Intelligent Systems 2II40 C1

1
Intelligent Systems (2II40)C1

• Alexandra I. Cristea

September-November 2005
2
Outline

• Administrative issues
• Course overview
• What are Intelligent Systems?
• A brief history
• State of the art
• Intelligent agents

3
Book references

• Artificial Intelligence, A Modern Approach, S.
  Russel, P. Norvig (2nd edition) Prentice Hall
• Intelligent Systems for Engineers and Scientists,
  A.A. Hopgood (2nd edition) CRC
• Intelligent Systems, Architecture, Design and
  Control, J.S. Albus, S. M. Meystel, L. A. Zadeh,
  Wiley
• Web Dynamics, Adapting to Change in Content,
  Size, Topology and Use, M. Levene, A.
  Poulovassilis (Eds.), Springer
• Soft Computing and Intelligent Systems Design,
  Theory, Tools and Applications, F.O. Karray, C.
  D. Silva, Addison Wesley

4
Administrative issues

• 2II40 Intelligent Systems course site
• http//wwwis.win.tue.nl/alex/HTML/IS/
• Check Thursdays Tuesdays (frequent updates!!)
• Will contain ALL powerpoint presentations,
  schedule, extra material, info on course
  development assignments
• Name list
• student ID, first-last name, educational
  direction, email
• Evaluation (each item below has to be passed,
  i.e., 60 completed to graduate below are the
  contributions to the final grade)
• Exam 40 (individual)
• Projects 40 (group)
• Small assignments (homeworks) 20 (group)

5
Questions, homework delivery

• mailto a.i.cristea_at_tue.nl
• Subject IS course 2II40 ltsubject matter titlegt
• Body
• ltstudent ID, firstlast name, educational
  directiongt
• If referring to group work, also ltgroup IDgt
• If referring to a homework, also ltassignment
  IDgt
• ltsubject matter gt
• Note unless otherwise specified, homeworks
  should be delivered BEFORE the next course
  (date on e-mail counts)
• late homeworks dont count
• Homeworks count for points for final grade

6
Homeworks (20 grade) send by e-mail

• make groups of 4-5 people for homeworks project
  
• send info via e-mail (check e-mail format one
  e-mail per group, w. one e-mail contact person
  per group)

7
Project (40 grade)

• Performed in a group
• Checked at various stages (topic selection, PEAS,
  two presentations (interim final, see schedule)
• On a selected topic from the Course overview

8
Programming

• Some assignments and/ or projects might
  contain programming tasks
• you can perform them in any language you are
  familiar with (C, C, Prolog, Lisp, etc.)
• Note this is NOT a programming course

9
Course Goals

• more breadth (theoretical knowledge)
• more depth (hands-on experience)
• learn a further framework for discriminating and
  interrelating approaches to AI
• survey the increasingly broad range of AI
  applications
• take on (larger) AI programming projects
• take first steps towards AI research
• learn to separate implementation details from
  research topics

10
Course overview

• Introduction IS
• Intelligent agents
• Search
• Knowledge and reasoning
• Planning
• Uncertainty
• Learning
• Hybrid systems

11
Course overview

• Introduction IS
• Intelligent agents
• Search
• Knowledge and reasoning
• Planning
• Uncertainty
• Learning
• Hybrid systems

12
What is an Intelligent System?

• System that
• does everything that I want it to do nothing
  that I dont
• Human-like reasoning
• recover from failure
• Learns from its mistakes
• Adapts to its environment
• Makes decision about appropriateness of actions

13
(No Transcript)
14
What are Intelligent Systems?

• (What is AI?)

15
Turing test (50)
16
Turing test pros cons

• Predicted that by 2000 a machine might have a 30
  chance of fooling a lay person for 5 min
• Anticipated major arguments against AI
• Pb not reproducible, constructive, allows no
  mathematical analysis
• Suggested major components of AI knowledge,
  reasoning, language understanding, learning

17
Acting rationally

• Doing the right thing
• Expected to maximize goal achievement, given
  available info
• Doesnt necessarily involve thinking!!
• Reflexes, etc.

18
Dimensions of AI

• symbolic or sub-symbolic (i.e., numerical)
• manually engineered or automatically learned
• cognitively plausible
• perfect world assumption or probabilistic
• evaluated by hunch, single example, authoritative
  tone of voice or numerical measure
• classification, numerical or planning
• full system or human-assistor
• online or offline
• real-time or offline
• intelligent or just software engineering
• sound theoretical foundation or trialerror

19
(some) Categories of intelligent system software
All software
Knowledge based systems
Computational intelligence
Rule based systems
Expert systems
NN
Evolutionary alg.
Bayesian updating, Certainty theory, Fuzzy logic
Simulated Annealing
Objects, frames, agents
20
Example intelligent agent Steve

• http//www.isi.edu/isd/VET/steve-demo.html

Acting rationally humanly
Collaboration
21
Example evolution
Evolving artificial creatures, Karl Sims
http//biota.org/ksims/blockies/index.htmlvideo
22
Other Intelligent Systems
Distributed intelligence
23
Applications of Intelligent Systems
24
Applications of Adaptive Systems

• expert systems
• (e.g. medical diagnosis)
• data mining
• (e.g. search engines)
• computational linguistics
• games

25
More Applications

• Parallel computing
• evolution of cellular automata
• Molecular biology
• molecular evolution, design of useful molecules,
  protein design
• Computer security
• immune systems for computers
• Intelligent agents and robotics Internet!!
• Scientific modeling
• evolution, ecologies, economies, insect
  societies, immune systems, organizations

26
AI is New Science

• We're still learning about perceiving, planning
  and learning
• It is hard to compare methods/paradigms

You'll be pointed at research literature
I'm you're tour guide methods and applications
27
Should we replace people with machines?

• Yes. Expand the meaning of "grunt-work", and make
  a machine do it.
• No. The devastating dehumanisation of automation.
  
• No. Economic objections?
• No. A National Aeronautics and Space
  Administration report supporting manned space
  exploration states, "Man is the lowest cost,
  150-pound, non-linear, all-purpose computer
  system that can be mass produced by unskilled
  labour."
• with built-in sense-of-humour system
• Yes. what about the expense of life support and
  litigation?
• No. Nothing's gonna replace people I'm a
  humanitarian

28
Homework 1 (group)

• Send the list of members of the group (student
  ID, name, email) contact person
• Check who won this years Loebner prize for the
  Turing test. What technique does the IS use?
• Find (google) a system for every buzzword
  (category) of intelligent system software
  mentioned earlier. Give system name, short
  description, link.
• Find a definition of cognitive science, as well
  as for logic (laws of thought), the other 2
  dimensions of intelligent systems.
• Find at least 3 application areas of Intelligent
  Systems that are not mentioned here.
• Define your general info on your project (at
  least desired topic, programming language)

29
Course overview

• Introduction IS
• Intelligent agents
• Search
• Knowledge and reasoning
• Planning
• Uncertainty
• Learning
• Hybrid systems

30
II. Intelligent agents

• Rational agent generalities
• Agent its environment
• Example a simple agent
• Rationality defined
• Task environment
• PEAS
• Proprieties
• Agent proprieties