Fundamentals In AI & ML

Slot: C14+E11+E12

CSA2001
Dr. Priscilla Dinkar Moyya
(School of Computer Science Engineering and Artificial Intelligence)

VIT Bhopal University, India

 Module-1
Introduction

2
 Artificial Intelligence:
 The term Artificial Intelligence was first coined
decades ago in the year 1956 by “John McCarthy” at
the Dartmouth conference. He defined-
 “Artificial Intelligence is the science and engineering
of making intelligent machines, especially intelligent
computer programs”

3
  In the recent past AI has been able to accomplish this
by creating machines and robots that are being used in
a wide range of fields including-
 Healthcare
 Robotics
 Marketing
 Business analytics and many more
• However many AI applications are not perceived as AI
because we often tend to think of artificial intelligence
as robots doing our daily course.

4
  People often tend to think that Artificial Intelligence,
Machine Learning and Deep learning are the same since they
have common applications. Example- SIRI
 However, Artificial Intelligence is not restricted to only
machine learning as well as deep learning. It covers a vast
domain of fields including Natural Language Processing,
Object Detection, Computer Vision, Robotics and Expert
systems and so on.

5
 Real life example of AI-
• Manufacturing robots.
• Self-driving cars.
• Smart assistants.
• Proactive healthcare management.
• Disease mapping.
• Automated financial investing.
• Virtual travel booking agent.
• Social media monitoring
• Siri, Alexa and other smart assistants
• Email spam filters
• Netflix's recommendations
6
 Evolutionary of Artificial
Intelligence:
Based on Capabilities

7
 Example- Alexa,
iPhone
Tesla
Google
Maps

8
9
 Stephen Hawking’s

“Strong AI would take off on its own, and re-design

itself at ever-increasing rate. Humans, who are limited
by slow biological evolution, couldn’t complete, and
would be superseded.”
10
11
 Types of Artificial Intelligence:
Based on the functionality of AI based systems Artificial
Intelligence can be categorized into 4 types:
1. Reactive Machine AI:
Reactive Machine AI includes machines that
operates solely based on present data, taking into account
only the current situation. Reactive AI machines cannot
form Inferences from the data to evaluate their future
actions. Example- IBM’S Deep Blue.

12
 2. Limited Memory AI:
Limited Memory AI can make informed and improved
decisions by studying the past data from its memory.
Such an AI has a short-lived or a temporary memory that
can be used to store past experiences and hence evaluate
future actions.
Example- Self-driving Cars

13
 3. Theory of Mind:
The Theory of Mind AI will focus mainly on emotional
intelligence so that human believes and thoughts can be
better comprehended.

14
 4. Self-aware AI:
The self- aware AI includes machines that have their
own consciousness and become self-aware.
This type of AI does not exist yet.

15
 Why Artificial Intelligence?
Following are some main reasons to learn about AI:

• 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 Cortana, 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.
16
 Artificial Intelligence Applications
There are numerous, real-world applications of AI
systems today:

1. Artificial Intelligence in E-Commerce:

 Personalized Shopping-
• Recommendation engines can enable you to
engage with your customers, by taking into
consideration their usage history, preferences and
interests.
• This can lead to improved brand loyalty and an
increase in the number of conversions.
17
  AI Powered Assistants-
• AI powered assistants like virtual shopping assistants
and chatbots help improve user experience while
shopping online.
• Using techniques like Natural Language Processing
(NLP), conversations with users can seem personal to
users and tailored to their interests.

 Smart Purchasing-
• Artificial Intelligence helps with forecasting demand
for products and enhance the decision making behind
what items to stock up and when it should be done, so
that customer expectations can be met.
18
  Fraud Prevention-
• AI can identify credit card usage patterns and reduce
the possibility of credit card fraud taking place.
• AI can also help identify and handle fake reviews, in
the process improving customer’s trust in your brand
and products.
2. Applications of AI in Speech Recognition:
Speech recognition is one such technology that is
empowered by AI to add convenience to its users. This
new technology has the power to convert voice messages
to text. And it also has the ability to recognize an
individual based on their voice command.
19
 3. Natural Language Processing (NLP):
Natural language processing is a subfield of
linguistics, computer science, and artificial intelligence
concerned with the interactions between computers and
human language, in particular how to program computers
to process and analyse large amounts of natural language
data.
There’s a good chance you’ve interacted with NLP in the
form of voice-operated GPS systems, digital assistants,
speech-to-text dictation software, customer service
chatbots, and other consumer conveniences.
20
 4. Application of AI in Navigation:
Based on research from MIT, an AI using a
combination of CNN, GNN would enable an GPS
application to automatically predict the number of lanes
and roads types behind obstructions.
5. Application of AI in Robotics:
AI enabled robots will be able to maneuver through
its path of travel with real-time updates. It uses this path
to sense obstacles and pre-plan its path.

21
 6. Application of AI in Healthcare:
Audit system that can use AI can prevent prescription
errors and ensure the disease is properly identified.
Prescriptive analysis can be performed on patient data
for ensuring that the case is prioritized in real time and
triage can be performed.

