Changes

Jump to: navigation, search

EPAM

16,069 bytes added, 15:34, 14 August 2018
Created page with "'''Home * Knowledge * Cognition * EPAM''' FILE:epamnet.jpg|border|right|thumb| EPAM discrimination net <ref>A typical EPAM discrimination net, Image f..."
'''[[Main Page|Home]] * [[Knowledge]] * [[Cognition]] * EPAM'''

[[FILE:epamnet.jpg|border|right|thumb| EPAM discrimination net <ref>A typical EPAM discrimination net, Image from [[Edward Feigenbaum]], [[Herbert Simon]] ('''1963'''). ''[https://saltworks.stanford.edu/catalog/druid:sf355sf7850 Elementary Perceiver and Memorizer: Review of Experiments]''. in Symposium on Simulation Models, pp. 103</ref> ]]

'''EPAM''', (Elementary Perceiver and Memorizer)<br/>
an early computer model of [https://en.wikipedia.org/wiki/Rote_learning rote learning] by the method of [https://en.wikipedia.org/wiki/Pair_by_association paired associates], first conceived by [[Herbert Simon]] and [[Allen Newell]] during their early conception about computer simulation of [[Cognition|cognitive]] processes in the 50s <ref>[[Edward Feigenbaum]] ('''1959'''). ''[http://www.rand.org/pubs/papers/P1817.html An Information Processing Theory of Verbal Learning]''. [https://en.wikipedia.org/wiki/RAND_Corporation RAND Paper]</ref> , implemented as computer program by [[Edward Feigenbaum]] in the late 50s in [https://en.wikipedia.org/wiki/Information_Processing_Language IPL-V] for the [[IBM 704]] and [[IBM 7090]], as topic of his Ph.D. thesis at [[Carnegie Mellon University]]. In terms of [[Psychology|psychology]] and [https://en.wikipedia.org/wiki/Behaviorism behaviorism] EPAM associates responses with external [https://en.wikipedia.org/wiki/Stimulus_%28psychology%29 stimuli], quite similar to [https://en.wikipedia.org/wiki/Classical_conditioning classical conditioning].

=Learning=
EPAM [[Learning|learns]] by growing a [https://en.wikipedia.org/wiki/Discrimination_%28disambiguation%29#Science_and_research discrimination] [https://en.wikipedia.org/wiki/Net_%28mathematics%29 net] kept in long-term [[Memory|memory]], a [https://en.wikipedia.org/wiki/Tree_%28data_structure%29 tree-like structure] whose [https://en.wikipedia.org/wiki/Vertex_%28graph_theory%29 nodes] contain tests that may be applied to objects that have been described as bundles of [https://en.wikipedia.org/wiki/Perception perceptual] features. In EPAM III, introduced in 1964 <ref>[[Herbert Simon]], [[Edward Feigenbaum]] ('''1964'''). ''An Information-processing Theory of Some Effects of Similarity, Familiarization, and Meaningfulness in Verbal Learning''. Journal of Verbal Learning and Verbal Behavior, Vol. 3, No. 5, [https://saltworks.stanford.edu/assets/zp668jb3733.pdf pdf]</ref> , the test nodes were generalized as n-ary switch instead of binary of EPAM II. When a familiar object is perceived, it is recognized by being sorted through the EPAM net. At the terminal nodes of the EPAM net, partial "images" are stored, also in the form of feature bundles of the objects sorted to the respective terminals, together with other information about the objects <ref>[[Herbert Simon]], [[William Chase]] ('''1973'''). ''Skill in Chess''. [https://en.wikipedia.org/wiki/American_Scientist American Scientist], Vol. 61, No. 4, Reprinted ('''1988''') in [[Computer Chess Compendium]], [http://digitalcollections.library.cmu.edu/awweb/awarchive?type=file&item=44582 pdf]</ref> , such as [https://en.wikipedia.org/wiki/Sensory_cue cue] information, used to feed back into the net [[Recursion|recursively]] .

=EPAM in Chess=
Thus, EPAM has a recursive structure. Any object, once familiarized and incorporated into the net, can itself serve as a perceptual feature of a more complex object. For instance in the domain of chess, once the various types of chess pieces and their proximity become familiarized, these can become features of more complex configurations, i.e. a "fianchettoed castled Black King's position". Once familiarized, such a complex can, in turn, serve as a perceptual feature of a still more complex pattern, finally the entire chess position.

