BCS 3053 ARTIFICIAL INTELLIGENT

1
BCS 3053ARTIFICIAL INTELLIGENT

Chapter 1
2
Outline

• Overview of Artificial Intelligence
• What is Artificial Intelligence?
• Artificial Intelligence in Industry
• Example of an AI Application

3
Introduction to Artificial Intelligence
4
What is Intelligence?
5
(No Transcript)
6
Aspects of Intelligence
From B. Koskos book
We never step twice into the same
river Heraclitus (1,500 BC)
We live in a world of marvelous complexity and
variety, a world where events never repeat
exactly. But even though events are never exactly
the same, they are also not completely different.
There is a thread of continuity, similarity, and
predictability that allows us to generalize,
often correctly, from past experience to future
events.
James Anderson (1990)
7
According to the Oxford and Penguin English
Dictionaries the word intelligence can be
defined as follows

• ability to understand
• reason
• perceive
• quickness in learning
• mental alertness
• ability to grasp relationships
• clever
• information
• news

8
One way to understand intelligence is by
looking at our own capabilities, which means that
humans are able to

• think
• understand
• recognize
• perceive
• generalize
• adapt
• learn
• make decisions
• solve daily problems

9
Examples and Aspects Biological Intelligence

• Self-repair
• Self-guidance
• Reproduction
• Making decisions
• Reasoning capability
• Predicting/forecasting
• Understanding noisy or fuzzy information

• Capability to Learn
• Capability to Generalize/Classify
• Capability to Survive
• Gathering of Information
• Recognizing Patterns
• Common Sense
• Logical Thinking

10
Humans have self-repair mechanisms in their bodies
11
Outline

• Overview of Artificial Intelligence
• What is Artificial Intelligence?
• Artificial Intelligence in Industry
• Example of an AI Application

12
Definition of AI

• Turban Aronson (2001)- concerned with two basic
  ideas, firstly involves studying the thought
  process of humans and second, it deals with
  representing these processes via machines.
• Luger (1999)- branch of CS that is concerned with
  the automation of intelligent behaviour

13
Definition of AI (cont..)

• Norvig and Russel (1995)defines in 4 ways
• System that think like human
• "The automation of activities that we associate
  with human thinking, activities such as
  decision-making, problem solving, learning..."
  (Bellman, 1978)
• System that act like human
• "The study of the computations that make it
  possible to perceive, reason, and act" (Winston,
  1992)
• System that think rationally
• " The art of creating machines that perform
  functions that require intelligence when
  performed by people" (Kurzweil, 1990
• System that act rationally
• "The branch of computer science that is concerned
  with the automation of intelligent behavior"
  (Luger and Stubblefield, 1993)

14
Artificial Intelligence (AI) ?

• AI is a study about inventing
  machines/computers that capable of mimicking
  human/animal intelligent behavior.
• The ultimate objective is to develop a system
  that can think and act rationally like humans.

15
AI Tree (Turban Aronson, 2001)
16
(No Transcript)
17
What is Artificial Intelligence?

• AI is a tool that has been developed to imitate
  human intelligence and decision-making functions,
  providing basic reasoning and other human
  characteristics.

18
Meaning of intelligent behaviour

• Learning or understanding from experiences
• Making sense out of ambiguous or contradictory
  messages
• Responding quickly and succesfully to a new
  situation (different responses-gtflexibility)
• Using reasoning in solving problems and directing
  conduct effectively
• Dealing with perplexing situations
• Understanding and inferring in ordinary rational
  ways
• Applying knowledge to manapulate the environment
• Thinking and reasoning
• Recognizing the relative importance of different
  elements in a situation.

19
An Intelligent pH sensor
20
What the Intelligent Microprocessor-based pH
Transmitter can do?

• It can tell the user if its glass electrode is
  damaged or clogged
• It can determine if a sensor cable is
  disconnected
• It can determine if the liquid level is too low

21
Is there really an Intelligent Machine/System?

• From this point of view it appears that an
  intelligent system (or device) contains a
  collection of simple features that jointly make
  the system easy to use

22
Can machines be developed to have intelligence?

• Perhaps one way to do this is to develop
  algorithms based on human or animal intelligence

23
COMPUTER ARCHITECTURES
Copying from Biological Systems

• The Motherboard from single layer to multilayer

24
Copying from Biological Systems
25
Copying from Biological Systems
In a study by T. Yoshikawa (Kyoto University),
the design of the optimal length of robotic
manipulators should follow that of the human arm
26
Copying from Biological Systems
From Thumb Print ? Bar Code
27
Examples and Aspects Biological Intelligence

• Self-repair
• Self-guidance
• Reproduction
• Making decisions
• Reasoning capability
• Predicting/forecasting
• Understanding noisy or fuzzy information

