PowerPoint-Prentation - PowerPoint

Document Sample
PowerPoint-Prentation - PowerPoint Powered By Docstoc

 Irina Codreanu and Monica Gavrila
    Students at Bucharest University
Socrates Students at Hamburg University
   Context
   Knowledge
   Human brain
   Human brain vs. computer
   Can computers be considered intelligent?
     Positive examples
     Negative examples
       Expressing knowledge through language
   Several definitions

    – Discourse that surrounds a language unit and
      helps to determine its interpretation

    – The set of facts or circumstances that
      surround a situation or an event
     Some context related properties
    Contexts increase inferential power
    Learning (new information) occurs in specific
    Knowledge can be generalised from specific
     contexts to more general ones
    Contexts themselves can be objects of inference
    Different contexts can be selected depending on
     previous contexts
    Whether something acts as a context or not could
     itself be context dependent
 The act or state of knowing; clear
  perception of fact, truth or duty; cognition
 The psychological result of perception of
  learning and reasoning
 Knowledge is information that has been
  pared, shaped, interpreted, selected and
  transformed (Ray Kurzweil)
     Facts alone do not constitute knowledge
Human vs. Computer
   Human intelligence
    – Remarkable ability of creating links between
    – Weak at storing information on which
      knowledge is based

   The natural strengths of computers are
    roughly the opposite  powerful allies of the
    human intellect
Human Knowledge
   Abstract concepts
   When we come in contact with a new concept we add new
   Knowledge structures are not affected by the failure of the
    hardware (50000 neurons die each day in an adult brain,
    but our concepts and ideas do not necessary deteriorate)
   We are capable of storing apparently contradictory ideas
   Unless a new idea is reinforced it will eventually die out
   Strong links between our emotions and our knowledge
   Our knowledge is closely tied to our pattern-recognition
   We are able to change our minds  change our internal
    networks of knowledge
Computer Knowledge
   A section of the 15th edition of Encyclopaedia
    Britannica (1980)
   An ambitious attempt to organize all human
    knowledge in a single hierarchy
   Allows multiple classifications
   Takes time to understand but it is successful in view of
    the vast scope of the material it covers
    Such data structures provide a formal
    methodology for representing a broad class of
    knowledge  easily stored and manipulated by
    the computer
Human brain and knowledge
   Human brain

    Highly parallel early vision circuits
    Visual cortex neuron clusters
    Auditory cortex circuits
    The hippocampus
    The amygdala
Human Brain
   Human brain  on the order of 100 billion neurons
   One neuron  thousands of synaptic connections
   There is a speculation that certain long-term
    memories are chemically coded in neuron cell
   The capacity of each neuron  1000 bits  the
    brain has the capacity of 1014 bits
   If we assume an average redundancy factor of
    104, that gives us 1010 bits per concept  10 6
    concepts per human brain
Human Brain

   It has been estimated that a “master” of
    a particular domain of knowledge has
    mastered about 50000 concepts, which
    is about 5 percent of the total capacity,
    according to the above estimate
Human Brain vs. Computer

 The human brain uses a type of circuitry
  that is very slow
 For tasks as vision, language or motor
  control, the brain is more powerful than
  1000 super computers
 For certain tasks simple tasks such as
  multiplying digital numbers it is less
  powerful that the 4-bit microprocessor
  found in a ten dollar calculator
         Computer Learning vs.
          Biological Learning
   The brain is wired to learn in interaction with the world,
    re-programming themselves over time
   Computers don’t learn easy by experience
   A human child
    – Starts out listening to and understanding spoken
    – Learns to speak
    – Learns written language
   Computer
    –   Starts with the ability to generate written languge
    –   Learning to understand it
    –   Speak with synthetic voices
    –   Understand continuous human speech (recently)
Deep Blue
   Its predecessor Deep Thought appeared at
    Carnegie Mellon University. In 1989 it was
    beaten by Kasparov in 41 moves
   Project continued at IBM’s T.J. Watson
    Research centre
   Improvements every year: now it has 30
    Power Two Super Chip Processors
   Is capable of 200 million positions / second
    (Kasparov of 3 positions / second)
   Almost no use of psychology
Deep Blue
   Its strenghts are the strenghts of a machine: it
    has a database of opening games played by
    grandmasters over the last 100 years
   It does not think, it reacts
   Only one specific job
   It considers before deciding on a move 4
    parameters: material, position (control of the
    centre), King safety and tempo (losing tempo=
    wasting time by indecision, and the opponent
    making productive moves)
   Created in mid 1970’s by E.H. Shortliffe at
    Standford University
   Medical diagnosis tool (attempts to identify the
    cause of infection)
   Suggests a course of medication
   It uses 500 rules
   Each rule has assigned a number  its users
    can assess the validity of it’s conclusion
   Can recognise approximate 100 causes of
    bacterial infection
Uses rules like:
MYCIN Rule …
IF …
Fragment of a dialog between Mycin and a doctor

