Download AI-01a- Intro - Computer Engineering

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Turing test wikipedia , lookup

Technological singularity wikipedia , lookup

Embodied cognitive science wikipedia , lookup

Ethics of artificial intelligence wikipedia , lookup

History of artificial intelligence wikipedia , lookup

Intelligence explosion wikipedia , lookup

Existential risk from artificial general intelligence wikipedia , lookup

Philosophy of artificial intelligence wikipedia , lookup

Transcript
Introduction to Artificial Intelligence
Lecture 1a: Course Overview and Introduction
CE-40417
MON, WED 1030-1200
Hall 205,Computer Engineering Dept.
Ramin Halavati
Room 308, CE Dept.
[email protected]
WHAT IS INTELLIGENCE AND WHO IS INTELLIGENT?
ABOUT INTELLIGENCE
•
Intelligence is subjective,
– You need not be great in all domains to be called
intelligent.
– Physicists boil watches!
– Frogs, Wasps, Crickets, etc.
•
Intelligence is a relative measure.
– A child who talks fluently.
– A dog which identifies his owner’s voice
– I.Q.
QUOTES ABOUT INTELLIGENCE
•
The ability to carry out abstract thinking. (Terman, 1921)
•
The capacity for knowledge, and knowledge possessed. (Henmon, 1921)
•
The capacity to learn or to profit by experience. (Dearborn, 1921)
•
Intelligence is what is measured by intelligence tests. (Boring, 1923)
•
A global concept that involves an individual's ability to act purposefully,
think rationally, and deal effectively with the environment. (Wechsler,
1958)
•
Intelligence is a general factor that runs through all types of performance.
(Jensen)
•
A person possesses intelligence insofar as he had learned, or can learn,
to adjust himself to his environment. (Colvin 1982)
QUOTES ABOUT INTELLIGENCE
• Intelligence is adaptation to the environment. (unknown)
• Intelligence is that faculty of mind by which order is perceived in a
situation previously considered disordered. (R.W. Young, 1999)
• Intelligent activity consists of grasping the essentials in a given
situation and responding appropriately to them. (unknown)
• Intelligence is the ability to use optimally limited resources including time - to achieve goals. (Kurzweil, 1999)
• Intelligence is what you do when you don't know what to do.
(unknown)
• Intelligence is a hypothetical idea which we have defined as being
reflected by certain types of behavior. (unknown)
WHAT IS ARTIFICIAL INTELLIGENCE?
WHAT IS ARTIFICIAL INTELLIGENCE? - SAMPLES
•
•
•
•
•
•
•
•
•
Thermostats?
Phones that recognize names?
Spelling auto-correction?
Washers that adjust to weight?
Lights that go off automatically?
Spaceships that cruise automatically for years?
Aircrafts Autopilots?
Games?
…
WHAT IS ARTIFICIAL INTELLIGENCE?
• To create machines, smarter than previous ones.
• To add features to machines which machines don’t
have, but human has.
SAMPLES OF HUMAN LEVEL INTELLIGENCE
•
•
•
•
•
•
•
You beat somebody at chess (or checkers or backgammon or go or
Othello or poker).
You prove a mathematical theorem using a set of known axioms.
You are told some facts about the relationship between forests and the
weather and you conclude that the practices of logging companies should
change.
On a particular day, you need to buy a bunch of things, meet three
different people, return some books to the library, and get a certain
amount of exercise. You plan the day in such a way that everything is
achieved in an efficient manner.
You are a lawyer who is asked to defend someone. You recall three similar
cases in which the defendant was found guilty, and you turn down the
potential client.
You are trying to come up with an algorithm to solve a problem using other
algorithms you are familiar with. You have meta-knowledge about how one
should think about algorithms, and you use this knowledge to critique your
algorithm as you create it.
A stranger passing you on the street notices your watch and asks, "Can
you tell me the time?" You say, "It's 3:00," and not simply "Yes."
SAMPLES OF HUMAN LEVEL INTELLIGENCE
•
•
•
•
•
•
You are told to find a large Phillips screwdriver in a cluttered workroom.
