Upload
thais
View
15
Download
0
Tags:
Embed Size (px)
DESCRIPTION
Analogy-Making. Consider the following cognitive activities. Recognition:. Recognition: A child learns to recognize cats and dogs in books as well as in real life. Recognition: A child learns to recognize cats and dogs in books as well as in real life. - PowerPoint PPT Presentation
Citation preview
Analogy-Making
Consider the following cognitive activities
• Recognition:
• Recognition:– A child learns to recognize cats and dogs in books as
well as in real life.
• Recognition:– A child learns to recognize cats and dogs in books as
well as in real life.
– People can recognize letters of the alphabet, e.g., ‘A’, in many different typefaces and handwriting styles.
– People can recognize letters of the alphabet, e.g., ‘A’, in many different typefaces and handwriting styles.
– People can recognize styles of music:
– People can recognize styles of music:
• “That sounds like Mozart”
– People can recognize styles of music:
• “That sounds like Mozart”
• “That’s a muzak version of ‘Hey Jude’”
– People can recognize styles of music:
• “That sounds like Mozart”
• “That’s a muzak version of ‘Hey Jude’”
– People can recognize abstract situations:
– People can recognize styles of music:
• “That sounds like Mozart”
• “That’s a muzak version of ‘Hey Jude’”
– People can recognize abstract situations:
• A “Cinderella story”
• “Another Vietnam”
• “Monica-gate”
• “Shop-aholic”
• People make scientific analogies:
• People make scientific analogies:– “Biological competition is like economic competition” (Darwin)
• People make scientific analogies:– “Biological competition is like economic competition” (Darwin)
– “The nuclear force is like the electromagnetic force” (Yukawa)
• People make scientific analogies:– “Biological competition is like economic competition” (Darwin)
– “The nuclear force is like the electromagnetic force” (Yukawa)
– “The computer is like the brain” (von Neumann)
• People make scientific analogies:– “Biological competition is like economic competition” (Darwin)
– “The nuclear force is like the electromagnetic force” (Yukawa)
– “The computer is like the brain” (von Neumann)
– “The brain is like the computer” (Simon, Newell, etc.)
• People make unconscious analogies
• People make unconscious analogiesMan: “I’m going shopping for a valentine for my wife.”
• People make unconscious analogiesMan: “I’m going shopping for a valentine for my wife.”
Female colleague: “I did that yesterday.”
• People make unconscious analogiesNewly married woman: “I often forget my new last name”
• People make unconscious analogiesNewly married woman: “I often forget my new last name”
Man: “I have that trouble every January”
• People make unconscious analogiesComputer scientist: “I’m in artificial intelligence because it’s a mixture of psychology, philosophy, linguistics, and computer science”
• People make unconscious analogiesComputer scientist: “I’m in artificial intelligence because it’s a mixture of psychology, philosophy, linguistics, and computer science”
Architect: “That’s the reason I’m in architecture”
What is common to all these examples?
Copycat
(Douglas Hofstadter, Melanie Mitchell, Jim Marshall)
Idealizing analogy-making
abc ---> abdijk --->
Idealizing analogy-making
abc ---> abdijk ---> ijl (replace rightmost
letter by successor)
Idealizing analogy-making
abc ---> abdijk ---> ijl (replace rightmost
letter by successor) ijd (replace rightmost
letter by ‘d’)
Idealizing analogy-making
abc ---> abdijk ---> ijl (replace rightmost
letter by successor) ijd (replace rightmost
letter by ‘d’) ijk (replace all
‘c’s by ‘d’s)
Idealizing analogy-making
abc ---> abdijk ---> ijl (replace rightmost
letter by successor) ijd (replace rightmost
letter by ‘d’) ijk (replace all
‘c’s by ‘d’s) abd (replace any
string by ‘abd’)
Idealizing analogy-making
abc ---> abdiijjkk ---> ?
