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

Hierarchical learning of conjunctive...

Gunay, Cengiz.

Linked to FindBook

Google Book

Amazon

博客來

Hierarchical learning of conjunctive concepts in spiking neural networks.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Hierarchical learning of conjunctive concepts in spiking neural networks./
Author:	Gunay, Cengiz.
Description:	223 p.
Notes:	Source: Dissertation Abstracts International, Volume: 64-12, Section: B, page: 6162.
Contained By:	Dissertation Abstracts International64-12B.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3116874
ISBN:	0496643078

Hierarchical learning of conjunctive concepts in spiking neural networks.
Gunay, Cengiz.

Hierarchical learning of conjunctive concepts in spiking neural networks. - 223 p.

Source: Dissertation Abstracts International, Volume: 64-12, Section: B, page: 6162.

Thesis (Ph.D.)--University of Louisiana at Lafayette, 2003.

The temporal correlation hypothesis proposes that synchronous activity in different regions of the brain describes integral entities. This temporal binding approach is a possible solution to the longstanding binding problem of representing composite objects. To complement the dynamic nature of temporal binding, a recruitment learning method has been proposed for providing long-term storage. We improve the recruitment method to use a more realistic and powerful spiking neuron model.

ISBN: 0496643078Subjects--Topical Terms:

626642
Computer Science.

Hierarchical learning of conjunctive concepts in spiking neural networks.
LDR:01817nmm 2200301 4500 001 1838416
005 20050526083751.5
008 130614s2003 eng d
020 $a 0496643078
035 $a (UnM)AAI3116874
035 $a AAI3116874
040 $a UnM $c UnM
100 1 $a Gunay, Cengiz. $3 1926834
245 1 0 $a Hierarchical learning of conjunctive concepts in spiking neural networks.
300 $a 223 p.
500 $a Source: Dissertation Abstracts International, Volume: 64-12, Section: B, page: 6162.
500 $a Director: Anthony S. Maida.
502 $a Thesis (Ph.D.)--University of Louisiana at Lafayette, 2003.
520 $a The temporal correlation hypothesis proposes that synchronous activity in different regions of the brain describes integral entities. This temporal binding approach is a possible solution to the longstanding binding problem of representing composite objects. To complement the dynamic nature of temporal binding, a recruitment learning method has been proposed for providing long-term storage. We improve the recruitment method to use a more realistic and powerful spiking neuron model.
520 $a However, using continuous-time spiking neurons and brain-like connectivity assumptions poses new problems in hierarchical recruitment. First, we propose timing parameter constraints for recruitment over asymmetrically delayed lines. Second, we calculate required feedforward excitatory and lateral inhibitory connection densities for stable propagation of activity independent of network size.
590 $a School code: 1363.
650 4 $a Computer Science. $3 626642
650 4 $a Biology, Neuroscience. $3 1017680
650 4 $a Artificial Intelligence. $3 769149
690 $a 0984
690 $a 0317
690 $a 0800
710 2 0 $a University of Louisiana at Lafayette. $3 1025962
773 0 $t Dissertation Abstracts International $g 64-12B.
790 1 0 $a Maida, Anthony S., $e advisor
790 $a 1363
791 $a Ph.D.
792 $a 2003
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3116874