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

FindBook

Google Book

Amazon

博客來

Language Processing in Real and Artifical Neural Networks.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Language Processing in Real and Artifical Neural Networks./
作者:	Wong, Chun Kit.
面頁冊數:	1 online resource (163 pages)
附註:	Source: Dissertations Abstracts International, Volume: 73-06, Section: A.
Contained By:	Dissertations Abstracts International73-06A.
標題:	Linguistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3488974click for full text (PQDT)
ISBN:	9781267056979

Language Processing in Real and Artifical Neural Networks.
Wong, Chun Kit.

Language Processing in Real and Artifical Neural Networks. - 1 online resource (163 pages)

Source: Dissertations Abstracts International, Volume: 73-06, Section: A.

Thesis (Ph.D.)--The Chinese University of Hong Kong (Hong Kong), 2009.

Includes bibliographical references

The first part of this thesis reports a computational simulation work on modelling language processing. The motivation was from a study that attempted to show that contemporary connectionist models, the simple recurrent networks being the exemplar, fail to exhibit a kind of generalisation that is essential for acquiring natural language. A replication of the simulation, however, revealed a pattern that was to the contrary. I extended the simulation to investigate the plausible causes of the discrepancies and I argued that generalisation is possible in connectionist models as long as the knowledge of categories is successfully induced by the networks. The second part of the thesis reports an investigation of how the real brain functions during tasks of language processing. To be more specific, during a task of reading for comprehension. I employed a high temporal resolution brain imaging technique known as electroencephalography (EEG), through which the electrical potentials, in terms of micro-volts, as a consequence of participants' engagement of the reading task were measured from electrodes that were placed on their scalps. Event-related-potentials (ERPs), also referred to as "brain waves", were then derived from these measured time series of voltages. In this ERP study of reading, I identified the earliest brain responses to semantic processing and I argued that within one fifth of a second the brain has already started to process the meanings of a word. Despite the fact that the two parts of the thesis represent research work of two different disciplines, the central theme of my thesis remains clear - to study how language is possible in a brain.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9781267056979Subjects--Topical Terms:

524476
Linguistics.
Subjects--Index Terms:

Artificial neural networksIndex Terms--Genre/Form:

542853
Electronic books.

Language Processing in Real and Artifical Neural Networks.
LDR:03136nmm a2200421K 4500 001 2365388
005 20231213130707.5
006 m o d
007 cr mn ---uuuuu
008 241011s2009 xx obm 000 0 eng d
020 $a 9781267056979
035 $a (MiAaPQ)AAI3488974
035 $a AAI3488974
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Wong, Chun Kit. $3 3706248
245 1 0 $a Language Processing in Real and Artifical Neural Networks.
264 0 $c 2009
300 $a 1 online resource (163 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 73-06, Section: A.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Wang, William S-Y.
502 $a Thesis (Ph.D.)--The Chinese University of Hong Kong (Hong Kong), 2009.
504 $a Includes bibliographical references
520 $a The first part of this thesis reports a computational simulation work on modelling language processing. The motivation was from a study that attempted to show that contemporary connectionist models, the simple recurrent networks being the exemplar, fail to exhibit a kind of generalisation that is essential for acquiring natural language. A replication of the simulation, however, revealed a pattern that was to the contrary. I extended the simulation to investigate the plausible causes of the discrepancies and I argued that generalisation is possible in connectionist models as long as the knowledge of categories is successfully induced by the networks. The second part of the thesis reports an investigation of how the real brain functions during tasks of language processing. To be more specific, during a task of reading for comprehension. I employed a high temporal resolution brain imaging technique known as electroencephalography (EEG), through which the electrical potentials, in terms of micro-volts, as a consequence of participants' engagement of the reading task were measured from electrodes that were placed on their scalps. Event-related-potentials (ERPs), also referred to as "brain waves", were then derived from these measured time series of voltages. In this ERP study of reading, I identified the earliest brain responses to semantic processing and I argued that within one fifth of a second the brain has already started to process the meanings of a word. Despite the fact that the two parts of the thesis represent research work of two different disciplines, the central theme of my thesis remains clear - to study how language is possible in a brain.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Linguistics. $3 524476
650 4 $a Psychobiology. $3 555678
650 4 $a Artificial intelligence. $3 516317
653 $a Artificial neural networks
653 $a Brain imaging
653 $a ERP
653 $a Language processing
653 $a Neural networks
653 $a Simulation
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0290
690 $a 0349
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a The Chinese University of Hong Kong (Hong Kong). $3 1017547
773 0 $t Dissertations Abstracts International $g 73-06A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3488974 $z click for full text (PQDT)