  >> What is the patient’s name?
  John Doe
 >>Male or female?
 >>Age?
 >>Let’s call the most recent positive culture C1
  From what site was C1 taken?
 >>My recommendation is as follows: give gentamycin using a
   dose of 119 mg…
Other intelligent programs
in medicine:
   PUFF: a system for interpreting pulmonary
   ONCOCIN: a system for the design of
    oncology chemotherapy protocols
   CADUCEUS (former Internist): a system for
    diagnosis within a broad domain of internal
    medicine; it contains over 100,000
    associations between symptoms (70% of the
    relevant knowledge in the field)
Other domains
 Teknowledge is creating a system for General
  Motors that will assist garage mechanics
 ISA (Intelligent Scheduling Assistant): schedules
  manufacturing and shop floor activity
 DENDRAL: embodied extensive knowledge of
  molecular structure analysis (Meta-DENDRAL)
 SCI (Strategic Computing Initiative): several
  prototypes, among which is Vision System (will
  provide real-time analysis of imaging data from
  intelligent weapons and reconnaissance
Expressing Knowledge
through Language
 Language is the principal means by which
  we share knowledge
 Language in both its auditory and written
  forms is hierarchical with multiple levels
 To respond intelligently to human speech,
  one need to know, among other things:
    –   The structure of the speech sounds
    –   The way speech is produced
    –   The patterns of sound
    –   The rules of word usage
Expressing Knowledge
through Language
   Computers sentence-parsing systems
    can do good jobs at analysing sentences
    that confuses humans:

“This is the cheese that the rat that the cat
          that the dog chased bit ate”
Expressing Knowledge
through Language
 Butwith other types of sentences it
 has difficulties:
          “Time flies like an arrow”
       “Squad Helps Dog Bite Victim”
 The difficulties appear when a word has
  several meanings or are used idiomatic
Expressing Knowledge
through Language
   Explanation to the first sentence:
    For the computer this sentence it might mean:
       The time passes as quickly as an arrow passes,
       Or maybe it is a command telling us to time flies
    the same way that an arrow flies - Time flies like an
    arrow would
       Or it could be a command telling us to time only
    those flies that are similar to arrows - Time flies that
    are like an arrow
       Or perhaps it means that the type of flies known
    as time flies have a fondness for arrows - Time flies
    like (that is cherish) an arrow.
Expressing Knowledge
through Language

   The ambiguity of language is far grater
    than may appear.

    At MIT Speech Lab, a researcher found
    a sentence published in a technical
    journal with over 1,000,000 syntactically
    correct interpretations!!!!!!!!
Expressing Knowledge
through Language
  one of the challenges in developing
  computerized translation system
 Each pair of languages represents a
  different translation problem
 Best solution known was given by a
  Dutch firm named DLT
Expressing Knowledge
through Language
   Solution found by DLT:
    – Developed translators for six languages to and
      from a standard root language (ESPERANTO)
    – A translation from English to German would be
      accomplished in 2 steps: from English to
      Esperanto and from Esperanto to German
    – Esperanto was selected because it is
      particularly good at representing concepts in an
      unambiguous way
    – Translating among 6 different languages would
      ordinarily require 30 different translators, but
      with the DLT approach only 12 are required
 Robot in Star Wars
 Designed to operate in deep space, interfacing
  with fighter craft and computer systems to
  augment the capabilities of ships and their pilots
 Monitors flight performance, well-versed in star
  ship repair, a.s.o.
 Converses in a dense electronic language
  (beeps, chirps, whistles)
 Can understand most forms of human speech,
  but must have his own communication
  interpreted by other computers