Useful%20Techniques%20in%20Artificial%20Intelligence%20-%20Introduction

1
Useful Techniques in Artificial
Intelligence-Introduction
Cranfield University, 16th November 2005
PRESENTED BY Dr WILL BROWNE
Cybernetics, University of Reading Whiteknights Re
ading UK
2
(No Transcript)
3
Picture of Lt Commander Data
4
This 1100 spin Bosch machine is incredibly quiet
and positively high-end. It haseverything you
would expect to find on a Bosch including
exclusive features likethe 3D AquaSpa wash
system with Fuzzy Control.
5
Stanley 2 million Prize awarded to Stanford
Racing TeamFive teams completed the Grand
Challenge four of them under the 10 hour limit.
The Stanford Racing Team took the prize with a
winning time of 6 hours, 53 minutes. The SRT
software system employs a number of advanced
techniques from the field of artificial
intelligence, such as probabilistic graphical
models and machine learning.
http//en.wikipedia.org/wiki/Darpa_grand_challenge

http//www.darpa.mil/grandchallenge/index.asp http
//www.darpa.mil/grandchallenge/gallery.asp
6
Aim

• To introduce the field of artificial
  intelligence,
• so that it is possible to
• Determine if an artificial intelligence technique
  is useful for a problem
• and be able to
• Select an appropriate technique for further
  investigation.

7
Objective

• Introduction to Artificial Intelligence
• Generic function of Artificial Intelligence
  tools
• Review of major techniques
• Benefit and pitfalls of applying these tools.

8
Contents

• Applications of Techniques
• Description of Artificial Intelligence Field
• Function of Important Techniques
• Benefit and Pitfalls of Applying Techniques
• Summary

9
Finance Business

• Predict stock market trends
• Insurance/credit risk assessment
• Fraud detection

10
Industry

• Communication mobile phone ground station
  satellite networks
• Scheduling of work, transport, crane operations
  and so on
• Routing of computer networks.

INTELSAT operates a fleet of 19 satellites
11
Engineering

• Optimisation of route planning
• Design of complex structures
• Process optimisation

12
Control

• Domestic appliances, such as Microwave ovens
• Traffic flows
• Aircraft flight manoeuvres

13
Academia

• Game playing, e.g., chess
• Robotic football
• Test problems, e.g., iterated prisoners dilemma.

14
Definition of AI

• Artificial -
• easily understood
• Artificial Intelligence -
• whole concept can be discussed
• Intelligence -
• easy to recognise
• hard to define

15
Artificial

• Not Human, plant or animal
• Computer-based
• (workstation, PC, parallel-computer or Mac)
• Computer programs

16
Artificial Intelligence

• Enable computers to perceive, reason and act.
• Do jobs that currently humans do better.
• Artificial Intelligence is what Artificial
  Intelligence researchers study.

17
Intelligence

• Intelligence is the ability to store, retrieve
  and act on data - efficiently and effectively.
• Intelligence has insight and can go beyond
  problem definition - but not experience?
• True intelligence does not exist!
• How do you speak Alien?

18
Programme Languages

• Assembler
• C, C, Java and FORTRAN
• Lisp, Small Talk and PROLOG
• Shells, e.g., G2 Expert System
• Toolboxes, e.g., Neural Networks in Matlab.

19
Function

• NOT RELIANT UPON MATHEMATICAL DESCRIPTION OF
  DOMAIN.
• (stochastic)
• May include mathematics within technique
• May be similar to mathematical techniques

20
Functionality

• Search Optimisation
• Modelling
• Knowledge-handling
• Routing Scheduling
• Visualisation Design Querying Learning
• Game-playing Adaptive-Control
• Rule-Induction
• Data-Access Data-Manipulation
• Prediction Diagnosis

21
Function Summary

• EXPLORE v EXPLOIT
• EFFICIENTLY AND EFFECTIVELY

22
Functional Division of AI

• Modelling -- Explore
• Knowledge-Based -- Exploit
• Optimisation -- Explore then
• Exploit
• Advanced -- Explore
• Exploit

