CS 2710, ISSP 2610 Foundations of Artificial Intelligence

1
CS 2710, ISSP 2610Foundations of Artificial
Intelligence

• introduction

2
Outline

• Course information and syllabus
• Introduction to AI

3
4 Views of AI
4
Basic Framework

• Getting computers to do the right thing based on
  their circumstances and what they know.

5
Applied Areas of AI

• Game playing
• Speech and language processing
• Expert reasoning and theorem proving
• Planning and scheduling
• Vision
• Robotics

6
Some Examples

• Playing chess
• Driving on the highway
• Mowing the lawn
• Answering questions

• Recognizing speech
• Diagnosing diseases
• Translating languages

7
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

8
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?...

9
Whats 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

10
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

11
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 cant reliably distinguish
  between human and computer, then the computer is
  deemed intelligent

12
Eliza (Joseph Weizenbaum in the last 60s)

• Takes the role of a psychoanalyst in a
  psychiatric interview.
• Sample dialog and modern Turning test

13
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.

14
Passing the Test

• Free conversation is very hard
• But people are prone towards attributing human
  qualities to technology

15
Implications

• Whether or not we set out to build intelligent
  interactive agents, people expect computers to
  act like people

16
Challenges Ahead

• Systems lack generality and adaptability
• They cant easily switch contexts
• Key problems knowledge acquisition, lack of
  commonsense knowledge, lack of sufficient data,
  what aspects of context are relevant?

17
Example

• Information extraction example consider
  brittleness and what we could do about it

18
In-Class Discussion Questions

• This file