You enter the room (you've never been there before), look around, make
your way around without falling over things, and eventually find the
screwdriver.
You are shown five letters in an unfamiliar font. Later you recognize this
font when you see a different character from it, and you are also able to
make good guesses as to what the other characters in the font would look
like.
Asked to prove a geometry theorem, you draw a diagram and use it to
help you.
You're a 6-month-old infant. You can produce sounds with your vocal
organs, and you can hear speech sounds around you, but you don't know
how to make the sounds you're hearing. In the next year you figure out
what the sounds of your parents' language are and how to make them.
Someone taps out a rhythm, and you are able to beat along with it and to
continue to even after it stops.
You're some sort of primitive invertebrate. You know nothing about how to
move about in your world, only that you need to find food and keep from
bumping into walls. After lots of reinforcement and punishment (maybe
generations of it), you get around just fine.
ABSTRCTION OF HUMAN LEVEL INTELLIGENCE
• Learning
• Reasoning
• Problem Solving
• Perception
– Vision
– Audio
• Language
FORMAL DEFINITION of ARTIFICIAL INTELLIGENCE
Human Level
Rational
Behavior
Systems that behave
like humans.
Systems that act
rationally.
Thinking
Systems that think like
humans.
Systems that think
rationally.
HOW TO JUDGE A.I.?
• Systems that think like human.
– Comparison of thinking process with that of human.
• General Problem Solver, (Newel and Simon, 1961)
– Comparison with Psychological Theories
• Gestalt School, Emotions, …
– Inspiration from Biology
• Neural Nets, …
X
Human thinking has lots of mysteries.
HOW TO JUDGE A.I.?
• Systems that think rationally.
– To mathematically / logically prove the approach.
X How to prove a machine recognizes faces correctly?
X How to prove what’s the best action at such
moment?
HOW TO JUDGE A.I.?
• Systems that act like human.
– Turing Test, Alen Turing, 1950
• Basic test:
– Interrogator in one room, human in another, system in a
third
– Interrogator asks questions; human and system answer
– Interrogator tries to guess which is which
– If the system wins, it’s passed the Turing Test
• The system doesn’t have to tell the truth (obviously…)
THE TURING TEST
http://aimovie.warnerbros.com
http://www.ai.mit.edu/projects/infolab/
THE TURING TEST
http://aimovie.warnerbros.com
http://www.ai.mit.edu/projects/infolab/
THE TURING TEST
http://aimovie.warnerbros.com
http://www.ai.mit.edu/projects/infolab/
THE TURING TEST
http://aimovie.warnerbros.com
http://www.ai.mit.edu/projects/infolab/
THE TURING TEST
http://aimovie.warnerbros.com
http://www.ai.mit.edu/projects/infolab/
HOW TO JUDGE A.I.? – Turing Test continued
• Basic Test:
– Natural Language Processing
– Knowledge Representation
– Reasoning
– Learning
• Additional Subjects:
– Emotions, Characteristics
– Vision
– Speech recognition and production
– Robotics
HOW TO JUDGE A.I.?
• Systems that behave rationally
– A rationality measure
– Distance to goal
– False alarms
– Bounded rationality
HOW TO JUDGE A.I.?
• The Engineering View:
– It’s just working that matters.
– Does it have customers?
CLASS TARGET
• Getting a Feeling of Artificial Intelligence, its fields,
open problems, and schools of thought
• Learning some basic tools of Artificial Intelligence
• Having a little experience with Artificial Intelligence
TEXT BOOK
Chapters 1 - ~13
Search, Games
Logic & Reasoning
Planning
+ Some additional
parts, if possible.
ASSESSMENTS:
•
•
•
•
•
•
Mid Term Exam:
Final Exam:
Exercises:
Project:
Presentation:
Class Work:
50% (2 weeks after end of chapter 6)
50%
4 points - Optional
2..3 points - Optional
-1..+2 points - Bonus
+X
• WARNINGS:
– If the exams sum < 50%, it would be multiplied in
Exercises and Project.
– The deadlines are deadly serious.
– It is highly recommended not to count only on
exams.
Contacts
To join mailing list:
mail to: [email protected] w/ subject ADD2LIST
Questions, discussions, etc.:
• All days, 9-16,
Room 308.
Preferably, even days.