Refinement Planning: Status and Prospectus - PowerPoint PPT Presentation

About This Presentation
Title:

Refinement Planning: Status and Prospectus

Description:

coast to coast. CMU's RALPH program drove a van for all but 52 miles ... A focus on problems that do not respond to algorithmic solutions. ... – PowerPoint PPT presentation

Number of Views:64
Avg rating:3.0/5.0
Slides: 25
Provided by: MBE
Learn more at: https://pages.mtu.edu
Category:

less

Transcript and Presenter's Notes

Title: Refinement Planning: Status and Prospectus


1
1946 ENIAC heralds the dawn of Computing
2
1950 Turing asks the question.
I propose to consider the question
Can machines think?
--Alan Turing, 1950
3
1995 RALPH takes a trip from coast to coast
CMUs RALPH program drove a van for all but 52
miles of a trip from D.C. to San Diego
4
1996 EQP proves that Robbins Algebras are all
boolean
An Argonne lab program has come up with a major
mathematical proof that would have been called
creative if a human had thought of it.
-New
York Times, December, 1996
5
Jan 12, 1997 HAL 9000 becomes operational in
fictional Urbana, Illinois
by now, every intelligent person knew that
H-A-L is derived from Heuristic ALgorithmic
-Dr. Chandra, 2010 Odyssey Two

6
May, 1997 Deep Blue beats the World Chess
Champion
vs.
I could feel human-level intelligence across the
room -Gary Kasparov, World Chess
Champion (human)
7
May, 1999 Remote Agent takes Deep Space 1 on a
galactic ride
8
May 2000 SCIFINANCEsynthesizes programsfor
financial modeling
  • Develop pricing models for complex derivative
    structures
  • Involves the solution of a set of PDEs (partial
    differential equations)
  • Integration of object-oriented design, symbolic
    algebra, and plan-based scheduling

9
Sept. 2002 Cindy Smart marketed
  • Vision can read, tell the time
  • Speech recognition can recognize 700 words and
    77 phrases
  • Voice synthesis speaks with a soft voice

10
What else?
  • Real-time response
  • robustness
  • autonomous intelligent interaction with the
    environment
  • planning
  • communication with natural language
  • commonsense reasoning
  • creativity
  • learning
  • ???

11
Administrivia
  • Textbook Lugers Artificial Intelligence, 2002,
    Addison Wesley
  • Grading
  • Assignments 40
  • Midterm Exam 1 20
  • Midterm Exam 2 20
  • Final Exam 20
  • Academic honesty

12
Contents
  • PART I Artificial Intelligence Its Roots and
    Scope
  • Chapter 1 AI History and Applications
  • PART II Artificial Intelligence as
    Representation and Search
  • Chapter 2 The Predicate Calculus
  • Chapter 3 Structures and Strategies for State
    Space Search
  • Chapter 4 Heuristic Search
  • Chapter 5 Control and Implementation of
    State-Space Search

13
Contents (contd)
  • Part III Representation and Intelligence The AI
    Challenge
  • Chapter 6 Knowledge Representation
  • Chapter 7 Strong Method Problem Solving
  • Chapter 8 Reasoning in Uncertain Situations

14
Contents (contd)
  • Part IV Machine Learning
  • Chapter 9 Machine Learning Symbol-based
  • Chapter 10 Machine Learning Connectionist
  • Chapter 11 Machine Learning Social and Emergent

15
Contents (contd)
  • Part V Advanced Topics for AI Problem Solving
  • Chapter 12 Automated Reasoning
  • Chapter 13 Understanding Natural Language

16
Contents (contd)
  • Part VI Languages and Programming Techniques for
    AI
  • Chapter 14 An Introduction to Prolog
  • Chapter 15 An Introduction to Lisp
  • Part VII Epilogue
  • Chapter 16 Artificial Intelligence as Empirical
    Enquiry

17
What is AI?
18
Figure 1.1 The Turing test.
19
Definitions of AI
  • Systems that think like humans
  • Systems that act like humans
  • Systems that think rationally
  • Systems that act rationally

20
Question
  • What would impress you as an
  • intelligent system?

21
Important Research and Application Areas
  • Game playing
  • Automated Reasoning and Theorem Proving
  • Expert Systems
  • Natural Language Understanding and Semantic
    Modeling
  • Modeling Human Performance
  • Planning and Robotics
  • Languages and Environments for AI
  • Machine Learning
  • Alternative Representations Neural Nets and
    Genetic Algorithms
  • AI and Philosophy

22
Important Features of AI
  • The use of computers to do reasoning, pattern
    recognition, learning, or some other form of
    inference.
  • A focus on problems that do not respond to
    algorithmic solutions. This underlies the
    reliance on heuristic search as an AI
    problem-solving technique.
  • A concern with problem solving using inexact,
    missing, or poorly defined information and the
    use of representational formalisms that enable
    the programmer to compensate for these problems.

23
Important Features of AI (contd)
  • Reasoning about the significant qualitative
    features of a situation.
  • An attempt to deal with issues of semantic
    meaning as well as syntactic form.
  • Answers that are neither exact nor optimal, but
    are in some sense sufficient. This is a result
    of the essential reliance on heuristic
    problem-solving methods in situations where
    optimal or exact results are either too expensive
    or not possible.

24
Important Features of AI (contd)
  • The use of large amounts of domain-specific
    knowledge in solving problems. This is the basis
    of expert systems.
  • The use of meta-level knowledge to effect more
    sophisticated control of problem solving
    strategies. Although this is a very difficult
    problem, addressed in relatively few current
    systems, it is emerging as an essential area of
    research.
Write a Comment
User Comments (0)
About PowerShow.com