23
Theoretical Division of AI
ARTIFICIAL INTELLIGENCE TECHNIQUES
KNOWLEDGE BASED
ENUMERATIVES
GUIDED
NON-GUIDED
Expert
Decision
Case Based
Backtracking
Branch
Dynamic
Systems
Support
Reasoning
Bound
Programming
INTELLIGENT AGENTS
(inc. Artificial Life)
FUZZY LOGIC
LEARNING
IMMUNE
CELLULAR
ANT
SYSTEMS
AUTOMATA
COLONY
GUIDED
HILL CLIMBING
Tabu
REINFORCEMENT LEARNING
Simulated
Search
NON-GUIDED
Annealing
Las Vegas
STATE-BASED
GENETIC EVOLUTIONARY COMPUTATION
NEURAL NETWORKS
Hopfiled
Kohonen
Multilayer
Maps
Perceptrons
GENETIC ALGORITHMS
GENETIC
EVOLUTION STRATEGIES
PROGRAMMING
PROGRAMMING
LEARNING CLASSIFIER SYSTEMS
24
Knowledge-Based Expert Systems

• What Capture and reason about knowledge
  (especially human) in a transparent form.
• How Store of rules and information (the
  knowledge base)
• Reason about information (inference engine).
• Where Rolling Mill Expert System project.
• Satellite control/maintenance.

IF Temp lt 400 oC THEN Rolling is Poor
25
Knowledge-Based Case Based Reasoning (CBR)

• What Past examples (cases) used to reason about
  novel examples.
• How Store of cases and information Reason and
  interpolate information Update, maintain and
  repair cases.
• Where Decision support type systems.
• Initial bridge design selection.

Temp 400 oC Rolling Poor
Temp 450 oC Rolling Good
Temp 430 oC Rolling ?
26
Enumerative Branch Bound

• What Knowledge stored in decision trees. E.g.,
  ID3 and C4.5
• How Domain is classified into sections
• Tree of decisions is formed.
• Where Insurance fraud detection
• Credit assessment.

Age gt 25 T F Sex F T F T F 250 300 300 4
25
27
Fuzzy Logic

• What Grey or fuzzy (i.e. human) thinking in
  computers.
• How Member sets formed to classify inputs
• Overlap of sets allows imprecise logic.
• Where Domestic appliance intelligence, e.g.,
  washing machines microwaves.

Distribution in department
F M
5.2 5.6 5.10 6.2 Height
28
Fuzzy Logic

• What Grey or fuzzy (i.e. human) thinking in
  computers.
• How Member sets formed to classify inputs
• Overlap of sets allows imprecise logic.
• Where Domestic appliance intelligence, e.g.,
  washing machines microwaves.

Detergent Water ratio
Silk Wool
2 4 6 8 Weight
29
LearningGuided Search

• What Optimisation techniques that avoid being
  trapped in local optima.
• How Simulated Annealing
• Probability of accepting new search point
• Probability reduced near to optimum.
• How Tabu Search
• Can not search previously visited point
• Therefor will not become stuck.
• Where Optimisation problems, where domain is
  described by a function.
• http//www.exatech.com/Optimization/optimization.h
  tm

30
Learning Genetic Evolutionary Computation

• What Uses evolution to optimise fitness
  (function) of solution.
• How
• 1. Population of solutions created
• 2. Fitness of each solution evaluated
• 3. Best solutions mated for new
• population
• 4. Repeated until optimum solution.
• Where Design optimisation
• Stock market investment
• Autonomous programme development

31
Learning Genetic Evolutionary Computation

• Genetic Algorithms
• Optimise numeric solution of fitness function.
• Learning Classifier Systems
• Optimise the co-operation of rules for solving
  and input/output thickness function.
• Genetic Programming
• Optimise the interaction of code to solve a
  programming function.
• Evolutionary Systems
• Optimise the solution based on a behavioural
  (phenotypic) instead of genetic (genotypic) level.

