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

Linked to FindBook

Google Book

Amazon

博客來

Modular Neural Networks.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Modular Neural Networks./
Author:	Sakryukin, Andrey.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
Description:	139 p.
Notes:	Source: Dissertations Abstracts International, Volume: 83-07, Section: B.
Contained By:	Dissertations Abstracts International83-07B.
Subject:	Signal transduction. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28832594
ISBN:	9798460441884

Modular Neural Networks.
Sakryukin, Andrey.

Modular Neural Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 139 p.

Source: Dissertations Abstracts International, Volume: 83-07, Section: B.

Thesis (Ph.D.)--National University of Singapore (Singapore), 2021.

This item must not be sold to any third party vendors.

The term Modular Network was known before its application to Neural Networks and was defined multiple times in different areas of research, including Applied Mathematics, Social Sciences, Biology, and others. Li and Shuurmans defined modularity as a function quantifying the quality of a network division into communities. So Modular Networks (MN) - are the networks containing highly connected regions (communities), which are sparsely connected to the rest of the network. In this work we study the evolvement of different types of Modular Networks in the field of deep learning. The focus of our research is in the advantages of such architectures applied to different domains and tasks. We start by introducing the advantages of modular architectures in addressing high-dimensional output space problems, as well as proposing a novel uncertainty-based strategy for the structure inference. Next, we study the application of MNs to the problem of incremental learning and functionality disentanglement. Finally, we discuss advantages of modular architectures in sparse-reward problems of reinforcement learning.

ISBN: 9798460441884Subjects--Topical Terms:

3546420
Signal transduction.
Subjects--Index Terms:

Modular Network

Modular Neural Networks.
LDR:02400nmm a2200445 4500 001 2349639
005 20230509091134.5
006 m o d
007 cr#unu||||||||
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798460441884
035 $a (MiAaPQ)AAI28832594
035 $a (MiAaPQ)USingapore186012
035 $a AAI28832594
040 $a MiAaPQ $c MiAaPQ
100 1 $a Sakryukin, Andrey. $3 3689051
245 1 0 $a Modular Neural Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 139 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-07, Section: B.
502 $a Thesis (Ph.D.)--National University of Singapore (Singapore), 2021.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be sold to any third party vendors.
520 $a The term Modular Network was known before its application to Neural Networks and was defined multiple times in different areas of research, including Applied Mathematics, Social Sciences, Biology, and others. Li and Shuurmans defined modularity as a function quantifying the quality of a network division into communities. So Modular Networks (MN) - are the networks containing highly connected regions (communities), which are sparsely connected to the rest of the network. In this work we study the evolvement of different types of Modular Networks in the field of deep learning. The focus of our research is in the advantages of such architectures applied to different domains and tasks. We start by introducing the advantages of modular architectures in addressing high-dimensional output space problems, as well as proposing a novel uncertainty-based strategy for the structure inference. Next, we study the application of MNs to the problem of incremental learning and functionality disentanglement. Finally, we discuss advantages of modular architectures in sparse-reward problems of reinforcement learning.
590 $a School code: 1883.
650 4 $a Signal transduction. $3 3546420
650 4 $a Schizophrenia. $3 525919
650 4 $a Deep learning. $3 3554982
650 4 $a Success. $3 518195
650 4 $a Recommender systems. $3 3562220
650 4 $a Brain research. $3 3561789
650 4 $a Neural networks. $3 677449
650 4 $a Design. $3 518875
650 4 $a Age groups. $2 bicssc $3 2081388
650 4 $a Algorithms. $3 536374
650 4 $a Actors. $3 641271
650 4 $a Ablation. $3 3562462
650 4 $a Expected values. $3 3563993
650 4 $a Games. $3 525308
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
650 4 $a Information science. $3 554358
650 4 $a Mental health. $3 534751
650 4 $a Morphology. $3 591167
650 4 $a Neurosciences. $3 588700
650 4 $a Recreation. $3 535376
650 4 $a Web studies. $3 2122754
653 $a Modular Network
653 $a Neural Networks
690 $a 0389
690 $a 0800
690 $a 0984
690 $a 0723
690 $a 0347
690 $a 0287
690 $a 0317
690 $a 0814
690 $a 0646
710 2 $a National University of Singapore (Singapore). $3 3352228
773 0 $t Dissertations Abstracts International $g 83-07B.
790 $a 1883
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28832594