7. Google Predictive Search Engine

8. Self-driving Cars
22
 History of Artificial Intelligence:

23
 Maturation of AI (1943-1952)
• Year 1943: The first work which is now recognized as
AI was done by Warren McCulloch and Walter pits in
1943. They proposed a model of artificial neurons.
• Year 1949: Donald Hebb demonstrated an updating
rule for modifying the connection strength between
neurons. His rule is now called Hebbian learning.
• Year 1950: The Alan Turing who was an English
mathematician and pioneered Machine learning in
1950. Alan Turing publishes "Computing Machinery
and Intelligence" in which he proposed a test. The
test can check the machine's ability to exhibit
intelligent behaviour equivalent to human intelligence,
24 called a Turing test.
 The birth of Artificial Intelligence (1952-1956)

• 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, and find new
and more elegant proofs for some theorems.
• Year 1956: The word "Artificial Intelligence" first
adopted by American Computer scientist John
McCarthy at the Dartmouth Conference. For the first
time, AI coined as an academic field.
At that time high-level computer languages such as
FORTRAN, LISP, or COBOL were invented. And the
enthusiasm for AI was very high at that time.
25
 The golden years-Early enthusiasm (1956-1974)

• Year 1966: The researchers emphasized

developing algorithms which can solve
mathematical problems. Joseph Weizenbaum
created the first chatbot in 1966, which was named
as ELIZA.
• Year 1972: The first intelligent humanoid robot
was built in Japan which was named as WABOT-1.

26
 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.

27
 A boom of AI (1980-1987)

• Year 1980: After AI winter duration, AI came back

with "Expert System". Expert systems were
programmed that emulate the decision-making
ability of a human expert.
• In the Year 1980, the first national conference of
the American Association of Artificial
Intelligence was held at Stanford University.

28
 The second AI winter (1987-1993)
• The duration between the years 1987 to 1993
was the second AI Winter duration.
• Again Investors and government stopped in
funding for AI research as due to high cost but not
efficient result. The expert system such as XCON
was very cost effective.

29
 The emergence of intelligent agents (1993-
2011)
• Year 1997: In the 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: AI came in the Business world till the
year 2006. Companies like Facebook, Twitter,
and Netflix also started using AI.
30
 Deep learning, big data and artificial general
intelligence (2011-present)
• Year 2011: In the year 2011, IBM's Watson won
jeopardy, a quiz show, where it had to solve the
complex questions as well as riddles. Watson had
proved that it could understand natural language
and can solve tricky questions quickly.
• Year 2012: Google has launched an Android app
feature "Google now", which was able to provide
information to the user as a prediction.
• Year 2014: In the year 2014, Chatbot "Eugene
Goostman" won a competition in the infamous
"Turing test."
31
  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.

32
 Future of Artificial Intelligence

 In the last 10 years, the artificial intelligence has

changed the world in subtle but sweeping waves
poised recognition on every smartphone was a simple
proof of concept over the next 10 years artificial
intelligence will more progress than in the 50 before it
combined with countless quickly oncoming
applications to business, government and personal life.
Its influence will soon touch absolutely every aspect
of our lives.

33
 1. Medical Diagnosis:
Diagnosis is now complementing a doctor’s human
intuition with the precision and completeness of AI could
be one of the greatest revolutions in healthcare.
2. Financial Services:
It is fun to watch the bankers get automated into
unemployment but the real win is when the AI takes
over.
3. Translation & Linguistics:
To an extent real time machine translation already
exists from major tech companies like pipe and
Microsoft but other research bodies like google and even
DARPA are looking to take the idea ahead.
34
 4. Paying for Things:
AI could also change the world of paying for anything
now this technology can save an incredible amount of
time. Advanced AI face recognition algorithms will soon
be quick enough and cheap enough to support millions of
transactions per day but Machine learning can teach a
computer to recognize more than faces.
5. Shopping with AI:
Amazon is already working to make physical
shopping even less hassle than online.
Online shopping algorithms are a dime a dozen these
days but one fascinating project from Pinterest would
35
expand the idea to the physical wall.
 6. Purchase through Photographs:
Have you ever clicked the picture of a product so
that you can look for something similar in these stores.
Amazon the giant e-commerce platform has already
incorporated the visual search option on its mobile
application.

36
 Considering the growing adoption and popularity of AI,
we can imagine how things would change for humans in
the future-
• Automated transportation will become more common,
even as early as possible.
• Humans will be able to augment themselves with
robots. Robots could bring a cup of coffee, prepare
reports, control home appliances, and handle other
tasks.
• There will be more smart cities as vehicles, phones,
and home appliances that will be run by AI.

37
 • Home robots will help older people with their day-to-
day work. Japan, for instance, already has an in-depth
program where they’ve begun to integrate robots to
help. Tasks like contacting a doctor in case of
emergency can now be done with AI.
• Robots will take over hazardous jobs like bomb
defusing, welding, etc.