• Capability to Learn
• Capability to Generalize/Classify
• Capability to Survive
• Gathering of Information
• Recognizing Patterns
• Common Sense
• Logical Thinking

28
AI Concepts / Topics(from J. McCarthy, Stanford
University)

• Logical AI
• Search
• Pattern recognition
• Representation
• Inference
• Common sense knowledge and Engineering
• Learning from experience
• Planning
• Epistemology a study of the kinds of knowledge
  that are required for solving problems in the
  world
• Ontology - study of the kinds of things that
  exist
• Heuristics
• Genetic Programming

29
What is the implication of adding intelligence
in machines?

• If artificial systems can be made more robust,
  costly redesigns can be reduced or eliminated
• If higher level of adaptation can be achieved,
  existing systems can perform their functions
  longer and better
• If machines can be made to be self-organized then
  less operations are needed by humans

30
Intelligence that can be designed

• Self learning machines
• Autonomous / Self-organizing systems
• Self-optimization
• Path planning
• Pattern recognition
• Decision making
• Prediction
• .

31
How do we design Intelligence?

• Study from biological models (brain, genetic,
  DNA, life, Molecular biology, .) ? neural nets,
  GA, Artificial Life, DNA Computing, Quantum
  Computing, Robotics, etc.
• Study from human phenomena (common sense,
  reasoning, predicting, observing, inference, ) ?
  fuzzy logic, expert systems, search techniques,
  etc.
• Need to develop mathematical/logical algorithms
  based on the above biological models or phenomena

32

• Mathematics
• Control Theory
• Computer Science
• Physics
• Operational Research

• Neuroscience
• Psychology
• Philosophy
• Biological Science
• Physiology

Artificial Intelligence
Symbolic AI
New AI
Micro. Bio. Models

• KBS
• Symbolic M. L.
• Logic Prog.
• Nat. Lang. Proc.
• Search techniques

• Fuzzy
• Rough Sets
• Chaos
• ..

• ANN
• GA
• A. Life
• ..

33
Some Examples of Available Artificial
Intelligence Techniques

• Expert Systems
• Fuzzy Logic
• Neural Networks
• Genetic Algorithms
• Chaos Theory
• Rough Sets
• Artificial Life, etc.
• DNA Computing

Many AI techniques have been developed based on
biological systems/behavior
34
The AI Field

• Expert System
• Natural language processing
• Speech (voice) understanding
• Robotic Sensor system
• Computer vision and scene recognation
• Intelligent computer aided instruction
• Neural computing
• Language translation
• Fuzzy logic
• Genetic algorithms
• Intelligent agent

35
AI Application Area

• Game playing
• Automated reasoning Theorem Proving
• Expert System
• Natural language understanding semantic
  modelling
• Modelling human performance
• Planning robotic
• Language Environment for AI
• Machine Learning
• Parallel Distribution Processing (PDP) Emergent
  Computation

36
http//www.aiexplained.com/history/history.html
37
Future of AI

• Artificial intelligence is always on the
  futurist's list of hopefuls but often seems to be
  the most unachievable. Here are some of the
  predictions for the future decade "The popular
  conception of AI as seen with HAL in 2001,
  Commander Data in Star Trek, and David in the
  film AI, is not far away." This may sound
  outlandish, however, who would have thought by
  2001, we would have four computers in our kitchen
  (this includes the computer chips in our coffee
  makers, refrigerators, stoves and radios). "By
  2006, it will be quite possible to ask a robot
  general questions which it hasn't been told
  beforehand and get a response. By 2010, the first
  robot will have passed its GCSE exams. Such a
  robot would be ready to take its A-Levels a few
  years later and a degree a few years after that."
  
• This is predicted by BT futurologist, Ian
  Pearson.

38
Others predictions..

• Speed freaks will need to be careful with the
  possible introduction of intelligent "cats' eyes"
  with integrated speed cameras.
  
• A food tester that can identify the presence of
  bugs could prove useful in the kitchen.
  
• The desktop looks set for a make-over with
  air typing and an air mouse.

39
AI Field An Overview

• Expert System
• Fuzzy Logic
• Neural Network
• Genetic Algorithm

40
What is an Expert System (ES)?

• Expert System (ES) is a branch of Artificial
  Intelligence that attempt to mimic human experts.
  
• Expert systems can either support decision makers
  or completely replace them.
• Expert systems are the most widely applied
  commercially successful AI technology.

41
What is an ES?

• Prof. Edward Feigenbaum of Stanford University,
  leading researchers in ES has produced the
  following definition
• " . . . An intelligent computer program that uses
  knowledge and inference procedures to solve
  problems that are difficult enough to require
  significant human expertise for their solution."