Idealizing analogy-making
abc ---> abdiijjkk ---> iijjklReplace rightmost letter by successor
Idealizing analogy-making
abc ---> abdiijjkk ---> ?
Idealizing analogy-making
abc ---> abdiijjkk ---> iijjllReplace rightmost “letter” by successor
Idealizing analogy-making
abc ---> abdkji ---> ?
Idealizing analogy-making
abc ---> abdkji ---> kjjReplace rightmost letter by successor
Idealizing analogy-making
abc ---> abdkji ---> ?
Idealizing analogy-making
abc ---> abdkji ---> ljiReplace “rightmost” letter by successor
Idealizing analogy-making
abc ---> abdkji ---> ?
Idealizing analogy-making
abc ---> abdkji ---> ?
Idealizing analogy-making
abc ---> abdkji ---> kjhReplace rightmost letter by “successor”
Idealizing analogy-making
abc ---> abdmrrjjj ---> ?
Idealizing analogy-making
abc ---> abdmrrjjj ---> mrrjjkReplace rightmost letter by successor
Idealizing analogy-making
abc ---> abdmrrjjj ---> ?
Idealizing analogy-making
abc ---> abdmrrjjj ---> ? 1 2 3
Idealizing analogy-making
abc ---> abdmrrjjj ---> ? 1 2 3 1 2 4
Idealizing analogy-making
abc ---> abdmrrjjj ---> mrrjjjj 1 2 3Replace rightmost “letter” by successor
1 2 4
Idealizing analogy-making
abc ---> abdxyz ---> ?
Idealizing analogy-making
abc ---> abdxyz ---> xyaReplace rightmost letter by successor
Idealizing analogy-making
abc ---> abdxyz ---> xya (not allowed)
Replace rightmost letter by successor
Idealizing analogy-making
abc ---> abdxyz ---> ?
Idealizing analogy-making
abc ---> abdxyz ---> ?
last letter in alphabet
Idealizing analogy-making
abc ---> abdxyz ---> ?
last letter in alphabet
first letter in alphabet
Idealizing analogy-making
abc ---> abdxyz ---> ?
last letter in alphabet
first letter in alphabet
Idealizing analogy-making
abc ---> abdxyz ---> wyz
last letter in alphabet
first letter in alphabet
Replace “rightmost” letter by “successor”
Idealizing analogy-making
abc ---> abdxyz ---> wyz
last letter in alphabet
first letter in alphabet
Abilities needed in the letter-string microworld
The Copycat program(Hofstadter and Mitchell)
The Copycat program(Hofstadter and Mitchell)
• Inspired by collective behavior in complex systems (e.g., ant colonies)
The Copycat program(Hofstadter and Mitchell)
• Inspired by collective behavior in complex systems (e.g., ant colonies)
• Understanding and perception of similarity is built up collectively by many independent simple “agents” working in parallel
The Copycat program(Hofstadter and Mitchell)
• Inspired by collective behavior in complex systems (e.g., ant colonies)
• Understanding and perception of similarity is built up collectively by many independent simple “agents” working in parallel
• Each agent has very limited perceptual and communication abilities
The Copycat program(Hofstadter and Mitchell)
• Inspired by collective behavior in complex systems (e.g., ant colonies)
• Understanding and perception of similarity is built up collectively by many independent simple “agents” working in parallel
• Each agent has very limited perceptual and communication abilities
• Teams of agents explore different possibilities for structures, building on what previous teams have constructed.
The Copycat program(Hofstadter and Mitchell)
• Inspired by collective behavior in complex systems (e.g., ant colonies)
• Understanding and perception of similarity is built up collectively by many independent simple “agents” working in parallel
• Each agent has very limited perceptual and communication abilities
• Teams of agents explore different possibilities for structures, building on what previous teams have constructed.
• The resources (agent time) allocated to a possible structure depends on its promise, as assessed dynamically as exploration proceeds.