38
Few widely recognized definitions of Artificial Intelligence (AI):
 John McCarthy (1956): AI is "the science and engineering of making
intelligent machines, especially intelligent computer programs." This early
definition highlights AI's focus on creating systems that can simulate human
intelligence.
 Stuart Russell and Peter Norvig (in their book "Artificial Intelligence: A
Modern Approach"): AI is defined as "the study of agents that receive
percepts from the environment and perform actions." This definition
emphasizes AI as a field focused on developing intelligent agents that can
make decisions based on the information they gather from their surroundings.
 Merriam-Webster: AI is "a branch of computer science dealing with the
simulation of intelligent behavior in computers." This definition focuses on
AI's role in creating systems that mimic human behavior and intelligence.
 IBM: AI refers to "any human-like intelligence exhibited by a computer,
robot, or other machine." This definition includes various forms of intelligence
that computers and machines can demonstrate, similar to human thought
processes.
 François Chollet (Creator of Keras): AI is defined as “the ability of a
39
system to adapt to new environments, to generalize its knowledge, and to
apply it to previously unseen tasks.”
 Intelligent Agents:

Perceive
(Sensors)
Agent  Environment
act
(actuators)

- Structure of Agent
Architecture+ State+
Program

40
41
 Intelligent Agents:
Intelligent Agents is one which can take input from the
environment through its sensors and act upon the
environment through its actuators. Its actions are always
directed to achieved a goal.
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
42
rational action.
 Sensors:
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.

43
 Categories of Intelligent Agents:

Agents can be grouped into four classes based on their

degree of perceived intelligence and capability :

1. Simple Reflex Agents

2. Model-Based Reflex Agents
3. Goal-Based Agents
4. Utility-Based Agents
5. Learning Agent

44
 Categories of Intelligent Agents:

1. Simple Reflex Agents

45
46
 Simple Reflex Agents:
• The Simple reflex agents are the simplest agents.
These agents take decisions on the basis of the current
percepts and ignore the rest of the percept history.
• These agents only succeed in the fully observable
environment.
Problems for the simple reflex agent design approach:
• They have very limited intelligence
• They do not have knowledge of non-perceptual parts of
the current state
• Mostly too big to generate and to store.
• Not adaptive to changes in the environment.
47
• The Simple reflex agent does not consider any part of
percept's history during their decision and action process.
• The Simple reflex agent works on Condition-action rule,
which means it maps the current state to action. Such as a
Room Cleaner agent, it works only if there is dirt in the room.

48
 Categories of Intelligent Agents:

2. Model-Based Reflex Agents

49
50
 Model-Based Reflex Agents:
• The Model-based agent can work in a partially
observable environment, and track the
situation.
A model-based agent has two important factors:
• Model: It is knowledge about "how things happen
in the world," so it is called a Model-based agent.
• Internal State: It is a representation of the current
state based on percept history.
• No Learning

51
 Categories of Intelligent Agents:

3. Goal-Based Agents

52
 Goal-Based Agents:
• The knowledge of the current state environment is not
always sufficient to decide for an agent to what to do.
• The agent needs to know its goal which describes
desirable situations.
• Goal-based agents expand the capabilities of the model-
based agent by having the "goal" information.
• They choose an action, so that they can achieve the goal.
• These agents may have to consider a long sequence of
possible actions before deciding whether the goal is
achieved or not. Such considerations of different scenario
are called searching and planning, which makes an agent
proactive.
53
54
 Categories of Intelligent Agents:

4. Utility-Based Agents

55
56
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.
• The utility function maps each state to a real number to check
how efficiently each action achieves the goals.

57
 Categories of Intelligent Agents:

5. Learning Agent

58
59
Learning Agents:
• A learning agent in AI is the type of agent which
can learn from its past experiences, or it has
learning capabilities.
• It starts to act with basic knowledge and then 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 environment
• Critic: Learning element takes feedback from critic
which describes that how well the agent is doing
with respect to a fixed performance standard.

60
 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.
• Hence, learning agents are able to learn, analyse
performance, and look for new ways to improve
the performance.

61
 Summary: Agent Types
(1) Simple reflex agents
○ are based on condition-action rules, implemented with an
appropriate production system. They are stateless devices
which do not have memory of past world states.
(2) Agents with memory - Model-based reflex agents
○have internal state, which is used to keep track of past states of
the world.
(3) Agents with goals – Goal-based agents
○ are agents that, in addition to state information, have goal
information that describes desirable situations. Agents of this
kind take future events into consideration.
62
 Summary: Agent Types
(4) Utility-based agents
○ base their decisions on classic axiomatic utility theory in order
to act rationally.
(5) Learning agents
○they have the ability to improve performance through learning.

63
 Applications of Intelligent Agents:
Intelligent agents in artificial intelligence have been
applied in many real-life situations:

• Information search, retrieval, and navigation

• Repetitive office activities
• Medical diagnosis
• Vacuum cleaning
• Autonomous driving

64
 Characteristics of Intelligent Agents
Intelligent agents have the following distinguishing
characteristics:
• They have a learning ability that enables them to learn
even as tasks are carried out.
• They have some level of autonomy that allows them
to perform certain tasks on their own.
• They can interact with other entities such as agents,
humans, and systems.
• New rules can be accommodated by intelligent agents
incrementally.
• They exhibit goal-oriented habits.
• They are knowledge-based. They use knowledge
65 regarding communications, processes, and entities.