than human mind.

 Self awareness AI does not exist till now and it is a

hypothetical concept.
 Applications of AI
1. Chat bots:
AI Powered Chat bots can simulate a conversation (or a chat)
with a user in natural language through messaging applications,
websites, mobile apps or through the telephone.

2. AI in Healthcare:
There are lot of AI applications in the healthcare sector. AI is
used to detect diseases and uses the combination of historical
data & medical intelligence for the discovery of new drugs.
 Applications of AI (Cont’d)
3. Handwriting Recognition:
The handwriting recognition software reads the text written on
paper by a pen or on screen by a stylus. It can recognize the
shapes of the letters and convert it into editable text.

4. Speech Recognition:
Some intelligent systems are capable of hearing and
comprehending the language in terms of sentences and their
meanings while a human talks to it. It can handle different
accents, slang words, noise in the background, change in human’s
noise due to cold, etc.
 Applications of AI (Cont’d)
5. AI in Gaming :
AI can be used for gaming purpose. The AI machines can play
strategic games like chess, poker, tic-tac-toe, where the machine
needs to think of a large number of possibilities.

6. AI in Robots:
Generally robots are programmed such that they can perform
some repetitive task, but with the help of AI, we can create
intelligent robots which can perform tasks with their own
experiences without pre-programmed.
 Applications of AI (Cont’d)
7. AI in Education:
AI can automate grading so that the tutor can have more time
to teach. AI chatbot can communicate with students as a teaching
assistant. AI in the future can be work as a personal virtual tutor
for students, which will be accessible easily at any time and
any place.

8. AI in Data Security:
The security of data is crucial for every company and cyber-
attacks are growing very rapidly in the digital world. AI can be
used to make your data more safe and secure.
 Characteristics of AI
Application
 Ability to act intelligently as human.

 Ability to simulate functioning of human brain

 Ability to adapt and learn as an intelligent human

 Ability to process symbols and Natural Language like

humans

 Ability to perform an intelligent action.

 Some Terms in AI
1. Speech Processing:

 As well as trying to understand human systems, there are also

numerous real world applications : speech recognition for
dictation systems & voice activation control; speech production
for automated announcements and computer interfaces.
 How do we get from sound waves to text streams and vice-versa.

2. Natural Language Processing:

Machine understanding and translation of simple sentences.
 Some Terms in AI (Cont’d)
3. Planning:
 Planning refers to the process of choosing / computing the correct
sequence of steps to solve a given problem.

 To do this, we need some convenient representation of the problem

domain. We can define states in some formal language such as a
subset of predicate logic or a series of rules.

 A Plan can then be seen as a sequence of operations that transform

the initial state into the goal state i.e. the problem solution. Typically
we will use some kind of search algorithm to find a good plan.
 Advantages of AI
 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.
Advantages of AI (Cont’d)
 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 AI
 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.
 Disadvantages of AI
(Cont’d)
 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.
 Intelligent System
What is Intelligence?
The ability of a system to

 calculate
 reason
 perceive relationships and analogies
 learn from experience
 store and retrieve information from memory
 solve problems
 use natural language fluently
 comprehend complex ideas
 classify, generalize, and adapt new situations

is called Intelligence.
 What is Intelligence composed of ?
The intelligence is intangible. It is composed of−

 Reasoning

 Learning

 Perception

 Problem Solving

 Linguistic Intelligence
 Reasoning
 It is the set of processes that enables us to provide basis for
judgement, making decisions and prediction.
Inductive Reasoning Deductive Reasoning
It conducts specific observations to It starts with a general statement and
makes broad general statements. examines the possibilities to reach a
specific, logical conclusion.

Even if all of the premises are true in a If something is true of a class of things in
statement, inductive reasoning allows for general, it is also true for all members of
the conclusion to be false. that class.

Example − "Nita is a teacher. Nita is Example − "All women of age above 60

studious. Therefore, All teachers are years are old person. Rama is 65 years.
studious." Hence, Rama is an old person.."
 Learning
 It is the activity of gaining knowledge or skill by studying,
practising, being taught, or experiencing something.
 Learning enhances the awareness of the subjects of the study.
 The ability of learning is possessed by humans, some animals,
and AI-enabled systems.

 Learning is categorized as −
a. Auditory Learning e. Perceptual Learning
b. Episodic Learning f. Relational Learning
c. Motor Learning g. Spatial Learning
d. Observational Learning h. Stimulus-Response Learning
Some Learning Techniques
 Auditory Learning:
Learn by Listening and hearing. Ex – Students listening to
recorded audio lectures.

 Episodic Learning:
To learn by remembering sequence of events that one has
witnessed or experienced. This is linear and orderly.

 Motor Learning:
To learn by precise movement of muscles. For Example –
picking objects, writing etc.
Some Learning Techniques
 Observational Learning:
Learn by watching and imitating others. Ex – Child tries to learn
by mimicking his/her parent.

 Perceptual Learning:
To learn by recognising and stimulating that one has seen
before. Example – identifying and classifying objects and
situations.
 Problem Solving
 It is the process in which one perceives and tries to
arrive at a desired solution from a present situation by
taking some path, which is blocked by known or
unknown hurdles.

 Problem solving also includes decision making,

which is the process of selecting the best suitable
alternative out of available multiple alternatives to
reach the desired goal.
 Two more Compositions
Perception :-
 It is the process of acquiring, interpreting, selecting, and organizing
sensory information.
 Perception presumes sensing. In humans, perception is aided by
sensory organs.
 In the domain of AI, perception mechanism puts the data acquired
by the sensors together in a meaningful manner.

Linguistic Intelligence :-
 It is one’s ability to use, comprehend, speak, and write the verbal
and written language. It is important in interpersonal
communication.
 Difference between
Human & Machine Intelligence

 Humans perceive by patterns whereas the machines perceive by set

of rules and data.

 Humans store and recall information by patterns, machines do it

by searching algorithms. For example, the number 60606060 is
easy to remember, store and recall as its pattern is simple.

 Humans can figure out the complete object even if some part of
it is missing or distorted; whereas the machines cannot able to do it
correctly.
The End