The Copycat program(Hofstadter and Mitchell)
• Inspired by collective behavior in complex systems (e.g., ant colonies)
• Understanding and perception of similarity is built up collectively by many independent simple “agents” working in parallel
• Each agent has very limited perceptual and communication abilities
• Teams of agents explore different possibilities for structures, building on what previous teams have constructed.
• The resources (agent time) allocated to a possible structure depends on its promise, as assessed dynamically as exploration proceeds.
• The agents working together produce an “emergent” understanding of the analogy.
Architecture of Copycat
Concept network (Slipnet)
Architecture of Copycat
Concept network (Slipnet)
a b c ---> a b di i j j k k --> ?
Architecture of Copycat
Workspace
Concept network (Slipnet)
a b c ---> a b di i j j k k --> ?
Perceptual and structure-building agents (codelets)
Architecture of Copycat
Workspace
Concept network (Slipnet)
a b c ---> a b di i j j k k --> ?
Perceptual and structure-building agents (codelets)
Architecture of Copycat
Temperature
Workspace
Workspace
• The Workspace starts out with letters in the analogy problem and their initial descriptions.
Workspace
a b c --> a b d
m r r j j j --> ?
a b c --> a b d
m r r j j j --> ?
Aleftmostletter
Bmiddleletter
Crightmostletter
Aleftmostletter
Bmiddleletter
Drightmostletter
Mleftmostletter
Jleftmostletter
Rletter
Rletter
Jletter
Jletter
• The Workspace starts out with letters in the analogy problem and their initial descriptions.
• Codelets gradually build up additional descriptions and structures.
Workspace
a b c --> a b d
m r r j j j --> ?
a b c --> a b d
m r r j j j --> ?
• Codelets can be either “bottom-up” (noticers) or “top-down” (seekers).
Workspace
a b c --> a b d
m r r j j j --> ?
a b c --> a b d
m r r j j j --> ?
successorship
a b c --> a b d
m r r j j j --> ?
successorship
• Codelets make probabilistic decisions:
Workspace
• Codelets make probabilistic decisions:– What to look at next
Workspace
• Codelets make probabilistic decisions:– What to look at next– Whether to build a structure there
Workspace
• Codelets make probabilistic decisions:– What to look at next– Whether to build a structure there– How fast to build it
Workspace
• Codelets make probabilistic decisions:– What to look at next– Whether to build a structure there– How fast to build it– Whether to destroy an existing structure there
Workspace
a b c --> a b d
m r r j j j --> ?
a b c --> a b d
m r r j j j --> ? rightmost --> rightmost??
letter --> letter??
a b c --> a b d
m r r j j j --> ? rightmost --> rightmost?
letter --> letter?
a b c --> a b d
m r r j j j --> ? rightmost --> rightmost?
letter --> letter?leftmost --> leftmost??letter --> letter??
a b c --> a b d
m r r j j j --> ? rightmost --> rightmost
letter --> letterleftmost --> leftmost??letter --> letter??
a b c --> a b d
m r r j j j --> ? rightmost --> rightmost
letter --> letterleftmost --> leftmost??letter --> letter??
a b c --> a b d
m r r j j j --> ? rightmost --> rightmost
letter --> letterleftmost --> leftmost??letter --> letter??
rightmost --> rightmost??letter --> group??
a b c --> a b d
m r r j j j --> ? rightmost --> rightmost
letter --> letterleftmost --> leftmost??letter --> letter??
rightmost --> rightmost?letter --> group?
a b c --> a b d
m r r j j j --> ? leftmost --> leftmost?
letter --> letter?rightmost --> rightmostletter --> group
a b c --> a b d
m r r j j j --> ? leftmost --> leftmost?
letter --> letter?rightmost --> rightmostletter --> groupleftmost --> rightmost??
letter --> letter??
a b c --> a b d
m r r j j j --> ? leftmost --> leftmost?
letter --> letter?rightmost --> rightmostletter --> group
high prob.
low prob.
leftmost --> rightmost??letter --> letter??
• Probabilities are used to insure that no possibilities are ruled out in principle, but that not all possibilities have to be considered.
