animated version

Document Sample
animated version Powered By Docstoc
					                     Course Overview
 What is AI?
                                                     Part I:
 What are the Major Challenges?             Introduce you to
                                            what’s happening in
 What are the Main Techniques?             Artificial Intelligence

 Where are we failing, and why?                       Done

 Step back and look at the Science
                                                         Part II:
 Step back and look at the History of AI             Give you an
                                                    appreciation for
 What are the Major Schools of Thought?             the big picture

 What of the Future?                                Why it is a
                                                   grand challenge
                     Course Overview
 What is AI?
                                                     Part I:
 What are the Major Challenges?             Introduce you to
                                            what’s happening in
 What are the Main Techniques?             Artificial Intelligence

 Where are we failing, and why?                       Done

Step back and look at the Science
                                                         Part II:
 Step back and look at the History of AI             Give you an
                                                    appreciation for
 What are the Major Schools of Thought?             the big picture
                                                     Why it is a
 What of the Future?
                                                   grand challenge
      Clarifying what Functionalism is…
              Sensory                Central            Motor
                                     systems           systems
              systems
          Sight           Categorisation              Voice
          Hearing         Attention                   Limbs
          Taste            Memory                     Fingers
          Smell            Knowledge representation   Head       Motor
sensory
 input    Touch           Numerical cognition         …          output

          Balance         Thinking
          Heat/cold       Learning
          …               Language




                           Physical
                        Implementation
      Clarifying what Functionalism is…
              Sensory             Central                Motor
                                  systems               systems
              systems
          Sight           Categorisation               Voice
          Hearing         Attention                    Limbs
          Taste            Memory                        Fingers
                                                  Functionalism says
          Smell            Knowledge representation      Head
sensory                                             we can study theMotor
                                                                     output
 input    Touch           Numerical cognition            …
                                                       information
          Balance         Thinking
                                                    processing tasks
          Heat/cold       Learning
                                                  (and algorithms for
          …               Language
                                                       doing them)
                                                  independently from
                                                    the physical level


                           Physical
                        Implementation
      Clarifying what Functionalism is…
      This means they are
      “multiply realisable”      Central                Motor
            Sensory
                                 systems               systems
            systems
          to
   = ableSightbe manifested in
                       Categorisation                Voice
       various systems,
         Hearing       Attention                     Limbs
   even perhaps computers,
         Taste          Memory                         Fingers
                                                Functionalism says
           Smell         Knowledge representation      Head
sensory                                           we can study theMotor
 input so long as the system
           Touch        Numerical cognition            …           output
    performs the appropriate                         information
           Balance      Thinking
              functions Learning                  processing tasks
           Heat/cold
                                                (and algorithms for
           …             Language
       (Wikipedia definition)                        doing them)
                                                independently from
                                                  the physical level


                         Physical
                      Implementation
      Clarifying what Functionalism is…
              Sensory                  Central                   Motor
                                       systems                  systems
              systems
          Sight               What about Brooks?
                               Categorisation                  Voice
                            (remember tutorial article)
                               Attention
          Hearing                                              Limbs
          Taste                 Memory                         Fingers
                               Is he a functionalist?
          Smell                 Knowledge representation       Head       Motor
sensory
 input    Touch            Numerical wouldn’t
                  Yes! Otherwise hecognition be trying to …               output

          Balance    use computers to implement the
                           Thinking
                         processing in his robots.
                           Learning
          Heat/cold
          …                     Language
                         He would instead be trying to use
                                some organic system,
                        as a non-functionalist would believe
                        that the processing happening in an
                           animals’ neurons could not be
                              performed by a computer
                              Physical
                           Implementation
      Clarifying what Functionalism is…
              Sensory
                                                              Motor
                        So what was it Central was saying about
                                       Brooks
                                                             systems
              systems             the systems
                                       “real world”?
          Sight               Categorisation               Voice
          Hearing             Attention                    Limbs
          Taste                Memory                      Fingers
          Smell                Knowledge representation    Head        Motor
sensory
 input    Touch               Numerical cognition          …           output

          Balance             Thinking
          Heat/cold           Learning
          …                    Language




                             Physical
                          Implementation
      Clarifying what Functionalism is…
              Sensory
                                                              Motor
                        So what was it Central was saying about
                                       Brooks
                                      systems                systems
              systems              the real world?
          Sight               Categorisation               Voice
          Hearing             Attention                    Limbs
          Taste                Memory                      Fingers
          Smell              He said this side needs
                               Knowledge representation    Head        Motor
sensory
 input    Touch              to be connected to the
                              Numerical cognition          …           output

