Intelligent technologies

1
Intelligent technologies

• Why ? How ?

(Long version)
Prof. Peter Sincak TU Kosice Center for
Intelligent Technologies http//www.ai-cit.sk
2
Siemens AG Vienna, Austria

• Maria-Curie Fellowship within
• the 5. FP of European Union
• November, 2001 May, 2002
• Project
• Computational Intelligence in
• Real World Applications

3
Goal of this talk

• Explain or remind the basic principles of
  Intelligent technologies
• Basic principles and features of neural networks,
  fuzzy systems, evolutionary computing and hybrid
  systems
• Point out application potential and domains
• Some notes to the future technologies

4
Basic principles

• Historical background
• What is intelligence ??
• Basic features of Intelligent systems and
  Intelligent technologies
• What type of tasks could be under consideration
  using intelligent technology ?
• Can you call your product intelligent ?????

5
What is historical backgroundof AI ????
6
Basic facts about history of AI
First mentioning of the brain
Edwin Smith Papyrus
from 1700 BC info from 2625 BC Imhotepa first
surgeon ( also building pyramids and astr.)
Ebers papyrus - 110 pqges qbout anatomy Includig
brain and ist function

• Aristoteles (355 BC ) - his important
• work on memory, dreams and so on.

7
Basic facts about history of AI
First AI people fortune tellers extrapolating
life
Blaise Pascal's Pascaline (first calculating
machines) - 1642
G.W. Liebnitz (1646-1716) he was first Who
said brain is based on mathematics
Calculemus... "Let us calculate!" Goerge Boole
(1815-1864) in book Investigation of Minds
laws .. The mathemathics what has to be
discovered is mathematics of the human
intellect
8
Basic facts about history of AI
Computers and Intelligence Turingov
test Artificial neural network Book
Cybernetics - gt AI How you program the
machine To achieve ability to learn
??? Establishing AI as research Field
A. M. Turing - (1912-1954) W. McCulloch W.
Pitts (43) N. Wiener (1948) C. Shannon
(1953) Ashby (1952) Univ. Dartmouthe (56)
More about history Quo Vadis AI ???
9
Artificial Intelligence leading edge of
technolgy
M. Minski
N. Wiener
A. Turing
10
What is Artificial (machine) intelligence ?
11
Terminology non-unified
Non-unified USA, Japan, Európa
12
What is intelligence ?

• It is very complex notion but .....
• Intelligence is a feature to learn from
  experience
• What is Artificial Intelligence number of
  tools of AI

13
Basic tools of Computational Intelligence
Computational Intelligence (Prof.
Bezdek) Softcomputing (Prof. Zadeh)
Hybrid Systems
Alife
NN
FS
GA, GP
VI virtuálna realita
Virtual Intelligence
Workshop on VI - Sweeden
http//msia02.msi.se/lindblad/vi-dynn/vi-dynn.htm
l
14
Basic features of Intelligent systems and
Intelligent technologies
15
What are the main features of Intelligent
Systems ???
knowledge representation archivation
learning
reasoning - problem solving
Intelligent Technologies
Intelligent Systems
16
Why Intelligent ???

• Intelligence knowledge
• (Biologically inspired systems, brain-like
  systems)
• Knowledge in data (neural networks)
• Knowledge in experience (fuzzy logic)
• Knowledge in state space heuristic search,
  chaos (evolutionary computing, evolution)

17
Knowledge from data

• How to obtain some new info from data
  (Datamining ) ?
• How to Model complex system based on data ?
• How to make Rules extraction from data ?
• How Clusters in the hyperdimensional space ?
• How to handel data if you do not know their
  statistical distribution ?
• How to handle data non-statistical approach
• (model-free, can do everything as statistics
• and more )

18
Knowledge from experience

• How to extract knowledge from human experts?
• How to incorporate their knowledge into system?
• How to create link human experience machine?
• How to make a knowledge fusion from more experts
  and also knowledge replication ?

19
Knowledge in state space

• How to find a solution e.g. optimal coeficient
  if there is no idea how large is a state space
  ?
• How efectively search a space to find an optimal
  parameters ?
• If other approaches (including statistical) are
  failing to find a optimal or suboptimal values
  what should we do ?

