INTRODUCTION TO
ARTIFICIAL INTELLIGENCE
ARTIFICIAL INTELLIGENCE (AI)
The need of AI..
Industrial Revolution IR4.0?
In IR4.0, the concept is to have the machines
interconnected via network or the internet, thus the
term ‘Cyber Physical System’.
http://www.myforesight.my/wp-content/uploads/2016/12/MyForesight_Mag_04-2016_.pdf
IR4.0 Characteristics and
Components
The birth of AI: 1956
At the Dartmouth workshop of 1956's, Allen Newell,
Herbert A. Simon and Cliff Shaw debuted with Logic
Theorist
Introduction to Artificial Intelligence
Objectives :
To understand what is artificial intelligence and
intelligent machines
To identify the machine learning methods.
To understand Turing Imitation game
To understand AI programming paradigm
To identify the state of the art of artificial
intelligence
What is Artificial Intelligence?
Preliminary discussion
• Can machines think?
• And if so, how?
• And if not, why not?
• And what does this say about human beings?
• And what does this say about the mind?
Intelligent machines, or what machines
can do
Philosophers have been trying for over 2000 years
to understand and resolve two Big Questions of the
Universe:
How does a human mind work
Can non-humans have minds?
These questions are still unanswered.
What is intelligence?...
Intelligence is the ability to think, learn and
understand instead of doing things by instinct
or automatically.
(Essential English Dictionary, Collins, London,
1990)
What is intelligence?
In order to think, someone or something has to
have a brain, or an organ that enables someone
or something to learn and understand things, to
solve problems and to make decisions.
So we can define intelligence as the ability
to learn and understand, to solve
problems and to make decisions.
What is Artificial Intelligence?
Artificial intelligence (AI) is an area of
computer science that emphasizes the
creation of intelligent machines that work and
react like human where it has the ability to
learn and understand, to solve problems and
to make decisions.
.
Other definitions of AI
What is the goal of AI?
The goal of artificial intelligence (AI) as a science is
to make machines do things that would require
intelligence if done by humans. Therefore, the
answer to the question :
Can Machines Think? was vitally important to the
discipline.
The answer is not a simple “Yes” or “No”.
As humans, we all have the ability to learn and
understand, to solve problems and to make
decisions;
however, our abilities are not equal and lie in
different areas.
Therefore, we should expect that if machines
can think, some of them might be smarter than
others in some ways.
Some people are smarter in some ways than others.
Sometimes we make very intelligent decisions but
sometimes we also make very silly mistakes.
Some of us deal with complex mathematical and
engineering problems but are moronic in philosophy
and history.
Some people are good at making money, while
others are better at spending it.
Is there thought without experience? Is there mind
without communication? Is there language
without living? Is there intelligence without life?
All these questions, as you can see, are just
variations on the fundamental question of artificial
intelligence, Can machines think?
Intelligent Systems in Your Everyday Life
Post Office
automatic address recognition and sorting of mail
Banks
automatic check readers, signature verification systems
automated loan application classification
Customer Service
automatic voice recognition
The Web
Identifying your age, gender, location, from your Web surfing
Automated fraud detection
Digital Cameras
Automated face detection and focusing
Computer Games
Intelligent characters/agents
What’s involved in Intelligence?
Perceiving, recognizing, understanding the real world
Reasoning and planning about the external world
Learning and adaptation
So what general principles should we use to achieve
these goals?
Turing Imitation Game
Turing did not provide definitions of machines
and thinking, he just avoided semantic
arguments by inventing a game, the Turing
Imitation Game.
Turing Imitation Game
The imitation game originally included two phases.
In the first phase, the interrogator, a man and a
woman are each placed in separate rooms.
The interrogator’s objective is to work out who is
the man and who is the woman by questioning
them.
The man should attempt to deceive the
interrogator that he is the woman, while the woman
has to convince the interrogator that she is the
woman.