=The EPAM Simulation=
Excerpt from ''Elementary Perceiver and Memorizer: Review of Experiments'' <ref>[[Edward Feigenbaum]], [[Herbert Simon]] ('''1963'''). ''[https://saltworks.stanford.edu/catalog/druid:sf355sf7850 Elementary Perceiver and Memorizer: Review of Experiments]''. in Symposium on Simulation Models</ref> :
The EPAM processes perform the following four principal functions:
# Recognize an external stimulus as one about which some information has already been memorized
# Add new stimulus items to the memory by building discriminations (tests) that allow the new item to be distinguished from stimuli previously learned
# Associate (internally) two stored items, say x and y, by storing with x some cue information about y
# Respond to an external stimulus X with a response, Y, by retrieving the cue to the response, and then retrieving the response using the cue

Thus, EPAM has two performance processes, enabling It to respond using material already learned: the discrimination process (1), which recognizes the stimulus, and the response process (4), which finds the appropriate response associated with the stimulus and produces it. EPAM also has two learning processes: the discrimination learning process (2), which elaborates the structure of discrimination tests it applies to stimuli, and the association learning process (3), which associates response cues with stimuli.

The central "memory structure, which the performance processes use and the learning processes construct, is the discrimination net. It is a tree-like nexus of associations at whose terminal nodes are stored Images of encodings of external stimuli. At the non-terminal nodes of the net are stored tests which examine particular bits of the encodings. The image of a stimulus is retrieved by sorting the encoding of the stimulus down through the tests of the net to the appropriate terminal. In learning a set of stimuli, the net is grown to a size that is Just large enough (roughly) to discriminate among the different stimuli that have been presented to the system.

Association of a response, y, to a stimulus, x, is accomplished by storing a small amount of the information about y (an incomplete cue image of y) along with the image of x. The system determines by trial and error how much information must be stored as a cue to retrieve the response from the net when the association is made.

=MAPP=
EPAM was influential in formalizing the concept of [[Chunking|chunking]]. It was used in the [[MAPP]] (Memory-aided Pattern Perceiver) program by [[Herbert Simon|Simon]] and [[Kevin J. Gilmartin|Gilmartin]] <ref>[[Herbert Simon]], [[Kevin J. Gilmartin]] ('''1973'''). ''A Simulation of Memory for Chess Positions''. Cognitive Psychology, Vol. 5, pp. 29-46, reprinted in [[Herbert Simon]] ('''1979'''). ''[http://yalepress.yale.edu/yupbooks/book.asp?isbn=9780300024326 Models of Thought]''. [https://en.wikipedia.org/wiki/Yale_University_Press Yale University Press]</ref> to simulate the [[William Chase#Perception|chess board reconstruction task]]. An EPAM net was stimulated by the piece [https://en.wikipedia.org/wiki/Fixation_%28visual%29 fixation] of the [[Eye Movements|eye movement]] simulation program [[Perceiver]], to recognize cluster of pieces surrounding the fixated piece as a familar chunk. In the perception phase up to seven symbols designating these chunks were stored in short-term [[Memory|memory]]. In the reconstruction phase, the EPAM net was used to decode the symbols held in short-term memory into locational information for each of the pieces in a chunk. In various experiments, MAPP was able to reconstruct positions with 73% accuracy <ref>[[Herbert Simon]], [[Kevin J. Gilmartin]] ('''1973'''). ''A Simulation of Memory for Chess Positions''. Cognitive Psychology, Vol. 5, pp. 29-46</ref> <ref>[[Michael George]], [[Jonathan Schaeffer]] ('''1990'''). ''[http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.54.2766 Chunking for Experience]''. [[ICGA Journal#13_3|ICCA Journal, Vol. 13, No. 3]], [http://webdocs.cs.ualberta.ca/~jonathan/publications/ai_publications/mach.pdf pdf]</ref>
[[FILE:Chess_Mapp.jpg|none|border|text-bottom|link=http://snitkof.com/cg156/chesschunkingtheory.php]]
A schematic representation of the principle components of MAPP shows the learning and performance<br/>
processes used to reconstruct a chess position <ref>Image from [http://snitkof.com/cg156/chesschunkingtheory.php Expertise in Memory - Evidence for Chunking Theory] by [http://snitkof.com/cg156/contact.php Victor Long], [http://snitkof.com/cg156/contact.php Chandra Singh] and [https://www.linkedin.com/in/davidsnitkof David Snitkof], [https://en.wikipedia.org/wiki/Brown_University Brown University], see also Figure 6 in [[Herbert Simon]], [[William Chase]] ('''1973'''). ''Skill in Chess''. [https://en.wikipedia.org/wiki/American_Scientist American Scientist], Vol. 61, No. 4, pp. 401, reprinted in [[David Levy]] (ed.) ('''1988''') ''[[Computer Chess Compendium]]'', [http://digitalcollections.library.cmu.edu/awweb/awarchive?type=file&item=44582 pdf]</ref>

=CHREST=
The EPAM concept was further influential for [[Fernand Gobet|Fernand Gobet's]] [[CHREST]] (Chunk Hierarchy and REtrieval STructures) architecture, applied in Gobet's and [[Peter Jansen|Jansen's]] [[Pattern Learning|pattern learning]] chess program [[CHUMP]] <ref>[[Fernand Gobet]], [[Peter Jansen]] ('''1994'''). ''[http://people.brunel.ac.uk/~hsstffg/abstracts/chess_program.html Towards a Chess Program Based on a Model of Human Memory].'' [[Advances in Computer Chess 7]]</ref> .