20
What type of tasks could be under consideration
using intelligent technology ?
21
What type of problems ?

• Classification from data and human experience
• Modelling from data or human experience
• Prediction forecast
• Optimalization finding the optimal values
• Human-machine interface (human-centered)

22
In which areas IT were used and have application
potential ? (Business)

• Credit rating and risk assessment
• Insurance risk evaluation
• Fraud detection
• Insider dealing detection
• Marketing analysis , Mailshot profiling
• Signature verification , Inventory control
• Prediction of prices, electricity load and
  discharge

23
In which areas IT were used and have application
potential ? (engineering)

• Machinery defect diagnosis
• Signal processing , Character recognition
• Process control supervision , fault analysis
• Speech , vision and color recognition
• Radar signal classification
• Aircraft control, Car brakes
• Integrated circuit layout
• Image compression
• Prediction of signals and values in engineering

24
Can you call your product intelligent ?? Why not
???Will it have impact on demand and sales
???????
25
Home appliances
Company BPL Product washing machine ABS
50F Fuzzy system decides the type of Program
amount of water and washing ingredients
Company BPL Product washing machine ABS
60 NF Neuro-fuzzy system detects a type of
material in the machine and decides the type of
the program and amunt of water and washing
ingredients.
26
Home Appliances
Company Videocon-international Product
washing machine V-NA- 45 FDX The same as
before just 996 different cycle to choose from
. Which on is decided By neuro-fuzzy system
Company Videocon-internetional Product
Washing machine Fuzzy control of the machine
27
Home appliance
Company Sanyo Product washing
machine ASW-F60T The same concept made by
company
Company LG Product Refrigerator Neural
fuzzy system controls the freezing procedures in
the refrigirator
28
Home appliance
Company Sanyo Cook , owen cooker
ECJ-5205SN According to the senszors of infra,
thermal senzor a huminity senzor it estimate a
meal quality and determine A time of cooking.
29
Electronics
Company Sharp Product microwave owen Accoding
to the analysis of the inside air the lenght of
the cooking is controlled. The analysis of the
Food smell during cooking is matter of interest.
Company Videocon Product air-conditioner Neuro
-fuzzy control of air-conditioner to keep equal
temperature within the room
30
Electronics
Company Cannon Product videocamera Canon uses
fuzzy system with 13 rules to focus the
objectives based on the information in the image
characteristics
Company Mitsubishi Product TV set Make a
neural controller to adjust the image contrast
according to the broadcast image. This adaptive
approach produce a very good User feeling while
seeing TV program.
31
Electronics
Company Samsung Product Blod pressure
measurement Fuzzy system controls the overall
process of Blood measurement
Company Samsung Product Camera Fuzzy control
of image focusing sharpening
32
Electronics
Company JVC porduct car-radio Using neural
networks it is able to control car radio with
high reliability and adapt to the voice of the
speaker.
Company IntelaVoice Product switcher controled
by voice Using neural networks it is able to
control the switch with high reliability and
adapt to the voice of the speaker.
33
Copy machines
Company Canon Product Copy Machine Series of
CLC700 a CLC800 have a fuzzy control of the toner
to achieve the best results
Company Panasonic Product Copy machine In the
series FP-1680 up to FP-4080 is implemented a
neuro-fuzzy system to control various parameters
to get the best copy results as possible
34
Car industry
Companies Mercedes Hyundai Mercedes in
model CLK use Automatics transmission based on
Highly adaptive technology to adapt to the style
of the driver. Similar approach is in XG Hyundai
model.
Company BMW BMW uses long time a fuzzy
approach in ABS brake system which adapts the
braking process with the aim to avoid blocking
phase. Also in other advance systems these
technologies are used.
35
Car Industry

• Company Siemens AG
• Product Smart Airbag
• Smart airbags for persons safety uses some
  parts of intelligent technologies including
  adapting
• safety measures to the people.

36
Internet sources aproximate measures

• Applications neural engineering 56

Applications of of fuzzy - 35
Applications of EC 9
37
Basic principles of neural technology
38
What is Neural network ???

