CHAPTER ONE

INTRODUCTION TO ARTIFICIAL
INTELLIGENCE

1
 What is Artificial Intelligence ?
 making computers that think?
 the automation of activities we associate with human thinking,
like decision making, learning ... ?
 the art of creating machines that perform functions that require
intelligence when performed by people ?
 the study of mental faculties through the use of computational
models ?
 Artificial intelligence (AI), sometimes called machine intelligence, is
intelligence demonstrated by machines, in contrast to the natural intelligence
displayed by humans and other animals, such as "learning" and "problem
solving. .

 In computer science AI research is defined as the study of "intelligent agents":

any device that perceives its environment and takes actions that maximize its
chance of successfully achieving its goals.
2
 History of AI
 John McCarthy is considered as the father of Artificial Intelligence. John
McCarthy was an American computer scientist. The term "artificial
intelligence" was coined by him.
 He is one of the founder of artificial intelligence, together with Alan Turing,
Marvin Minsky, Allen Newell, and Herbert A.
 Sophia is marketed as a "social robot" that can mimic social behavior and induce
feelings of love in humans. Sophia was first activated on Valentines
Day, February 14, 2016..

What is the most advanced robot in 2023? 5

 The ‘von Neuman’ Architecture
 Refers to a design model for computers where the processing unit, memory, and
input-output devices are interconnected through a single, central system bus.
 This architecture was first proposed by John von Neumann, a Hungarian-American
mathematician and physicist, in the mid-20th century.
History of AI
 Origins
 The Dartmouth conference: 1956
 John McCarthy (Stanford)
 Marvin Minsky (MIT)
 Herbert Simon (CMU)
 Allen Newell (CMU)
 Arthur Samuel (IBM)
 The Turing Test (1950)
 “Machines who Think”
 By Pamela McCorckindale
Periods in AI
 Early period - 1950’s & 60’s
 Game playing
 brute force (calculate your way out)
 Theorem proving
 symbol manipulation
 Biological models
 neural nets
 Symbolic application period - 70’s
 Early expert systems, use of knowledge
 Commercial period - 80’s
 boom in knowledge/ rule bases
 Periods in AI cont’d
 ? period - 90’s and New Millenium
 Real-world applications, modelling, better evidence, use of
theory, ......?
 Applications
 visual recognition of traffic
 medical diagnosis
 directory enquiries
 power plant control
 automatic cars
 Fashions in AI
Progress goes in stages, following funding booms and crises: Some examples:
1. Machine translation of languages
1950’s to 1966 - Syntactic translators
1966 - all US funding cancelled
1980 - commercial translators available
2. Neural Networks
1943 - first AI work by McCulloch & Pitts
1950’s & 60’s - Minsky’s book on “Perceptrons” stops nearly all work on nets
1986 - rediscovery of solutions leads to massive growth in neural nets research
Symbolic and Sub-symbolic AI
 Symbolic AI is concerned with describing and manipulating our
knowledge of the world as explicit symbols, where these symbols
have clear relationships to entities in the real world.

 Sub-symbolic AI (e.g. neural-nets) is more concerned with

obtaining the correct response to an input stimulus without
‘looking inside the box’ to see if parts of the mechanism can be
associated with discrete real world objects.
Goals of AI

 To make computers more useful by letting them take over

dangerous or tedious tasks from human
 Understand principles of human intelligence
 The main goals are:
 to create a system that can exhibit intelligent behavior,
 learn new things, and
 help in decision-making for its users.
 What is Artificial Intelligence ?

THOUGHT Systems that think Systems that think

like humans rationally

Systems that act Systems that act

BEHAVIOUR like humans rationally

HUMAN RATIONAL
 Systems that act like humans:
Turing Test
 “The art of creating machines that perform functions that require
intelligence when performed by people.” (Kurzweil)
 “The study of how to make computers do things at which, at the
moment, people are better.” (Rich and Knight)
Systems that act rationally

 Study AI as rational agent –

2 advantages:
 It is more general than using logic only
 Because: LOGIC + Domain knowledge
 It allows extension of the approach with more
scientific methodologies
Some Advantages of Artificial
Intelligence
 more powerful and more useful computers
 new and improved interfaces
 solving new problems
 better handling of information
 relieves information overload
 conversion of information into knowledge
The Disadvantages

 increased costs
 difficulty with software development - slow and expensive
 few experienced programmers
 few practical products have reached the market as yet.
HOW ARE HUMANS INTELLIGENT ?
• Learning

• Reasoning

• Problem Solving and Creativity

• Social Behavior

• Experiencing our Environment with our senses:

• Hearing
• Sight
• Touch
• Taste
• Smelling 3
19
Ways that People Think and Learn About Things

• If you have a problem, think of a past situation where you

solved a similar problem.
• If you take an action, anticipate what might happen next.
• If you fail at something, imagine how you might have done
things differently.
• If you observe an event, try to infer what prior event might have
caused it.
• If you see an object, wonder if anyone owns it.
• If someone does something, ask yourself what the person's
purpose was in doing that.

