國立虎尾科技大學 |

On Efficient Approaches in Neural Networks.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	On Efficient Approaches in Neural Networks./
作者:	Vysogorets, Artem.
面頁冊數:	1 online resource (171 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
標題:	Statistics. -
電子資源:	click for full text (PQDT)
ISBN:	9798383165690

On Efficient Approaches in Neural Networks.
Vysogorets, Artem.

On Efficient Approaches in Neural Networks. - 1 online resource (171 pages)

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

Thesis (Ph.D.)--New York University, 2024.

Includes bibliographical references

The great advances of Artificial Intelligence (AI) come at ever-increasing costs associated with training and inference of deep neural networks. While the technological progress presently keeps up with these extraordinary demands, we may soon reach the ceiling of feasible computational throughput. This natural impending limit calls for developing alternative, more efficient approaches to building, optimizing, deploying, and storing neural networks. To this end, the present thesis contributes to several well-established research threads that address these challenges from different perspectives. In particular, it focuses on network pruning, continual learning, active learning, network initialization, and data pruning. In their unique ways, all of these domains are concerned with reducing the computational costs associated with deep learning and promoting affordability of AI solutions, from research to end-products.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798383165690Subjects--Topical Terms:

556824
Statistics.
Subjects--Index Terms:

Deep learningIndex Terms--Genre/Form:

554714
Electronic books.

On Efficient Approaches in Neural Networks.
LDR:02219ntm a22003857 4500 001 1150159
005 20241022111603.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798383165690
035 $a (MiAaPQ)AAI31143261
035 $a AAI31143261
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Vysogorets, Artem. $3 1476594
245 1 0 $a On Efficient Approaches in Neural Networks.
264 0 $c 2024
300 $a 1 online resource (171 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: 85-12, Section: B.
500 $a Advisor: Kempe, Julia.
502 $a Thesis (Ph.D.)--New York University, 2024.
504 $a Includes bibliographical references
520 $a The great advances of Artificial Intelligence (AI) come at ever-increasing costs associated with training and inference of deep neural networks. While the technological progress presently keeps up with these extraordinary demands, we may soon reach the ceiling of feasible computational throughput. This natural impending limit calls for developing alternative, more efficient approaches to building, optimizing, deploying, and storing neural networks. To this end, the present thesis contributes to several well-established research threads that address these challenges from different perspectives. In particular, it focuses on network pruning, continual learning, active learning, network initialization, and data pruning. In their unique ways, all of these domains are concerned with reducing the computational costs associated with deep learning and promoting affordability of AI solutions, from research to end-products.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Statistics. $3 556824
650 4 $a Computer science. $3 573171
653 $a Deep learning
653 $a Efficiency
653 $a Machine learning
653 $a Neural networks
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0463
690 $a 0800
710 2 $a New York University. $b Center for Data Science. $3 1468521
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 85-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31143261 $z click for full text (PQDT)