• In neural technology -

• It is massively parallel processor which tends
  to
• store knowledge

theory
It is biologicky inspired system tries to
simulate the Brain functionality because it has
simulation

• Interneural connections and network topology
  used storing knowledge
• it learns by examples (data)
  

implementation
39
What kind of neural networks we do have
Recurent NN
Feedforward NN
output
Input
output
layer
neurons
hidden
Synaptic weights
layer
40
Neuron basic processing element
wm
F
F
F
a
o
i
output
w1
input
activation
output
w0
function
Function
function
input
-1
41
Basic approaches in neural technology

• Supervised training by examples so you are
  getting neural network a tool for classification,
  modelling , prediction and etc. You have to
  have a data
• (input-output examples)
• Unsupervised training so you are able to neural
  network for clustering, dimentionality reduction,
  compression etc.
• (only input data)

42
What type of problems especially with NN

• classification
• neural control more nelinearity
• prediction problems based on history
• signal tranformation
• clustering in hyper-dimensional space
  (diagnostic applications)
• many other

43
Basic principles of fuzzy technology
44
What is fuzzy system ??

• Based on fuzzy logic fuzzy sets

It is good for expressing verbal values (small
people, mid-size people, tall people)
1
small
tall
mid
150
140
168
175
Height of people
45
Why fuzzy set is important ?

• You are able to describe a experience or
  behavior of the system in the form of
• IF .............. THEN ............... rules
  
• e.g.
• IF a car is big AND car is expensive THEN car is
  fast

Preposition
Consequens
46
Fuzzy system (controller) basic tool
De-fuzzification
Crisp output
Rule - Base (made by expert)
inference
Experience From the Expert
fuzzification
Crisp input
47
Where is good fuzzy logic ??

• Modeling e.g.
• experience in washing

Washing machine
In case when you are not able to get model and
you Are able to describe behavioral model by
fuzzy rule
Behavioral Model of the system
In case if you want to incorparate experience of
the expert In the system e.g. predictions,
decisions etc.
48
Aplication domains

• Transpotation (cars, trains, traffic
  management...)
• Computing with words Internet information
• retrieval
• Fuzzy measures image processing, databases
• Control easy to design (if you have an expert)
• Felling sensors Keise problem description by
  fuzzy, etc

49
What is the basic feature of these technologies
to have them useful ???
Basic feature is
Universal aproximation theorem
Universal unknown function aproximators
50
Basic principles of evolutionary technology
51
What are the basic tools in evolutionary
computation ?

• Genetic algorithms optimalization tool
• Genetic programming system for data analysis
  with aim to provide analytical
  expresion
• Based on biological inspiration and Darwin theory
• of evolution

52
Basic tools in Evolutionary computation

• Chromozoms encoding the problem
• Fittness function Evaluation function
• Operator mutation , selection, cross operator
  ...
• Some chromozoms survive some are destroyed
• To find in heuristic way the - best values

53
Evolution evolutionary solutions

• Interactive Evolutionary approach
• So e.g. you envolve design of the event
• Make few iteration
• Stop human will influence the evolution
• Envolving towards

54
Evolutionary programming
GP
Analytical expression
Data
Function approximation abilities
55
Where to use Evolutionary

• Optimalization problems in general
• Planning and scheduling (TSP problem)
• GP for data-mining with aim of analytical
  expression
• broad range of engineering, business and other
  applications

1.7Ghz ???????
Problem time consuming process
56
Some more tools of intelligent technologies

• All tools related to Machine (Artificial
  Intelligence)
• NN, FS, EC
• Expert systems
• Logic programming tools
• Tools of chaos theory
• Tools of Artificial Life
• Tools of Multi-Agent technologies
• Etc .......

57
What is the trend in using Intelligent technogies
Computational Intelligence

Neural Networks
Evol. Computat.
Fuzzy systems
Hybrid technologies ECANSE the clever
approach to solve the problem using various tools
of IT.
Expert systenms ..
Planning , Schedulling
Classical Artificial Intelligence
58
When to use Intelligent technologies ?

• Answer is simple

Only if the application of IT will make a
product more advace and succesfull on the market
(money) Nobody cares what technology but new
technology must be better It is general belief
that Intell. Techology is able to do it
59
Conclusion
I believe that computational - Machine
Intelligence tools should be subject of
research
Intelligent System
Application !!!
60
What could be the future trends ???
Intelligent technologies
Computers 2 Ghz
Hardware implementation ????????????????????
61
ISTAG IST EU program advisory group

• Visionary report
• Ambient Intelligence
• The role of Machine Intelligence in the
  Information Society

(http//www.cordis.lu/ist/istag.htm) -
No MI-people Participated ? ? ?
62

Thank you for beeing with me !

• Peter Sincák