This would be an example of a two line header

1
Neuro-Fuzzy and Soft Computingchapter 1 J.-S.R.
Jang
Bill Cheetham Kai Goebel
2
What is covered in this class?

• We will teach techniques useful in creating
  intelligent software systems that can deal with
  the uncertainty and imprecision of real world
  problems
• Some components of Intelligent systems are
• human-like - they possess human-like expertise
  within a specific domain,
• adaptable - they adapt themselves and learn to do
  better in a changing environment, and
• explanations - they explain how they make
  decisions or take actions

3
How will we teach the techniques?

• We will present
• multiple techniques from Soft Computing ,
• when each technique is applicable
• examples of industrial applications
• If the only tool you have is a hammer, then
  every problem looks like a nail
• - anonymous

4
What is Soft Computing?

• Soft Computing is a field that currently includes
• Fuzzy Logic
• Neural Networks
• Probabilistic Reasoning(Genetic Algorithms, BBN),
  and
• Other related methodologies
• Case-Based Reasoning
• Soft Computing combines knowledge, techniques,
  and methodologies from the sources above to
  create intelligent systems

5
Why is this important?
Farming corn cows

• The information revolution going on is allowing
  us to automate information processing tasks which
  require intelligence much like the industrial
  revolution automated manufacturing tasks
• Soft Computing techniques have already been
  applied successfully.

Industrial Revolution
Manufacturing chairs cars
Information Revolution
Service content and code
6
Business Week Magazine
The 21st Century Corporation (August 21-28,
2000)http//www.businessweek.com/2000/00_35/b3696
001.htm
7
Business Week Magazine
The 21st Century Corporation (August 21-28,
2000)http//www.businessweek.com/2000/00_35/b3696
001.htm
8
Business Week Magazine
The 21st Century Corporation (August 21-28,
2000)http//www.businessweek.com/2000/00_35/b3696
001.htm

• The biggest profits will go to those that manage
  information, not physical products
• Cost of a bank transaction teller 1.25, phone
  54 cents, ATM 24 cents, Internet 2 cents.
• Roughly 90 of Ciscos orders come into the
  company without ever being touched by human
  hands, and 52 of them are fulfilled without a
  Cisco employee being involved
• Companies will give consumers the tools to design
  and demand exactly what they want
• Dell custom makes each computer
• PG allows customers to custom design cosmetics
  and perfume

9
Soft Computing

• The essence of soft computing is that unlike the
  traditional, hard computing, soft computing is
  aimed at an accommodation with the pervasive
  imprecision of the real world. Thus, the guiding
  principle of soft computing is to exploit the
  tolerance for imprecision, uncertainty, and
  partial truth to achieve tractability,
  robustness, low solution cost, and better rapport
  with reality
• - Lotfi Zadeh

10
Fuzzy Logic - Kai

• Sets with fuzzy boundaries

A Set of tall people
11
Fuzzy Set Theory - Kai
Fuzzy set theory provides a systematic calculus
to deal with imprecise or incomplete
information Fuzzy if-then rules are used in
fuzzy inference systems If lt1gt is tall and lt1gt
is athletic then lt1gt is good basketball player.
T-norm
A
B
A
B
C
w
Z
X
Y
12
Neural Networks - Kai

• Pattern matching technique where input patterns
  are matched with a specific output pattern.
  Modeled after the neurons in the brain.

Network architecture Weights on the links
13
Case-Based Reasoning - Bill
A methodology of solving new problems by adapting
the solutions of previous similar
problems Models the way experts reason using
their experience
14
Genetic Algorithms

• An optimization technique

10010110 01100010 10100100 10011001 01111101 . .
. . . . . . . . . .
10010110 01100010 10100100 10011101 01111001 . .
. . . . . . . . . .
Elitism
Selection
Crossover
Mutation
Current generation
Next generation
15
Other Techniques - Bill

• Bayesian belief networks
• represent and reason with probabilistic
  knowledge
• Decision Trees
• classification using tree structure
• Least-squares estimator
• statistical regression
• Hybrid approaches
• use multiple techniques

16
Soft Computing is a Hybrid Method
dog dag
Knowledge base
Neural Character Recognizer
Animal?
dog
17
How does SC Relate to Other Fields
What is AI?
AI is the study of agents that exist in an
environment and perceive and act. (S. Russell
and P. Norvig)
AI is the art of making computers do smart
things. (Waldrop)
AI is a programming style, where programs
operate on data according to rules in order to
accomplish goals. (W. A. Taylor)
AI is the activity of providing such machines as
computers with the ability to display behavior
that would be regarded as intelligent if it were
observed in humans. (R. McLoed)
18
How does SC Relate to Other Fields
What is AI? (Jang)
The long term goal of AI research is the creation
and understanding of machine intelligence
Broad Definition
Conventional AI research focuses on an attempt to
mimic human intelligent behavior by expressing it
in symbolic rules
Narrow Definition
19
How does SC Relate to Other Fields
What is an Expert System (ES)?
Questions Responses
Inference Engine
User
KB rules facts
Knowledge Acquisition
Knowledge Engineer
20
How does SC relate to other fields?
symbolic manipulation
AI
Machine Learning
automatic improvement with experience
Soft Computing
Cognitive Psychology
Statistics
Probability (not possibility)
Study of the mind
uncertainty and imprecision
21
Soft Computing Characteristics
Human Expertise (if-then rules, cases,
conventional knowledge representations)
Biologically inspired computing models (NN)
New optimization techniques (GA, simulated
annealing)
Model-free learning (NN, CBR)
Fault tolerance (deletion of neuron, rule, or
case)
Real-world applications (large scale with
uncertainties)
22
The end