• Probabilities are used to insure that no possibilities are ruled out in principle, but that not all possibilities have to be considered.
• These decisions rely on information being obtained as the run takes place, e.g., pressure from current activation of concepts and neighboring structures.
• Probabilities are used to insure that no possibilities are ruled out in principle, but that not all possibilities have to be considered.
• These decisions rely on information being obtained as the run takes place, e.g., pressure from current activation of concepts and neighboring structures.
• Therefore, the probabilities have to be updated continually.
Slipnet
Part of Copycat’s Slipnet
Slipnet
• Concepts are activated as instances are noticed in workspace.
a b c --> a b d
x y z --> ?
a b c --> a b d
x y z --> ?
Part of Copycat’s Slipnet
successor
Slipnet
• Activation of concepts feeds back into “top-down” pressure to notice instances of those concepts in the workspace.
a b c --> a b d
x y z --> ?
successor
a b c --> a b d
x y z --> ?
successor
a b c --> a b d
x y z --> ?
successor
Slipnet
• Activated concepts spread activation to neighboring concepts.
a b c --> a b d
x y z --> ?
last
last
a b c --> a b d
x y z --> ?
last
lastfirst
a b c --> a b d
x y z --> ?
last
lastfirst
first
Slipnet
• Activation of link concepts determines current ease of slippages of that type (e.g., “opposite”).
a b c --> a b d
x y z --> ?
first
lastleftmost
rightmost
a b c --> a b d
x y z --> ?
first
lastleftmost
rightmost
a b c --> a b d
x y z --> ?
first
last
opposite
first last
first --> last
leftmost
rightmost
a b c --> a b d
x y z --> ?
first
last
opposite
first last
leftmost
rightmost
first --> last
leftmost
rightmost
a b c --> a b d
x y z --> ?
first
last
opposite
first last
leftmost
rightmost
first --> last
leftmost
rightmost
a b c --> a b d
x y z --> ?
first
last
opposite
first last
leftmost
rightmost
first --> lastrightmost --> leftmost
leftmost
rightmost
Temperature
• Measures how well organized the program’s “understanding” is as processing proceeds (a reflection of how good the current worldview is)
Temperature
• Measures how well organized the program’s “understanding” is as processing proceeds (a reflection of how good the current worldview is)– Little organization —> high temperature
Temperature
• Measures how well organized the program’s “understanding” is as processing proceeds (a reflection of how good the current worldview is)– Little organization —> high temperature– Lots of organization —> low temperature
Temperature
a b c --> a b d
m r r j j j --> ?
High temperature
leftmost --> leftmost?letter --> letter?
rightmost --> rightmost??letter --> group??
a b c --> a b d
m r r j j j --> ?
Medium temperature
leftmost --> leftmost?letter --> letter?
rightmost --> rightmostletter --> group
a b c --> a b d
m r r j j j --> ? leftmost --> leftmost
letter --> grouprightmost --> rightmostletter --> group
Low temperature
middle --> middleletter --> group
• Measures how well organized the program’s “understanding” is as processing proceeds (a reflection of how good the current worldview is)– Little organization —> high temperature– Lots of organization —> low temperature
Temperature
• Measures how well organized the program’s “understanding” is as processing proceeds (a reflection of how good the current worldview is)– Little organization —> high temperature– Lots of organization —> low temperature
• Temperature feeds back to codelets:
Temperature
• Measures how well organized the program’s “understanding” is as processing proceeds (a reflection of how good the current worldview is)– Little organization —> high temperature– Lots of organization —> low temperature
• Temperature feeds back to codelets: – High temperature —> low confidence in decisions
—> decisions are made more randomly
Temperature
• Measures how well organized the program’s “understanding” is as processing proceeds (a reflection of how good the current worldview is)– Little organization —> high temperature– Lots of organization —> low temperature
• Temperature feeds back to codelets: – High temperature —> low confidence in decisions
—> decisions are made more randomly– Low temperature —> high confidence in
decisions —> decisions are made more deterministically
Temperature
• Measures how well organized the program’s “understanding” is as processing proceeds (a reflection of how good the current worldview is)– Little organization —> high temperature– Lots of organization —> low temperature
• Temperature feeds back to codelets: – High temperature —> low confidence in decisions
—> decisions are made more randomly– Low temperature —> high confidence in
decisions —> decisions are made more deterministically
• Result: System gradually goes from random, parallel, bottom-up processing to deterministic, serial, top-down processing
Temperature
Demo
What’s needed to apply these ideas in “real world” problems?