20
Interacting with the Environment
 In order to enable intelligent behaviour, we will have to
interact with our environment.
 Properly intelligent systems may be expected to:
 accept sensory input
 vision, sound, …
 interact with humans
 understand language, recognise speech,
generate text, speech and graphics, …
 modify the environment
 robotics
Artificial intelligence (AI) - The study of computer systems that attempt
to model and apply the intelligence of the human mind.

For example, writing a program to pick out objects in a picture:

This is what
Computers do best
This is what
Humans do Can you count the
best distribution of letters
in a book?

Can you list Add a thousand 4-

the items in digit numbers?
this picture ?

A computer Match finger

might have prints?
trouble
identifying the Search a list of a
cat there. million values for
duplicates6?
When we compare Humans to Machines, it is important to note that a Machine can be
a car, a Smart Phone, a Digital Television, etc.

23
24
The illustration below illustrates a typical information flow between the "human" and
"machine" components of a system. For a properly designed
system, its important to know the capabilities and flexibilities of both.

https://www.hf.faa.gov/webtraining/HFModel/HFInterModel/overview.htm 9
10
 KEY RESEARCH AREAS IN AI
• Problem solving, planning, and search --- generic problem solving architecture based
on ideas from cognitive science (game playing, robotics).

• Knowledge Representation – to store and manipulate information (logical and

probabilistic representations)

• Automated reasoning / Inference – to use the stored information to

answer questions and draw new conclusions

• Machine Learning – intelligence from data; to adapt to new

circumstances and to detect and extrapolate patterns

• Natural Language Processing – to communicate with the machine

• Computer Vision --- processing visual information

• Robotics --- Autonomy, manipulation, full integration of AI capabilities 11

From SIRI and Alexa, to self-driving cars, artificial intelligence
(AI) is progressing rapidly.

While science fiction often portrays AI as robots with human-like characteristics,

AI can encompass anything from Google’s search algorithms, to IBM’s Watson,
to autonomous weapons.

Artificial intelligence today is properly known as narrow AI (or weak AI), in

that it is designed to perform a narrow task such as only facial recognition, or
only internet searches, or only driving a car).

However, the long-term goal of many researchers is to create general

AI (AGI or strong AI).

While narrow AI may outperform humans at whatever its specific task is, like
playing chess or solving equations, AGI would outperform humans at nearly
every thinking task.

28
29
The potential benefits from self-learning computer chips are limitless as these
types of devices can learn to perform the most complex thinking tasks, such as
interpreting critical cardiac rhythms, detecting anomalies to prevent cyber-
hacking and composing music.

This is a new one made by the Intel company and many other companies are
making special AI chips too.

1
4
Artificial Intelligence (AI) has entered our daily lives like never before and we are yet to
unravel the many other ways in which it could flourish.

All of the tech giants such as Microsoft, Uber, Google, Facebook, Apple, Amazon,
Oracle, Intel, IBM or Twitter are competing in the race to lead the market and acquire
the most innovative and promising AI businesses.

31
How AI communicates with humans?
32
AI Now? AI Not yet?

33
Google announced their Duplex system, a new technology for conducting natural
conversations to carry out “real world” tasks over the phone.

The technology is directed towards completing specific tasks, such as scheduling

certain types of appointments.

For such tasks, the system makes the conversational experience as natural as
possible, allowing people to speak normally, like they would to another person,
without having to adapt to a machine.

https://www.youtube.com/watch?v=GoXp1leA5Qc
34
35
 The Turing Test
Turing test
A test to determine whether a computer has achieved intelligence

Alan Turing
An English mathematician who wrote a landmark paper in 1950 that asked the
question: Can machines think?

He proposed a test to answer the question "How will we know when we have
succeeded?“

He said that a machine passes the test when it successfully generates responses
appropriate enough to convince the evaluator that it is human.

29
In the Turing test, the interrogator must determine which
respondent is the computer and which is the human.

37
 THE LOEBNER PRIZE FOR COMPLETING
THE TURING TEST
The Loebner Prize is an annual competition in artificial intelligence
that awards prizes to the computer
programs considered by the judges to be the most human- like, using the Turing
Test computer and person arrangement.

