Transcript Chapter 11: Intelligent Support Systems

Chapter 11
Intelligent Support Systems
Agenda
•
•
•
•
Artificial Intelligence
Expert Systems (ES)
Differences between ES and DSS
ES Examples
Artificial Intelligence
• Effort to develop computer-based systems
that behave like humans:
–
–
–
–
Learn languages
Accomplish physical tasks
Use a perceptual apparatus
Emulate human thinking
AI Branches
•
•
•
•
•
•
Natural language
Robotics
Vision systems
Expert systems
Intelligent machines
Neural network
Agenda
•
•
•
•
Artificial Intelligence
Expert Systems (ES)
Differences between ES and DSS
ES Examples
ES
• Feigenbaum
“intelligent computer program
using knowledge / inference procedures to
solve problems difficult enough to require
significant human expertise; a model of the
expertise of the best practitioners”
Components of an Expert System
•
•
•
•
•
•
•
Knowledge acquisition facility
Knowledge base (fact and rule)
Inference engine
User interface
Explanation facility
Recommended action
User
Reasons For Using ES
•
•
•
•
•
•
•
Consistent
Never gets bored or overwhelmed
Replaces absent, scarce experts
Quick response time
Cheaper than experts
Integration of multi-expert opinions
Eliminate routine or unsatisfactory jobs for
people
ES Limitations
• High development cost
• Limited to relatively simple problems
– limited domain
– operational mgmt level
• Can be difficult to use
• Can be difficult to maintain
When to Use ES
•
•
•
•
•
High potential payoff
Reduced risk
Need to replace experts
Need more consistency than humans
Expertise needed at various locations
at same time
• Hostile environment dangerous to human
health
Agenda
•
•
•
•
Artificial Intelligence
Expert Systems (ES)
Differences between ES and DSS
ES Examples
ES Versus DSS
• Problem Structure:
– ES: structured problems
•
•
•
•
clear
consistent
unambiguous
limited scope
– DSS: semi-structured problems
ES Versus DSS
• Quantification:
– DSS: quantitative
– ES: non-mathematical reasoning
IF A BUT NOT B, THEN Z
• Purpose:
– DSS: aid manager
– ES: replace manager
Agenda
•
•
•
•
Artificial Intelligence
Expert Systems (ES)
Differences between ES and DSS
ES Examples
Deep Blue
• World chess champion
Gary Kasparov
• IBM chess computer
“Deep Blue”
• 1997 match
• Deep Blue’s human programmers
included chess master
Deep Blue
• Included database that plays endgame
flawlessly
– 5 or fewer pieces on each side
• Can Deep Blue calculate possibilities of
earlier play?
• Kasparov lost - became frustrated and
played poorly
MYACIN
• Diagnose patient symptoms (triage)
– Free doctors for high-level tasks
• Panel of doctors
– Diagnose sets of symptoms
– Determine causes
– 62% accuracy
MYACIN
• Built ES with rules based on panel
consensus
• 68% accuracy
Stock Market ES
• Reported by Chandler, 1988
• Expert in stock market analysis
– 15 years experience
– Published newsletter
• Asked him to identify data used to make
recommendations
Stock Market ES
• 50 data elements found
• Reduced to 30
– Redundancy
– Not really used
– Undependable
• Predicted for 6 months of data whether
stock value would increase, decrease, or
stay the same
Stock Market ES
• Rule-based ES built
• Discovered that only
15 data elements needed
• Refined the ES model
• Results were better than expert
Points to Remember
•
•
•
•
Artificial Intelligence
Expert Systems (ES)
Differences between ES and DSS
ES Examples
Discussion Questions
• What do you think about the following
statement?
– “Expert systems are dangerous. People are
likely to be dependent on them rather than
think for themselves.”
• What kind of ES does your organization
have?
• What kind of ES will benefit your
organization?
Assignment
•
•
•
•
Review chapters 7-11
Read chapter 12
Group assignment
Research paper