東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Artificial language evolution on a d...

Swarup, Samarth.

FindBook

Google Book

Amazon

博客來

Artificial language evolution on a dynamical interaction network.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Artificial language evolution on a dynamical interaction network./
作者:	Swarup, Samarth.
面頁冊數:	114 p.
附註:	Adviser: Sylvian R. Ray.
Contained By:	Dissertation Abstracts International68-11B.
標題:	Artificial Intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3290395
ISBN:	9780549343929

Artificial language evolution on a dynamical interaction network.
Swarup, Samarth.

Artificial language evolution on a dynamical interaction network. - 114 p.

Adviser: Sylvian R. Ray.

Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2007.

This dissertation studies the impact of a dynamical interaction network on the distributed learning of a common language. We derive a new algorithm for generating realistic complex networks, called Noisy Preferential Attachment (NPA). This is a modification of preferential attachment that unifies it with the quasispecies model of molecular evolution. The growing network can now be seen as a process in which the links in the network are undergoing selection, replication, and mutation. We also demonstrate that by varying the mutation rate over time, we can reproduce features of growing networks in the real world. We then model a population of language learning agents on an interaction topology evolving according to NPA and demonstrate that under certain conditions they can converge very rapidly. However, we also note that they always converge to a maximally simple language. This leads us to introduce a method of relating language to task based on an analogy between the agents' hypothesis space and an information channel. We introduce a new "language game" which we call the classification game. We show that the population, through playing the classification game, converges to a representation which is simple, but not too simple, by balancing the pressures for learnability and functionality. We demonstrate that the population can avoid overfitting through this process. The languages that emerge can be either holistic or compositional. We then introduce temporal tasks and show that the same setup, using recurrent neural networks and form-meaning association matrices, can generate languages with strict symbol ordering, which is a rudimentary form of syntax. Finally, we bring together language and topology evolution and show that when the classification game is played on a topology evolving according to NPA, very rapid convergence can be achieved at the expense of a small increase in complexity of the solution. We also compare the convergence rates of several other topologies and show that NPA results in the fastest convergence. Regular and small world topologies show very slow convergence, due to the formation of communities which are locally converged but at odds with other communities.

ISBN: 9780549343929Subjects--Topical Terms:

769149
Artificial Intelligence.

Artificial language evolution on a dynamical interaction network.
LDR:03107nam 2200277 a 45 001 958975
005 20110704
008 110704s2007 ||||||||||||||||| ||eng d
020 $a 9780549343929
035 $a (UMI)AAI3290395
035 $a AAI3290395
040 $a UMI $c UMI
100 1 $a Swarup, Samarth. $3 1282442
245 1 0 $a Artificial language evolution on a dynamical interaction network.
300 $a 114 p.
500 $a Adviser: Sylvian R. Ray.
500 $a Source: Dissertation Abstracts International, Volume: 68-11, Section: B, page: 7454.
502 $a Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2007.
520 $a This dissertation studies the impact of a dynamical interaction network on the distributed learning of a common language. We derive a new algorithm for generating realistic complex networks, called Noisy Preferential Attachment (NPA). This is a modification of preferential attachment that unifies it with the quasispecies model of molecular evolution. The growing network can now be seen as a process in which the links in the network are undergoing selection, replication, and mutation. We also demonstrate that by varying the mutation rate over time, we can reproduce features of growing networks in the real world. We then model a population of language learning agents on an interaction topology evolving according to NPA and demonstrate that under certain conditions they can converge very rapidly. However, we also note that they always converge to a maximally simple language. This leads us to introduce a method of relating language to task based on an analogy between the agents' hypothesis space and an information channel. We introduce a new "language game" which we call the classification game. We show that the population, through playing the classification game, converges to a representation which is simple, but not too simple, by balancing the pressures for learnability and functionality. We demonstrate that the population can avoid overfitting through this process. The languages that emerge can be either holistic or compositional. We then introduce temporal tasks and show that the same setup, using recurrent neural networks and form-meaning association matrices, can generate languages with strict symbol ordering, which is a rudimentary form of syntax. Finally, we bring together language and topology evolution and show that when the classification game is played on a topology evolving according to NPA, very rapid convergence can be achieved at the expense of a small increase in complexity of the solution. We also compare the convergence rates of several other topologies and show that NPA results in the fastest convergence. Regular and small world topologies show very slow convergence, due to the formation of communities which are locally converged but at odds with other communities.
590 $a School code: 0090.
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Computer Science. $3 626642
690 $a 0800
690 $a 0984
710 2 $a University of Illinois at Urbana-Champaign. $3 626646
773 0 $t Dissertation Abstracts International $g 68-11B.
790 $a 0090
790 1 0 $a Ray, Sylvian R., $e advisor
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3290395