What’s needed to apply these ideas in “real world” problems?
• Much expanded repertoire of concepts
What’s needed to apply these ideas in “real world” problems?
• Much expanded repertoire of concepts
• Ability to generate temporary concepts on the fly
What’s needed to apply these ideas in “real world” problems?
• Much expanded repertoire of concepts
• Ability to generate temporary concepts on the fly(e.g., abc ---> abd, ace ---> ?)
What’s needed to apply these ideas in “real world” problems?
• Much expanded repertoire of concepts
• Ability to generate temporary concepts on the fly(e.g., abc ---> abd, ace ---> ?)
• Ability to learn new permanent concepts
What’s needed to apply these ideas in “real world” problems?
• Much expanded repertoire of concepts
• Ability to generate temporary concepts on the fly(e.g., abc ---> abd, ace ---> ?)
• Ability to learn new permanent concepts(e.g., bbb ---> ddd, ppp ---> ?)
What’s needed to apply these ideas in “real world” problems?
• Much expanded repertoire of concepts
• Ability to generate temporary concepts on the fly(e.g., abc ---> abd, ace ---> ?)
• Ability to learn new permanent concepts(e.g., bbb ---> ddd, ppp ---> ?)
• Ability for “self-watching”
What’s needed to apply these ideas in “real world” problems?
• Much expanded repertoire of concepts
• Ability to generate temporary concepts on the fly(e.g., abc ---> abd, ace ---> ?)
• Ability to learn new permanent concepts(e.g., bbb ---> ddd, ppp ---> ?)
• Ability for “self-watching”(e.g., abc ---> abd, xyz ---> ?)
What’s needed to apply these ideas in “real world” problems?
• Much expanded repertoire of concepts
• Ability to generate temporary concepts on the fly(e.g., abc ---> abd, ace ---> ?)
• Ability to learn new permanent concepts(e.g., bbb ---> ddd, ppp ---> ?)
• Ability for “self-watching”(e.g., abc ---> abd, xyz ---> ?)
(cf. Marshall, Metacat, Ph.D. Dissertation, Indiana University, 1998)
Applications of Ideas from Copycat
Applications of Ideas from Copycat
• Letter recognition (McGraw, 1995, Ph.D Dissertation, Indiana University)
Applications of Ideas from Copycat
• Letter recognition (McGraw, 1995, Ph.D Dissertation, Indiana University)
• Natural language processing (Gan, Palmer, and Lua, Computational Linguistics 22(4), 1996, pp. 531-553)
Applications of Ideas from Copycat
• Letter recognition (McGraw, 1995, Ph.D Dissertation, Indiana University)
• Natural language processing (Gan, Palmer, and Lua, Computational Linguistics 22(4), 1996, pp. 531-553)
• Robot control (Lewis and Lugar, Proceedings of the 22nd Annual Conference of the Cognitive Science Society, Erlbaum, 2000.)
Applications of Ideas from Copycat
• Letter recognition (McGraw, 1995, Ph.D Dissertation, Indiana University)
• Natural language processing (Gan, Palmer, and Lua, Computational Linguistics 22(4), 1996, pp. 531-553)
• Robot control (Lewis and Lugar, Proceedings of the 22nd Annual Conference of the Cognitive Science Society, Erlbaum, 2000.)
• Image understanding (Mitchell et al.)