42
Fuzzy logic has been developed from the human
reasoning process

• Dragon Fly
• 6 legs
• wings
• Body with 3 parts
• Insect

Knowledge Base
Infer

Sensor
Dragon fly!
43
Biological Network
Artificial Neural Network
An artificial neural network is a universal
function approximator. Weights Wij are learned
to fit any function.
1 n
x1
a1
O1
x2
O2
a2

ak
Om
xj
1 ji
n kj
W
W

44
Genetic Algorithms have been derived from the
human reproduction process
GA Operators
Population
Reproduction
Crossover
Mutation
Generation proceed
Generation
Chromosomes
(Carrier of Hereditary Information)
Genes
1
2
3
2
3
4
1
4
1
45
DNA Computing ltWatson-Crick Complementaritygt
The DNA Ladder
46
Artificial Life

• A-Life focuses not so much on human biology but
  on biology in its widest sense. It has already
  given birth to such strange things as robots that
  work in teams, machines that evolve and virtual
  creatures that learn, age, breed and die.
• Today, biologists study evolution in virtual
  worlds, computers are protected from malicious
  viruses by artificial immune systems, and in
  Oxford, a heart made from millions of software
  cells is teaching doctors things about medicine
  that no living heart could have done. Prepare to
  have your mind boggled...

47
Outline

• Overview of Artificial Intelligence
• What is Artificial Intelligence?
• Artificial Intelligence in Industry
• Example of an AI Application

48
World Industrial Leaders by Country(1975-2000)(MI
S for the Info Age)
In 1994 alone Japan sold US34 billion worth of
consumer products using fuzzy logic technology
49
3 General Types of Industries

• Companies engaged in manufacturing
• Automotive Parts Industrial Equipment
• High-tech Industry Heavy Equipment
• Planes and others

50
Why Industries need AI/new technology?

• Improved performance
• Reduced operations by humans
• Better reliability
• Cost reduction
• Easier maintenance
• Simpler to design
• Able to design complex tasks

51
Made in Japan(based on a video on innovations
and the need for change)

• 1980s
• Excellent Quality
• Expensive
• Leadership
• Balance of Payments
• High Technology
• Innovations

• 1960s
• Junk
• Cheap
• Poor Quality
• Copies
• Low Technology
• Imitation

52
Is there really a need for AI?

• Manufacturers need to improve on their products
• Need to satisfy customers
• Need to improve products reliability
• Need to improve products performance
• Need to improve products features
• Need to distinguish their products away from
  their competitors

53
AI Applications
(IT) Decision Support Systems
Consumer Products
AI
Industrial Products
Medical Applications
54
Intelligent Systems Design
CS
EE
Execution
TASKS
Algorithms, computations
Intelligent machine
55
Example of Products with AI
Genie Fuzzy Logic Jar Cookers
56
It also has a Neuro-Fuzzy Logic System- a smart
system that knowsyour lifestyle and learns your
pattern of use(like what time the doors are most
frequently opened or closed) and controls the
refrigerator accordingly either through quick
cooling, low cool or defrosting.
57
This Refrigerator has a Neuro-Fuzzy Control
System(For Door Cooling and Super-Cooling and
Freezing)
58
(No Transcript)
59
(No Transcript)
60
9 point AiAF Artificial Intelligence Autofocus
61
Why the need to develop Intelligent Systems and
Why Now?

• More challenging problems
• More complex systems
• More powerful computers/hardware
• Better/powerful algorithms
• Better software tools
• Human desire

62
Plants are becoming more complex, Thus, new
techniques are needed for better and tighter
control.
63
Advantages of Adding Intelligence in Products/
Systems

• Better performance
• Longer Life
• Reliability
• Simpler operation
• Cost effective
• Higher efficiency
• Self-organizing / self-optimization
• Simpler design

64
How would you design an intelligent traffic
lights system? Features/Advantages - Technology
65
Where AI can/should be applied?

• Data is overwhelming/abundance
• Too many manual operations/procedures
• Optimization is possible
• Parallel/Distributed procedures/architectures are
  needed
• Decision making is required
• When current techniques are too complicated to be
  used/designed

66
Where AI can/should be applied? .. Contd

• Mathematical models are too complex/impossible
• To increase efficiency
• To reduce cost
• To improve performance and reliability

67
Where AI should not be applied?

• Lack of Data
• Simpler techniques are available / sufficient
• Further optimization is not possible

68
How AI can be applied?
69
Some Pre-requisites in understanding AI

• Some mathematical background
• HLL Programming
• Discrete-time systems
• Some aspects of biological systems as well as
  philosophy and psychology
• ..