The contest was launched in 1990 by Hugh Loebner and there are bronze, silver,
and gold coin prizes, plus money.

38
 KNOWLEDGE REPRESENTATION
• We need to create a logical view of the data, based on how we want to process it
• Natural language is very descriptive, but does not lend itself to efficient
processing.

What are the different ways that we can represent knowledge so it

can be reviewed by an Artificial Intelligence computer program ?

1) Expert Learning Systems

2) Semantic Networks - A knowledge representation technique that focuses on the

relationships and word descriptions of objects. A graph is used to represent a semantic
network or net

3) Decision or Search tree

4) Neural networks – creating a computer version of the neurons of the br3a3in and how they
work
 1) Expert Learning Systems
• Expert Learning Systems were commercially the first and most successful
domain in Artificial Intelligence.

• Somewhat out of favor today

• These programs mimic the experts in whatever field is being studied.

Auto mechanic Telephone networking

Cardiologist Organic Delivery routing
compounds Mineral Professional auditor
prospecting Infectious Manufacturing Pulmonary
diseases function Weather
Diagnostic internal medicine forecasting Battlefield
computer configuration Engineering tactician
structural analysis Audiologist Space-station life support Civil
law
12-34
• Rule-based or Expert systems - Knowledge bases consisting of
hundreds or thousands of rules of the form:
• IF (condition) THEN (action).

• Use rules to store knowledge (“rule-based”).

• The rules are usually gathered from experts in the field being
represented (“expert system”).
• Most widely used knowledge model in the commercial world.

IF (it is raining AND you must go outside)

THEN (put on your raincoat)

• Rules can fire off a chain of other rules

IF (raincoat is on)
THEN (you will not get wet)
2) Semantic (word description) Networks
Semantic network
A knowledge representation technique that focuses on the relationships
between objects
A directed graph or word chart is used to represent a semantic network or net

42
 3) Search Trees
AI often revolves around the use of algorithms.

An algorithm is a set of instructions that a mechanical computer can execute.

A complex algorithm is often built on top of another, simpler, one

and a common way to visualize it is with a tree design.

43
THE HUMAN BRAIN AND NEURONS IN IT
The human brain has often been viewed as outstanding among mammalian brains: the
most cognitively able, the largest-than-expected from body size, endowed with an
overdeveloped cerebral cortex that represents over 80% of brain mass, and purportedly
containing 100 billion neurons and 10× more glial cells.

44
THE BRAIN IS DIVIDED INTO 4
PARTS AND THE CEREBELLUM
WHICH IS LOCATED AT THE
BOTTOM, BACK AREA

45
AI technology called machine learning today, is great at helping for taking good
photos, translating languages, recognizing your friends on Facebook, delivering search
results, screening out spam and many other chores.

It usually uses an approach called neural networks that works something like a human
brain, not a sequence of IF THIS, THEN steps as in traditional computing.

46
 TYPES AND FUNCTION OF NEURONS

Neurons are essential for every action that our body and brain carry out.

It is the complexity of neuronal networks that gives us our personalities and our
consciousness.

They make up around 10 percent of the brain; the rest consists of glial cells and other
cells that support and nourish the neurons.

47
Incoming signals to the neuron can be either excitatory – which means they tend to make the
neuron fire (generate an electrical impulse) – or inhibitory – which means that they tend to keep
the neuron from firing.

A single neuron may have more than one set of dendrites, and may receive many
thousands of input signals.

Whether or not a neuron is excited into firing an impulse depends on the sum of all of the
excitatory and inhibitory signals it receives.

If the neuron does end up firing, the nerve impulse is conducted down the axon.

48
How synapses work - Neurons are connected to each other at a location called a Synapse, so
that they can communicate messages

Amazingly, where each cell connects with the other one, NONE of these cells ever touch
each other !!

The signal that is carried from the first nerve fiber to the next one is transmitted by an
electrical signal or a chemical one, up to a speed of 268 miles per hour !

There is new evidence that both types closely interact with each other and that the
transmission of a nerve signal is both chemical and electrical, which is actually required for
normal brain development and function.
 4) Artificial Neural Network (ANN)
A computer representation of knowledge that attempts to mimic the neural
networks of the human brain
Yes, but what is a human neural network?

Neural networks, or neural nets, were inspired by the architecture of

neurons in the human brain.

A simple "neuron" N accepts input from multiple other neurons, each of which, when
activated (or "fired"), cast a weighted "vote" for or against whether neuron N should
itself activate.