32
F(x) cos(x) sin(x2) 1 lt xlt 3
GA j1 00010001 j2 01110001 j3
10010101 GP j1 sin(x) 2sin(x2) j2
sin(x) 2sin(x)cos(x) j3 sin(x) -
2sin(x)cos(x)
33
Intelligent-AgentsCellular Automata

• What Autonomous individuals (cells) reacting to
  state of neighbouring individuals - governed by
  rules.
• How Grid of individuals initiated
• Behaviour rules introduced
• (e.g., if gt 3 neighbours on, then on)
• Iteration until stable pattern emerges.
• Where Cast and mould design
• Screensavers!

34
Intelligent-AgentsAnt Colony

• What Complex domains explored autonomously to
  determine efficient and effective paths.
• How Domain and goal created
• Artificial ants created to explore and create
  trails around a domain.
• Ants attempt to create the optimum trail by
  following chemical trails.
• Where Routing problems, such as the travelling
  salesman problem.

35
Neural Networks Back-Propagation

• What Mimic the function of the human brain
  within a computer.
• How Nodes (representing neurons) are linked to
  other nodes via connections (representing
  synapses)
• Nodes send messages to their output (firing)
  when a threshold from their inputs has been
  reached.
• Where Modelling of industrial systems
• Speech recognition programs.

36
Neural Networks Self-Organising-Maps

• What Mimic the function of the human brain
  within a computer. To determine input relations
  (instead of input-output relationships).
• How Nodes are linked to other nodes via
  connections
• Network of nodes autonomously adjusts to
  represent input patterns.
• Where Fault diagnosis of industrial systems
• Growing patterns in crops

37
Technique Selection

• Overall Strategy - Explore (search) or
• Exploit (optimise)
• Representation - Required
• transparency
• Learning - Domain / fitness
• function known?
• Supervision - Feedback from
• domain available?

38
No Free Lunch Theorem

• ...all algorithms that search for an extreme of
  a cost function perform exactly the same,
  according to any performance measures, when
  averaged over all possible cost functions.
• Wolpert and Macready 96

39
No Free Lunch Theorem

• Reasons why theorem does not hold in practical
  situations
• Inclusion of domain knowledge
• Co-adaptation algorithms
• Domain specific algorithms
• Non-infinite populations
• Resampling is important
• Representation style is important in specific
  domains
• Wilson 97

40
Interpolate Extrapolate

• Aliasing
• Incomplete picture

x
x
x
x
x
x
x
x
x
x
x
41
Garbage In Garbage Out

• Often blind acceptance of inputs
• Often blind generation of outputs
• Practical need to
• Verify
• Validate
• Test

42
(No Transcript)
43
Lack of Transparency

• Black Box techniques, such as Neural Networks
• Semi-transparent techniques, such as Branch
  Bound, become difficult for human interpretation
  with large problems
• Transparent techniques, such as Expert Systems,
  become difficult for human interpretation with
  very large problems - above 1000 rules, the logic
  chain becomes huge.

44
Benefits

• Not reliant upon the mathematical description of
  the domain
• Speed, efficient solution production
• New/novel answers, effective solutions produced
• Direct areas of further research (human or
  conventional techniques)
• Hybridisation of techniques is possible
• Cost, wide range of options available

45
Conclusion

• Useful tools to complement existing techniques
• Multiple uses from exploring to exploiting the
  domains of problems
• Beneficial in efficiently and effectively
  obtaining solutions to problems

46
GUIDE TO EXPERT SYSTEM PROJECT

• Project Partners
• University of Leicester
• Will Browne - Knowledge Gathering
• Yi Cao - Model Development
• Turhan Ozen - Soaking Pit Optimisation
• British Aluminium Plate
• VAI Technology
• Aim
• Improve HMAS in knowledge handling for
• Shape Optimisation
• Soaking Pit Optimisation
• Product Plant Fault Diagnosis
• Scope
• Active project
• Knowledge Gathering over next 3 months
• Involves talking/listening to plant personnel.

47
GUIDE TO EXPERT SYSTEM PROJECT

• Expert Systems
• Multiple benefits, e.g., available expertise
• Reason about stored knowledge
• Built using knowledge gathering
• Knowledge Gathering
• Involves operators, managers engineers
• Two-way flexible process
• Requirements
• Designed to be straightforward
• Individual or group discussions
• (lasting 20 - 40 minutes)
• Fitted into shift activities.