=See also=
* [[CHREST]]
* [[CHUMP]]
* [[Chunking]]
* [[Learning]]
* [[MAPP]]
* [[Neural Networks]]
* [[Pattern Recognition]]

=Publicatons=
==1959==
* [[Edward Feigenbaum]] ('''1959'''). ''[http://www.rand.org/pubs/papers/P1817.html An Information Processing Theory of Verbal Learning]''. [https://en.wikipedia.org/wiki/RAND_Corporation RAND Paper]
==1960 ...==
* [[Edward Feigenbaum]] ('''1960'''). ''Information Theories of Human Verbal Learning''. Ph.D. thesis, [[Carnegie Mellon University]], advisor [[Herbert Simon]]
* [[Edward Feigenbaum]] ('''1961'''). ''[http://dl.acm.org/citation.cfm?id=1460704 The Simulation of Verbal Learning Behavior]''. Proceedings Western Joint Conference, Vol. 19
* [[Edward Feigenbaum]], [[Herbert Simon]] ('''1961'''). ''Performance of a Reading Task by an Elementary Perceiving and Memorizing Program''. [https://en.wikipedia.org/wiki/RAND_Corporation RAND Paper], [http://www.rand.org/content/dam/rand/pubs/papers/2008/P2358.pdf pdf]
* [[Edward Feigenbaum]], [[Herbert Simon]] ('''1961'''). ''[http://dl.acm.org/citation.cfm?id=800029.808503&coll=DL&dl=GUIDE&CFID=111335796&CFTOKEN=62851440 Forgetting in an association memory]''. ACM '61, [http://www.rand.org/content/dam/rand/pubs/papers/2008/P2311.pdf pdf]
* [[Edward Feigenbaum]], [[Herbert Simon]] ('''1962'''). ''A Theory of the Serial Position Effect''. [https://en.wikipedia.org/wiki/British_Journal_of_Psychology#Journals British Journal of Psychology], Vol. 53, 307-32, [http://www.rand.org/pubs/papers/2008/P2375.pdf pdf]
* [[Edward Feigenbaum]], [[Herbert Simon]] ('''1963'''). ''[https://saltworks.stanford.edu/catalog/druid:sf355sf7850 Elementary Perceiver and Memorizer: Review of Experiments]''. in Symposium on Simulation Models
* [[Herbert Simon]], [[Edward Feigenbaum]] ('''1964'''). ''An Information-processing Theory of Some Effects of Similarity, Familiarization, and Meaningfulness in Verbal Learning''. Journal of Verbal Learning and Verbal Behavior, Vol. 3, No. 5, [https://saltworks.stanford.edu/assets/zp668jb3733.pdf pdf]
==1970 ...==
* [[Herbert Simon]], [[Kevin J. Gilmartin]] ('''1973'''). ''A Simulation of Memory for Chess Positions''. [http://www.journals.elsevier.com/cognitive-psychology/ Cognitive Psychology], Vol. 5
* [[Herbert Simon]], [[William Chase]] ('''1973'''). ''Skill in Chess''. [https://en.wikipedia.org/wiki/American_Scientist American Scientist], Vol. 61, No. 4, Reprinted ('''1988''') in [[Computer Chess Compendium]], [http://digitalcollections.library.cmu.edu/awweb/awarchive?type=file&item=44582 pdf]
* [[Herbert Simon]] ('''1974'''). ''How big is a chunk''? [https://en.wikipedia.org/wiki/Science_%28journal%29 Science], Vol. 183, [http://digitalcollections.library.cmu.edu/awweb/awarchive?type=file&item=44527 pdf]
==1980 ...==
* [https://en.wikipedia.org/wiki/Lawrence_W._Barsalou Lawrence W. Barsalou], [https://en.wikipedia.org/wiki/Gordon_H._Bower Gordon H. Bower] ('''1984'''). ''[http://onlinelibrary.wiley.com/doi/10.1207/s15516709cog0801_1/abstract Discrimination Nets as Psychological Models]''. [https://en.wikipedia.org/wiki/Cognitive_Science_Society Cognitive Science], Vol. 8, No. 1 <ref>[https://en.wikipedia.org/wiki/Pandemonium_architecture Pandemonium architecture from Wikipedia]</ref>
* [[Edward Feigenbaum]], [[Herbert Simon]] ('''1984'''). ''[http://www.sciencedirect.com/science/article/pii/S0364021384800051 EPAMlike models of recognition and learning]''. [https://en.wikipedia.org/wiki/Cognitive_Science_Society Cognitive Science], Vol. 8, 305-336, [http://csjarchive.cogsci.rpi.edu/1984v08/i04/p0305p0336/MAIN.PDF pdf]
==1990 ...==
* [[Howard B. Richman]], [[James J. Staszewski]], [[Herbert Simon]] ('''1995'''). ''[http://psycnet.apa.org/journals/rev/102/2/305/ Simulation of Expert Memory with EPAM IV]''. Psychological Review, Vol. 102
* [[Fernand Gobet]], [[Howard B. Richman]], [[James J. Staszewski]], [[Herbert Simon]] ('''1997'''). ''Goals, Representations, and Strategies in a Concept Attainment Task: The EPAM model''. The Psychology of Learning and Motivation, Vol. 37, [http://digitalcollections.library.cmu.edu/awweb/awarchive?type=file&item=34259 pdf]
==2000 ...==
* [[Fernand Gobet]], [[Herbert Simon]] ('''2000'''). ''[http://onlinelibrary.wiley.com/doi/10.1207/s15516709cog2404_4/abstract Five Seconds or Sixty? Presentation Time in Expert Memory]''. [https://en.wikipedia.org/wiki/Cognitive_Science_Society Cognitive Science], Vol. 24, No. 4
* [[Fernand Gobet]], [[Peter Lane]], [http://my.ilstu.edu/~sfcroke/ Steve Croker], [http://www.informatik.uni-trier.de/~ley/db/indices/a-tree/c/Cheng:Peter_C=_H=.html Peter C-H. Cheng], [http://www.ntu.ac.uk/apps/Profiles/53951-1-4/Dr_Gary_Jones.aspx Gary Jones], [http://ijosblog.blogspot.de/2012_02_01_archive.html Iain Oliver], [http://www.liv.ac.uk/psychology-health-and-society/staff/julian-pine/ Julian M. Pine] ('''2001'''). ''[http://www.sciencedirect.com/science/article/pii/S1364661300016624 Chunking mechanisms in human learning]''. Trends in Cognitive Sciences, Vol. 5, No. 6
* [[Fernand Gobet]] ('''2005'''). ''[http://onlinelibrary.wiley.com/doi/10.1002/acp.1110/abstract Chunking Models of Expertise: Implications for Education]''. Applied Cognitive Psychology, Vol. 19, No. 2