54
An ANN is based on a collection of connected units or nodes called artificial neurons, which
loosely model the neurons in a biological brain.

Each connection, like the synapses in a biological brain, can transmit a

signal from one artificial neuron to another. An artificial neuron that receives
a signal can process it and then signal additional artificial neurons
connected to it.

55
 ARTIFICIAL NEURAL NETWORK
• Artificial neurons: Commonly called processing elements,
are modeled after real neurons of humans and other animals.

• Has many inputs and one output.

• The inputs are signals that are strengthened or weakened

(weighted).

• If the sum of all the signals is strong enough, the neuron

will put out a signal to the next neuron output of a 1.

Artificial
Inputs Neuron Output

12-56
 Artificial Neural Networks
Training
The process of adjusting the weights and threshold values in a neural net
How does this all work?
Train a neural net to recognize An eagle in a picture.
Given one output value per pixel, train network to produce an output value of 1 for
every pixel that contributes to the eagle and 0 for every one that doesn’t.

57
DeepMind is a subsidiary of Google that focuses on the development of
artificial intelligence and deep reinforcement machine learning.

The deep reinforcement learning of its AI algorithms has been used in both
research and applied contexts

DeepMind is built around the framework of neural networks and uses a method
called deep-reinforced-learning.

This means that the A.I can learn from it's experiences and become more
efficient at whatever it does.

The A.I is general-purpose meaning that it's NOT pre-programmed for a specific
task from the go.

https://www.youtube.com/watch?
v=TnUYcTuZJpM&ab_channel=ColdFusion
54
 Agents
• An agent is anything that can be viewed as a device that can perceive its
environment through sensors and act upon that environment through actuators.

• Human agent: eyes, ears, and other organs for sensors; hands, legs, mouth, and
other body parts for actuators

• Robotic agent: cameras and infrared range finders for sensors

• Rational Agent:
• For each possible sequence, a rational agent should select an action that is
expected to maximize its performance measure, given the evidence provided
by the perception sequence and whatever built-in knowledge the agent has.

55
 Why “meaning” is the central concept of AI
• For an agent to be “intelligent”, it must be able to understand the
meaning of information.

• Information is acquired / delivered / conveyed in messages which are phrased

in a selected representation language.

• There are two sides in information exchange:

• The source (text, image, person, program, etc.) and
• The receiver (person or an AI agent). They must speak the same “language” for
the information to be exchanged in a meaningful way.

• The receiver must have the ability to interpret the information correctly according to
the intended by the source meaning or semantics of it.

60
57
Machine Learning
The phrase ‘machine learning’ dates back to the middle of the last
century where Arthur Samuel in 1959 defined machine learning
as “the ability to learn without being explicitly programmed.”

Machine learning is a type of AI that helps a computer’s ability to

learn and essentially teach itself to evolve as it becomes
exposed to new and ever-changing data.

For example, Facebook’s news feed uses machine learning in an

effort to personalize each individual’s feed based on what they like.

58
 DRONE CHASSIS DESIGN
USING MACHINE
LEARNING

https://www.youtube.com/watch? 63
Deep Learning

Deep Learning is a new area of machine learning research, which has been
introduced with the objective of moving machine learning closer to artificial
intelligence.

It relates to study of ‘deep neural networks’ in the human brain and, under this
perspective, the deep learning tries to emulate the functions of inner layers of
the human brain, creating knowledge from multiple layers of information
processing.

Since the deep learning technology is modelled after the human

brain, each time new data is poured in, its capabilities get better.

Deep artificial neural networks are a set of algorithms reaching new levels
of accuracy for many important problems, such as image recognition, sound
recognition, recommender systems, etc.

60
For example, a deep learning
algorithm could be trained to
‘learn’ how a dog looks like. It
would take an enormous dataset of
images for it to understand the
minor details that distinguish a dog
from a wolf or a fox.

61
62
 CONCERNS ABOUT AI TAKING
OVER THE WORLD
The computer that wins at games of Chess or Go, is analyzing data for
patterns. It has no idea it’s playing Go as opposed to golf, or what would
happen if more than half of a Go board was pushed beyond the edge of a table.

When you ask Amazon’s Alexa to reserve you a table at a restaurant you
name, its voice recognition system, made very accurate by machine learning,
saves you the time of entering a request in Open Table’s reservation system.

But Alexa doesn’t know what a restaurant is or what eating is.

If you asked it to book you a table for two at 6 p.m. at the Mayo Clinic, it would
try.

63
64
65
66