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

Unitary Neural Networks.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Unitary Neural Networks./
作者:	Chang, Hao-Yuan.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	134 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-12, Section: B.
Contained By:	Dissertations Abstracts International83-12B.
標題:	Artificial intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29215036
ISBN:	9798802725825

Unitary Neural Networks.
Chang, Hao-Yuan.

Unitary Neural Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 134 p.

Source: Dissertations Abstracts International, Volume: 83-12, Section: B.

Thesis (Ph.D.)--University of California, Los Angeles, 2022.

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

This doctoral dissertation is a comprehensive study on a novel method based on unitary synaptic weights to construct intrinsically stable neural systems. By eliminating the need to normalize neural activations, unitary neural networks deliver faster inference speeds and smaller model sizes while maintaining competitive accuracies for image recognition. In addition, unitary networks are drastically more robust against adversarial attacks in natural language processing systems because unitary weights are resilient to small input perturbations. The last portion focuses on a small demo that implements unitary neural nets in quantum computing. With the comprehensive performance evaluation in classical machine learning, the rigorous framework in mathematics, and the exploration of quantum computing, this dissertation establishes a solid foundation for unitary neural networks in the future of deep learning.

ISBN: 9798802725825Subjects--Topical Terms:

516317
Artificial intelligence.
Subjects--Index Terms:

Artificial Intelligence

Unitary Neural Networks.
LDR:02080nmm a2200385 4500 001 2351651
005 20221107090149.5
008 241004s2022 ||||||||||||||||| ||eng d
020 $a 9798802725825
035 $a (MiAaPQ)AAI29215036
035 $a AAI29215036
040 $a MiAaPQ $c MiAaPQ
100 1 $a Chang, Hao-Yuan. $3 3691221
245 1 0 $a Unitary Neural Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 134 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-12, Section: B.
500 $a Advisor: Wang, Kang L.
502 $a Thesis (Ph.D.)--University of California, Los Angeles, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a This doctoral dissertation is a comprehensive study on a novel method based on unitary synaptic weights to construct intrinsically stable neural systems. By eliminating the need to normalize neural activations, unitary neural networks deliver faster inference speeds and smaller model sizes while maintaining competitive accuracies for image recognition. In addition, unitary networks are drastically more robust against adversarial attacks in natural language processing systems because unitary weights are resilient to small input perturbations. The last portion focuses on a small demo that implements unitary neural nets in quantum computing. With the comprehensive performance evaluation in classical machine learning, the rigorous framework in mathematics, and the exploration of quantum computing, this dissertation establishes a solid foundation for unitary neural networks in the future of deep learning.
590 $a School code: 0031.
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
650 4 $a Quantum physics. $3 726746
653 $a Artificial Intelligence
653 $a Lie group
653 $a Machine learning
653 $a Natural language processing
653 $a Neural networks
653 $a Quantum computing
690 $a 0800
690 $a 0984
690 $a 0599
710 2 $a University of California, Los Angeles. $b Electrical and Computer Engineering 0333. $3 3542511
773 0 $t Dissertations Abstracts International $g 83-12B.
790 $a 0031
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29215036