Transcript Introduction to the course

CS 2710, ISSP 2610
Foundations of Artificial
Intelligence
introduction
1
Outline
• Course information and syllabus
• Introduction to AI
2
4 Views of AI
“The automation of activities
that we associate with human
thinking…”
Bellman 1978
“The study of mental faculties
through the use of
computational models”
Charniak&McDermott
“The art of creating machines
that perform functions that
require intelligence when
performed by people.”
(Kurzweil, 1990)
“The branch of CS that is
concerned with the automation
of intelligent behavior.”
Lugar&Stubblefield
3
Basic Framework
Getting computers to do the right thing
based on their circumstances and
what they know.
4
Applied Areas of AI
•
•
•
•
•
•
Game playing
Speech and language processing
Expert reasoning and theorem proving
Planning and scheduling
Vision
Robotics
5
Some Examples
• Playing chess
• Driving on the
highway
• Mowing the lawn
• Answering
questions
• Recognizing
speech
• Diagnosing
diseases
• Translating
languages
6
AI is a synergy among…
• Philosophy: Can a machine think?
What are knowledge and belief?
Logic and reasoning…
• psychology and cognitive science:
problem solving skills…
• Linguistics: syntax, semantics,
pragmatics…
7
Synergy Among…
• Computer science and engineering:
complexity theory, algorithms, logic and
inference, programming languages, system
building,…
• Mathematics, physics: statistical modeling,
complex systems, chaos, game theory,…
• Economics: decision theory,…
• Neurobiology: how does the brain process
information?...
8
What’s involved in intelligence?
• Ability to interact with the real world
– Perceive, understand, and act
• Reasoning and planning
– Modeling external world
– Problem solving, planning, decision making
• Learning and adaptation
9
Goals in AI
• Engineering goal: solve real-world
problems. Build systems that exhibit
intelligent behavior
• Scientific goal: To understand what
kinds of computational mechanisms
and knowledge are needed for
modeling intelligent behavior
10
Turing Test (1950)
• Interrogator asks questions of two
agents who are out of sight and
hearing. One is person the other is a
computer.
• If the interrogator can’t reliably
distinguish between human and
computer, then the computer is
deemed “intelligent”
11
Eliza (Joseph Weizenbaum in
the last 60s)
• Takes the role of a psychoanalyst in a
psychiatric interview.
• Sample dialog and modern Turning
test
12
Turing Test
• Pros: Objective evaluation. Focus on
behavior (how could we evaluate
whether a computer thinks like a
human?)
• Cons: as much a test of the judge as
it is of the machine; promotes
development of artificial con artists
(Newel and Simon 1976). But….
13
Passing the Test
• Free conversation is very hard
• But people are prone towards
attributing human qualities to
technology
14
Implications
• Whether or not we set out to build
intelligent interactive agents, people
expect computers to act like people
15
Challenges Ahead
• Systems lack generality and
adaptability
• They can’t easily switch contexts
• Key problems: knowledge acquisition,
lack of commonsense knowledge, lack
of sufficient data, what aspects of
context are relevant?
16
Example
• Information extraction example:
consider brittleness and what we
could do about it
17
In-Class Discussion Questions
• This file
18