東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Copycat: A computer model of high-le...

Mitchell, Melanie.

Linked to FindBook

Google Book

Amazon

博客來

Copycat: A computer model of high-level perception and conceptual slippage in analogy making.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Copycat: A computer model of high-level perception and conceptual slippage in analogy making./
Author:	Mitchell, Melanie.
Description:	308 p.
Notes:	Source: Dissertation Abstracts International, Volume: 52-01, Section: B, page: 0349.
Contained By:	Dissertation Abstracts International52-01B.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9116256

Copycat: A computer model of high-level perception and conceptual slippage in analogy making.
Mitchell, Melanie.

Copycat: A computer model of high-level perception and conceptual slippage in analogy making. - 308 p.

Source: Dissertation Abstracts International, Volume: 52-01, Section: B, page: 0349.

Thesis (Ph.D.)--University of Michigan, 1990.

Central to every facet of human intelligence are the abilities to flexibly perceive and categorize situations, to see beyond superficial details and understand the essence of a situation, and to make analogies, fluidly translating concepts from one situation into a different situation. This dissertation describes "Copycat", a computer model of the mental mechanisms underlying this fluidity of concepts and high-level perception in the context of analogy-making.Subjects--Topical Terms:

626642
Computer Science.

Copycat: A computer model of high-level perception and conceptual slippage in analogy making.
LDR:03312nmm 2200325 4500 001 1859297
005 20041014084346.5
008 130614s1990 eng d
035 $a (UnM)AAI9116256
035 $a AAI9116256
040 $a UnM $c UnM
100 1 $a Mitchell, Melanie. $3 672812
245 1 0 $a Copycat: A computer model of high-level perception and conceptual slippage in analogy making.
300 $a 308 p.
500 $a Source: Dissertation Abstracts International, Volume: 52-01, Section: B, page: 0349.
500 $a Co-Chairs: Douglas R. Hofstadter; John H. Holland.
502 $a Thesis (Ph.D.)--University of Michigan, 1990.
520 $a Central to every facet of human intelligence are the abilities to flexibly perceive and categorize situations, to see beyond superficial details and understand the essence of a situation, and to make analogies, fluidly translating concepts from one situation into a different situation. This dissertation describes "Copycat", a computer model of the mental mechanisms underlying this fluidity of concepts and high-level perception in the context of analogy-making.
520 $a For the purpose of isolating and modeling the mechanisms underlying these abilities, a microworld has been developed in which analogies can be made between idealized situations involving strings of letters. Analogy-making in this stripped-down, seemingly simple domain requires many of the same abilities humans use to understand and to make analogies between more complex, real-world situations.
520 $a Copycat constructs interpretations of situations and creates analogies between situations in this microworld. In Copycat, the perception of the essence of a situation and the recognition of essential similarity between two superficially different situations result from the interaction of a large number of simple, independent, and locally-acting perceptual agents with an associative and context-sensitive network of concepts. Central to the model is the notion of statistically emergent high-level behavior, in which the system's low-level activities are permeated with nondeterminism, but more deterministic high-level behavior emerges from the statistics of the low-level nondeterminism.
520 $a This dissertation first discusses some of the central issues in high-level perception and analogy-making and illustrates how the letter-string microworld captures these issues in an idealized form. A description of the Copycat program is presented, and detailed results of its performance on a number of analogy problems are given, demonstrating the program's flexibility and the range of its abilities. Some problems with the model as it now stands are also discussed. Copycat is then compared with related research in artificial intelligence and cognitive science, and a discussion is given of the program's place in the spectrum of computer models of intelligence, ranging from high-level symbolic models to low-level subsymbolic models.
590 $a School code: 0127.
650 4 $a Computer Science. $3 626642
650 4 $a Psychology, General. $3 1018034
650 4 $a Artificial Intelligence. $3 769149
690 $a 0984
690 $a 0621
690 $a 0800
710 2 0 $a University of Michigan. $3 777416
773 0 $t Dissertation Abstracts International $g 52-01B.
790 1 0 $a Hofstadter, Douglas R., $e advisor
790 1 0 $a Holland, John H., $e advisor
790 $a 0127
791 $a Ph.D.
792 $a 1990
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9116256