Turing Imitation Game: Phase 1
Turing Imitation Game: Phase 2
In the second phase of the game, the man is
replaced by a computer programmed to deceive the
interrogator as the man did.
It would even be programmed to make mistakes and
provide fuzzy answers in the way a human would.
If the computer can fool the interrogator as often as
the man did, we may say this computer has passed
the intelligent behaviour test.
Turing Imitation Game: Phase 2
The Turing test has two remarkable qualities that
make it really universal.
By maintaining communication between the human
and the machine via terminals, the test gives us an
objective standard view on intelligence.
The test itself is quite independent from the details
of the experiment.
It can be conducted as a two-phase game, or even
as a single-phase game when the interrogator
needs to choose between the human and the
machine from the beginning of the test.
Turing Imitation Game
Turing believed that by the end of the 20th century it would
be possible to program a digital computer to play the
imitation game. Although modern computers still cannot
pass the Turing test, it provides a basis for the verification
and validation of knowledge-based systems.
A program thought intelligent in some narrow area of
expertise is evaluated by comparing its performance
with the performance of a human expert – Loebner
contest (http://www.aisb.org.uk/events/loebner-prize )
Example of winners of past
Loebner contests
Chatter box : demo a short conversation
https://pandorabots.com/mitsuku/
What are the machine learning
methods?
Artificial Neural Network – imitation how the
human brain works
Evolutionary Computation- imitation of the theory
of evolution
Fuzzy Logic – imitation of human’s uncertainty
Swarm Intelligence – imitation of the behaviors of
the bees and ants
What is Programming Paradigm?
A programming paradigm is a
fundamental style of computer programming, a way
of building the structure and elements of computer
programs.
AI programming paradigm
It is called Logic and symbolic programming
paradigm
It takes a declarative approach to problem-
solving.
Various logical assertions about a situation are
made, establishing all known facts.
Then queries are made. The role of the
computer becomes maintaining data and
logical deduction.
Structure of AI programming
paradigm
A logical program is divided into three sections:
a series of definitions/declarations that define
the problem domain
statements of relevant facts
statement of goals in the form of a query
Sample language : Prolog
(Programming Logic)
Domains
◦ being = symbol
Predicates
◦ animal(being) % all animals are beings
dog(being) % all dogs are beings
die(being) % all beings die
Clauses
◦ animal(X) :- dog(X) % all dogs are animals
dog(fido). % fido is a dog
die(X) :- animal(X) % all animals die
Sample Prolog program and
query
State of the art of AI
Game playing – Deep Blue versus Garry Kasparov was
a human–computer chess matches, in the format of machine
and humans, versus a human.
The matches were played between the IBM supercomputer
Deep Blue with a team of IBM programmers and chess experts
who directed and reprogrammed the machine between games
on the one side, and the World Chess ChampionGarry
Kasparov on the other side.
May 11, 1997: held in New York City, New York
Result: Deep Blue–Kasparov (3½–2½)
State of the art of AI
Natural language understanding
it is the understanding of the meaning behind words
and how they combine to form meaningful sentences
that computers can understand.
IBM's Watson system playing (and
winning) Jeopardy on TV against human competitors
State of the art of AI
Robotics : Asimo Honda robot
http://world.honda.com/ASIMO/
State of the art of AI
Robotics - Kismet (emotional robot)
State of the art of AI
Machine vision : face and facial recognition
Assignment 1 – individual work
Prepare a 5-min presentation that explains about
one of the state-of-the-art of AI.
Presentation date : 2nd lab time
Sample AI applications
http://www.aistudy.com/demo/es_demo.htm
http://pages.cs.wisc.edu/~dyer/cs540/demos.html
http://www.alicebot.org/
Winner of AI chatterbot contest
Review Questions
What is artificial intelligence?
What is an intelligent system?
Explain about Turing Imitation game.
Identify the machine learning methods.
Explain about AI programming paradigm
Identify the states of the art of artificial
intelligence.