=External Links=
* [https://en.wikipedia.org/wiki/EPAM EPAM from Wikipedia]
* [http://snitkof.com/cg156/epam.php Expertise in Memory - EPAM Model] by [http://snitkof.com/cg156/contact.php Victor Long], [http://snitkof.com/cg156/contact.php Chandra Singh] and [https://www.linkedin.com/in/davidsnitkof David Snitkof], [https://en.wikipedia.org/wiki/Brown_University Brown University]
* [http://snitkof.com/cg156/chesschunkingtheory.php Expertise in Memory - Evidence for Chunking Theory] by [http://snitkof.com/cg156/contact.php Victor Long], [http://snitkof.com/cg156/contact.php Chandra Singh] and [https://www.linkedin.com/in/davidsnitkof David Snitkof], [https://en.wikipedia.org/wiki/Brown_University Brown University]
* [[:Category:Agnes Obel|Agnes Obel]] - [https://en.wikipedia.org/wiki/Agnes_Obel#cite_ref-41 Familiar], [https://fr.wikipedia.org/wiki/Alcaline_(%C3%A9mission_de_t%C3%A9l%C3%A9vision) Alcaline], November 07, 2016, [https://en.wikipedia.org/wiki/YouTube YouTube] Video
: featuring [https://www.couchsurfing.com/people/kriskar Kristina Koropecki], [https://mobile.twitter.com/agnesobel_org/status/637306150413803524 Charlotte Danhier], [https://www.discogs.com/de/artist/1453695-Catherine-De-Biasio Catherine De Biasio]
: {{#evu:https://www.youtube.com/watch?v=bHZXsiNh4mA|alignment=left|valignment=top}}

=References=
<references />

'''[[Cognition|Up one Level]]'''
[[Category:Agnes Obel]]

Navigation menu