          Balance                 real
                              Thinking world, not a
          Heat/cold           Learningsimulation
          …                    Language
                               e.g. digital camera
                              getting data from real
                              world, with noise, and
                                 messy lighting
                               Physical etc.
                                 conditions,
                          Implementation
      Clarifying what Functionalism is…
              Sensory
                                                              Motor
                        So what was it Central was saying about
                                       Brooks
                                      systems                systems
              systems              the real world?
          Sight               Categorisation               Voice
          Hearing             Attention                    Limbs
          Taste                Memory                      Fingers
          Smell              He said this side needs
                               Knowledge representation    Head        Motor
sensory
 input    Touch              to be connected to the
                              Numerical cognition          …           output

          Balance                 real
                              Thinking world, not a
          Heat/cold           Learningsimulation
          …                    Language
                            e.g. wheels on the robot,
                             which might slip on the
                             ground or stick on the
                                   carpet, etc.
                                Physical
                                   i.e. messy
                          Implementation
      Clarifying what Functionalism is…
            Sensory
                                                            Motor
                      So what was it Central was saying about
                                     Brooks
                                    systems                systems
            systems              the real world?
          Sight             Categorisation               Voice
          Hearing           Attention                    Limbs

       He didn’t say he Memory
           Taste                                         Fingers

sensoryhad Smell problem Knowledge representation
            any                                          Head        Motor
 input     Touch the    Numerical cognition              …           output
            with
       algorithms being Thinking
           Balance

      implemented on aLearning
           Heat/cold
           …
          computer       Language




                           Physical
                        Implementation
      Clarifying what Functionalism is…
               Sensory              Central            Motor
                                    systems           systems
               systems
           Sight         Categorisation              Voice
           Hearing       Attention                   Limbs
           Taste          Memory                     Fingers
           Smell          Knowledge representation   Head       Motor
sensory
 input     Touch         Numerical cognition         …          output

           Balance       Thinking
           Heat/cold     Learning
           …             Language




          Continuing question from last lecture:
           How does this central system work?
              Physical Symbol System
     The Physical Symbol System
 Some sort of Physical Symbol System seems to be
  needed to explain human abilities
    Humans are “programmable”
    We can take on new information and instructions
    We can learn to follow new procedures
       e.g. a new mathematical procedure
    Human mind is very flexible
    …But not true of other animals, even apes
 Animals have special solutions for specific tasks
    Frog prey location
 Human flexible Physical Symbol System must have
  evolved from animals’ processing systems
    Details of physical implementation are unknown
 Let’s stick with Physical Symbol System for now…
    See can we flesh out more details
           The Language of Thought
 What is the language we “think in”?
 Is it our natural language, e.g. English, or mentalese?
 Some introspective arguments against natural language
    Word is “on the tip of my tongue”, but can’t find it
    Difficult to define concepts in natural language, e.g. dog, anger
    We have a feeling of knowing something, but hard to translate to
     language
 Some observable evidence against natural language
    Children reason with concepts before they can speak
 We often remember gist of what is said, not exact words
      Cognitive science experiment: (recall after 20 second delay)
      He sent a letter about it to Galileo, the great Italian Scientist.
      He sent Galileo, the great Italian Scientist, a letter about it.
      A letter about it was sent to Galileo, the great Italian Scientist.
      Galileo, the great Italian Scientist, sent him a letter about it.
        Represent as Propositions
 Just like the logic we had for AI             isa
    likes(john,mary)
           likes



                                   a
                                                      apple
                                        gives
mary
                   john




                          john
                                                 a



                                 mary
        Evidence for Propositions
 A cognitive Science experiment (Kintsch and Glass)
    Consider two different sentences,
     but both with three “content words”
    The settler built the cabin by hand.
    The crowded passengers squirmed uncomfortably.
         Evidence for Propositions
 A cognitive Science experiment (Kintsch and Glass)
    Consider two different sentences,
     but both with three “content words”
    The settler built the cabin by hand.
        One 3-place relation
    The crowded passengers squirmed uncomfortably.
        Three 1-place relations
 Subjects recalled first sentence better
    Suggests it was simpler in the representation


 (Cognitive Science involves a fair bit of guessing!)
                Associative Networks
 Idea: put together the bits of the propositions that are similar
                Associative Networks
 Idea: put together the bits of the propositions that are similar
                                      isa
              likes




                                                             gives
                             a
   mary                                      apple
                      john