70
Some Important Facts, you need to know.

• AI is not the only solution
• AI is only one part of technology
• AI is just a tool for improvement
• You must know your domain/target application

71
To gain Competitive Advantage in our Products

• Technology Driven
• International Market
• Develop Home-grown Expertise
• Design Own Products
• Integrate Local Design with Foreign Components
• Use Advanced Technology Tools
• Enhance RD Capabilities
• Innovate and Progress

72
The Future Humanoids
73
30-year robot project pitchedResearchers see
tech windfalls in costly humanoid quest

• Japanese researchers in robot technology are
  advocating a grand project, under which the
  government would spend 50 billion yen (USD400
  million) a year over three decades to develop a
  humanoid robot with the mental, physical and
  emotional capacity of a 5-year-old human. The
  researchers believe the Atom Project, inspired by
  the popular robot animation series "Tetsuwan
  Atom" by the late cartoonist Osamu Tezuka, would
  help promote scientific and technological
  advances in Japan, just like the U.S. Apollo
  Project, which not only succeeded in landing men
  on the moon but contributed to a broad range of
  technological breakthroughs. Unlike cartoonist
  Tezuka's "Atom" character, known as "Astro Boy"
  overseas, based on an image of a 9-year-old boy,
  the Atom Project aims to create a humanoid robot
  with the physical, intellectual and emotional
  capacity of a 5-year-old that would be able to
  think and move on its own, the researchers say.
  As exemplified by the Asimo robot developed by
  Honda Motor Co., Japan's technology in this field
  has reached a level where its robots can be
  programmed to approximate the way humans walk.
  However, their physical ability is still no match
  for a 5-year-old human.

74
Outline

• Overview of Artificial Intelligence
• What is Artificial Intelligence?
• Artificial Intelligence in Industry
• Example of an AI Application

75
(No Transcript)
76
Hondas Humanoid Robots
77
The P2 Humanoid
78
P3 Humanoid
79
Introducing a New ASIMO Featuring Intelligence
Technology

• Tokyo, December 5, 2002 --- Honda Motor Co., Ltd.
  has released a new model of its intelligent
  humanoid robot ASIMO which is capable of
  interpreting the postures and gestures of humans
  and moving independently in response. ASIMO's
  ability to interact with humans has advanced
  significantly --- it can greet approaching
  people, follow them, move in the direction they
  indicate, and even recognize their faces and
  address them by name. Further, utilizing networks
  such as the Internet, ASIMO can provide
  information while executing tasks such as
  reception duties. ASIMO is the world's first
  humanoid robot to exhibit such a broad range of
  intelligent capabilities. Starting from January
  of next year, Honda plans to commence rental of
  this new version of ASIMO to public institutions
  and companies.

80
ASIMOAdvanced Step in Innovative MObility
Camera Eyes AI
Antenna
Battery (Fuel Cell)
Gyro Sensor Measuring Body Angle
Actuators and Other Peripheral Systems
Controlling leg movements AI
Load Sensors In Leg
Intelligent Real-time Flexible Walking AI
81
The New ASIMO
The key features of the new ASIMO
includeAdvanced communication ability thanks to
pattern recognition technology 1. Recognition of
moving objects    4. Sound recognition 2. Posture
/gesture recognition    5. Face recognition
3. Environment recognition      
82
Mitsubishis- Annanova
83
Sonys AIBO
84
Fujitsus HOAP (Miniature Human Robot)
PINO ROBOTS
85
Sonys SDR (Sony Dream Robots)

• SDR-4X II
• Introducing 4 new technologies
• Small robot actuators (ISA-4)
• Real-time Integrated Adaptive Motion Control
• Motion creation software
• Real-time Real World Space perception
• Multi-modal Human-Robot Perception

86
SDR - specifications
87
Intelligent Servo Actuators (ISA-4)
88
Other Features

• Multi-face Detection

• Emotional Expression

89
Some Postures of SDR
90
Future Research in Humanoids

• HUMAN
• Slow
• Intelligent
• Easily tired
• Imaginative/Creative
• Emotional
• Etc.

• ROBOT
• Speed (Fast)
• Not tired-Can do repetitive job (Fuel Cell)
• Not imaginative/Not creative
• Better speech and pattern recognition
• Some emotion
• Entertainment
• Personal Friend

91
Issues in AI

• Party At Fault - The AI Machine
• Are Robots More Intelligent
  Than Humans?
• Can Robots Replace Humans?
• Human vs Machine

92
Class Discussion 1

• Choose one of the applications and explain it
  from the following point
• What concept of AI that applied
• How they applied it
• The benefit of applied AI to that application
• Compare the performance of application - before
  and after using AI