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

Hebbian-LMS Algorithm and Its Application to Clustering.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Hebbian-LMS Algorithm and Its Application to Clustering./
作者:	Kim, Youngsik.
面頁冊數:	1 online resource (134 pages)
附註:	Source: Dissertations Abstracts International, Volume: 82-10, Section: B.
Contained By:	Dissertations Abstracts International82-10B.
標題:	Computer engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28115917click for full text (PQDT)
ISBN:	9798698508953

Hebbian-LMS Algorithm and Its Application to Clustering.
Kim, Youngsik.

Hebbian-LMS Algorithm and Its Application to Clustering. - 1 online resource (134 pages)

Source: Dissertations Abstracts International, Volume: 82-10, Section: B.

Thesis (Ph.D.)--Stanford University, 2017.

Includes bibliographical references

The Hebbian-LMS algorithm is a new unsupervised learning algorithm of an artificial neuron. It comes from the combination of two important concepts: Hebbian learning in neurobiology, and the Least Mean Square algorithm in signal processing. Hebbian learning is widely accepted as a basic theory of synaptic plasticity, which is essential for learning and memory in the human brain. The Least Mean Square algorithm is also widely used in many engineering areas, such as channel equalization or machine learning. The Hebbian-LMS algorithm is simpler and more biologically plausible than other training algorithms of artificial neural networks because the training of each artificial neuron takes place locally following Hebbian learning theory. Thanks to the simplicity, it is easy to apply the Hebbian-LMS algorithm to complicated artificial neural network structures, and the Hebbian-LMS clustering algorithm is introduced on multiple-layer artificial neural networks. It is shown that more artificial neurons and more layers improve the result of the Hebbian-LMS clustering algorithm. Furthermore, the Hebbian-LMS clustering algorithm is tested for various synthetic and real datasets to show that it is a decent clustering algorithm.

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

Mode of access: World Wide Web

ISBN: 9798698508953Subjects--Topical Terms:

621879
Computer engineering.
Subjects--Index Terms:

Hebbian-LMSIndex Terms--Genre/Form:

542853
Electronic books.

Hebbian-LMS Algorithm and Its Application to Clustering.
LDR:02606nmm a2200385K 4500 001 2363093
005 20231116093749.5
006 m o d
007 cr mn ---uuuuu
008 241011s2017 xx obm 000 0 eng d
020 $a 9798698508953
035 $a (MiAaPQ)AAI28115917
035 $a (MiAaPQ)STANFORDrk326xm7876
035 $a AAI28115917
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Kim, Youngsik. $3 3598497
245 1 0 $a Hebbian-LMS Algorithm and Its Application to Clustering.
264 0 $c 2017
300 $a 1 online resource (134 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: 82-10, Section: B.
500 $a Advisor: Poon, Ada Shuk Yan Poon;Widrow, Bernard;Osgood, Brad.
502 $a Thesis (Ph.D.)--Stanford University, 2017.
504 $a Includes bibliographical references
520 $a The Hebbian-LMS algorithm is a new unsupervised learning algorithm of an artificial neuron. It comes from the combination of two important concepts: Hebbian learning in neurobiology, and the Least Mean Square algorithm in signal processing. Hebbian learning is widely accepted as a basic theory of synaptic plasticity, which is essential for learning and memory in the human brain. The Least Mean Square algorithm is also widely used in many engineering areas, such as channel equalization or machine learning. The Hebbian-LMS algorithm is simpler and more biologically plausible than other training algorithms of artificial neural networks because the training of each artificial neuron takes place locally following Hebbian learning theory. Thanks to the simplicity, it is easy to apply the Hebbian-LMS algorithm to complicated artificial neural network structures, and the Hebbian-LMS clustering algorithm is introduced on multiple-layer artificial neural networks. It is shown that more artificial neurons and more layers improve the result of the Hebbian-LMS clustering algorithm. Furthermore, the Hebbian-LMS clustering algorithm is tested for various synthetic and real datasets to show that it is a decent clustering algorithm.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 621879
650 4 $a Neurosciences. $3 588700
650 4 $a Artificial intelligence. $3 516317
653 $a Hebbian-LMS
653 $a Clustering
653 $a Unsupervised learning algorithm
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0464
690 $a 0800
690 $a 0317
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 82-10B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28115917 $z click for full text (PQDT)