                                               john
                                                                     a



                                                      mary
                   Associative Networks
 Idea: put together the bits of the propositions that are similar

                  likes




                                 isa

   mary
                          john



                          a
                                       apple


          gives
                  Associative Networks
   Idea: put together the bits of the propositions that are similar
   Each node has some level of activation
   Activation spreads in parallel to connecting nodes
   Activation fades rapidly with time
   A node’s total activation is divided among its links
                  Associative Networks
   Idea: put together the bits of the propositions that are similar
   Each node has some level of activation
   Activation spreads in parallel to connecting nodes
   Activation fades rapidly with time
   A node’s total activation is divided among its links
     These rules make sure it doesn’t spread everywhere
 Nodes and links can have different capacities
     Important ones are activated very often
     Have higher capacity
 These ideas seem to match our intuition from introspection
     One thought links to another connected one
              Associative Networks
Cognitive Science experiment (McKoon and Ratcliff)
 Made short paragraphs of connected propositions
 Subjects viewed 2 paragraphs for a short time
 Subjects were shown 36 test words in sequence
  and asked if those words occurred in one of the stories
 For some of the 36 words, they were preceded by a word from
  same story
 For some of the 36 words, they were preceded by a word from
  other story
 Word from same story helped them remember
 …Suggests it is because they were linked in a network
 They also showed recall was better if closer in the network
 …Suggests activation weakens as it spreads
                                Schemas
 Propositional networks can represent specific knowledge
     John gave the apple to Mary
 …but what about general knowledge, or commonsense?
       Apple is edible fruit
       Grows on a tree
       Roundish shape
       Often red when ripe…
   Could augment our proposition network
   Add more propositions to the node for apple
   Apple then becomes a concept
   The connections to apple are a schema for the concept

 What about more advanced concepts/schemas like a trip to a
  restaurant?...
                  Scripts
Elements of a script…
 Identifying name or theme
    Eating in a restaurant
    Visiting the doctor
 Typical roles
    Customer
    Waiter
    Cook
 Entry conditions
    Customer hungry, has money
                     Scripts
 Sequence of goal directed scenes
      Enter
      Get a table
      Order
      Eat
      Pay bill
      Leave
 Sequence of actions within scene
      Get menu
      Read menu
      Decide order
      Give order to waiter
                                      Scripts
 How to represent a script?
 Could use proposition network for all the parts
 … but maybe whole script should be a unit
 Introspection suggests that it is activated as a unit
  without interference from associated propositions
 Experimental evidence (Bower, Black, Turner 1979)…
       Got subjects to read a short story
       Story followed a script, but didn’t fill in all details
       They were then presented various sentences
       Some from story, and some not
       Some trick sentences were included:
          Not from the story, but part of the script
     Subjects were asked to rate 1(sure I didn’t read it) -7(sure I did read it)
     Subjects had a tendency to think they read the trick sentences
     Suggests that they activate the script and fill in the blanks in memory
   …Starting to get a Model of the Mind
 Propositional-schema representations stored in long-term
  memory
 Associative activation used to retrieve relevant memories
 …but many details unspecified
 Need more machinery to account for
    Assess retrieved information, see does it relate to current goals
    Decompose goals into subgoals
    Draw conclusions, make decisions, solve problems
 More importantly:
    How to get new propositions and schemas into memory
    Schemas are often generalised from examples, not taught


 What about working memory?
                      Working Memory
 Most long-term memory not “active” most of the time
 Just keep a few things in working memory for current
  processing
 Very limited: try multiplying 3-digit numbers without paper
 Working memory holds 3-4 chunks at a time
 Why so limited? (it seems useful to have more nowadays)
      Maybe complex circuitry required
      Maybe costly in energy
      Maybe tasks were less complex in environment of early humans
      Or maybe more working memory would cause too many clashes,
       or be too hard to manage
 However limits can be overcome by skill formation

 Note also: limit of 3-4 does not mean other “propositions” inactive
    Could be a lot more going on subconsciously
                         Skill Acquisition
 With a lot of practice we can “automate” many tasks
 We distinguish this from “controlled processing” – using working memory
 Once automated:
    Takes little attention or working memory
     (these are “freed up”)
    Hard not to perform the task – cannot control it well
 Most advanced skills use a combination
    Automatic processes under direction of controlled processes, to meet goals
    Examples: martial arts expert, or musician
            Is Skill Acquisition Separate?
 Evidence from Neuropsychology:
     People with severe “anterograde amnesia”
     Cannot learn new facts
         i.e. can’t get them into long-term propositional memory
     …but can learn new skills
     Example:
         Can learn to solve towers of Hanoi with practice
         But cannot remember any occasion when they practised it
 Suggests that a different part of the brain handles each
 Skill may reside in visual and motor systems, rather than central systems
 Maybe because of evolution:
     Animals often have good skill acquisition
     Maybe humans evolved a specific new module for high level functions
                               Mental Images
 Sometimes we seem to evoke visual images in “mind’s eye”
 Subjective experience suggests visual image is separate from propositions
     …but need experimental evidence
 In imagining a scene:
     Example: search a box of blocks for 3cm cube with two adjacent blue sides
     Properties are added to a description
     But not so many properties as would be present in a real visual scene
         Support, illumination, shading, shadows on near surfaces
     Image does not include properties not available to visual perception
         Other side of cube
 Intuition suggests that “mind’s eye” mimics visual perception
     Maybe it uses the same hardware?
     Would mean that “central system” sends information to vision system
                            Mental Images
Hypothesis: there is a human “visual buffer”
 Short-term memory structure
 Used in both visual perception and “mind’s eye”
 Special features/procedures:
     Can load it, refresh it, perform transformations
     Has a centre with high resolution
     Focus of attention can be moved around


Assuming it exists… what good is it?
 Allows you to pull things out of your visual long term memory
 Use it to build a scene, with all spatial details filled in
 Useful to plan a route, or a rearrangement of objects

 Experiment: how many edges on a cube?
     (Assuming answer is not in long term memory)
    Experiments to show Mental Images
Test a special procedure: mental rotation
Experiments to show Mental Images
   Time taken depended on how much rotation was needed
      Suggests that we really rotate in the “visual buffer”
Experiments to show Mental Images
    Experiments to show Mental Images
 However… just because we rotate stuff doesn’t necessarily mean that we do
  it in the “visual buffer”
    …Need more evidence
 PET brain scans have shown that the “occipital cortex” is used
    “occipital cortex” is known to be involved in visual processing
           So far…
 The “Symbolic” Approach to
     explaining cognition

        an alternative…
the “Connectionist” approach…
           So far…
 The “Symbolic” Approach to
     explaining cognition

        an alternative…
the “Connectionist” approach…
              Connectionist Approach
 What is connectionism?
      Concepts are not stored as clean “propositions”
      They are spread throughout a large network
      “Apple” activates thousands of microfeatures
      Activation of apple depends on context, no single dedicated unit
 Neural plausibility
    Graceful degradation, unlike logical representations
 Cognitive plausibility
    Could explain entire system, rather than some task in central system
     (symbolic accounts can be quite fragmented)
    Could explain the “pattern matching” that seems to happen everywhere
     (for example in retrieval of memories)
    Explain how human concepts/categories do not have clear cut definitions
         Certain attributes increase likelihood (ANN handles this well)
         But not hard and fast rules
    Explains how concepts are learned
         Adjust weights with experience
Another Perspective on Cognitive Science / AI
 We have seen multiple models for the mind,
  and each has an “AI version” too
      Propositions  AI’s logic statements
      Scripts  AI’s case based reasoning
      Mental images  AI: some work, but not much
      Connectionist models  AI’s neural networks
 This gives us another perspective on Cognitive Science / AI
    Both are working in different directions
 AI person starts with a computer and says
    How can I make this do something that a mind does?
    May take some inspiration from what/how a mind does it
 Cognitive Science person starts with a mind and says
    How can I explain something this does, using the “computer metaphor”?
    May take some inspiration from how computers can do it
    Especially from how AI people have shown certain things can be done
Another Perspective on Cognitive Science / AI
 We have seen multiple models for the mind,
                   Which model is
  and each has an “AI version” too correct?
      Propositions  AI’s logic statements
                          …possibly… all of them
      Scripts  AI’s case based reasoning
      Mental images  AI: some work, but not much
                           i.e. all working together
      Connectionist models  AI’s neural networks
 This gives us another perspectivelogicCognitive Science / AI
                e.g. we have seen that on could be
    Both are working in different directions Neurons
                    implemented on top of
 AI person starts with a be in “clean” and says
                (need not computer symbolic way)
    How can I make this do something that a mind does?
    May take some inspiration from what/howfor mind does it
                   This would give opportunity a logical
 Cognitive Science personreasoning, a mind and says
                                   starts with
                    while still having “scruffy” intuitions
                        something the does, using
    How can I explain going on in this background.the “computer metaphor”?
    May take some inspiration from how computers can do it
    Especially from how AI people have shown certain things can be done

				
DOCUMENT INFO
Categories:
Tags:
Stats:
views:0
posted:3/25/2013
language:Unknown
pages:41
xeniawinifred zoe xeniawinifred zoe not http://
About I am optimistic girl.