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 到查詢結果 [ author_sort:"liu, feng." ]

切換: 標籤 | MARC模式 | ISBD

Meta-learning and Ensemble Methods f...

liu, feng.

FindBook

Google Book

Amazon

博客來

Meta-learning and Ensemble Methods for Deep Neural Networks.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Meta-learning and Ensemble Methods for Deep Neural Networks./
作者:	liu, feng.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	127 p.
附註:	Source: Dissertations Abstracts International, Volume: 81-12, Section: B.
Contained By:	Dissertations Abstracts International81-12B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27961423
ISBN:	9798641818467

Meta-learning and Ensemble Methods for Deep Neural Networks.
liu, feng.

Meta-learning and Ensemble Methods for Deep Neural Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 127 p.

Source: Dissertations Abstracts International, Volume: 81-12, Section: B.

Thesis (Ph.D.)--Florida Atlantic University, 2020.

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

Deep Neural Networks have been widely applied in many different applications and achieve significant improvement over classical machine learning techniques. However, training a neural network usually requires large amount of data, which is not guaranteed in some applications such as medical image classification. To address this issue, people propose to implement meta learning and ensemble learning techniques to make deep learning trainers more powerful. This thesis focuses on using deep learning equipped with meta learning and ensemble learning to study specific problems. In the first part, we consider the suggestion mining problems and apply the ensemble method, Random Multi-model Deep Learning (RMDL). In the second part, we propose a new meta-learning method-named HARMLESS (Hawkes Relational Meta Learning method for Short Sequences) for learning heterogeneous point process models from short event sequence data along with a relational network. In the third part, we propose two generic ensemble approaches, gradient boosting and meta-learning, to solve the catastrophic forgetting problem in tuning pre-trained neural network models. Numerical experiments on multiple datasets are presented to justify the good performance of our methods.

ISBN: 9798641818467Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Deep learning

Meta-learning and Ensemble Methods for Deep Neural Networks.
LDR:02310nmm a2200337 4500 001 2274471
005 20201202125033.5
008 220629s2020 ||||||||||||||||| ||eng d
020 $a 9798641818467
035 $a (MiAaPQ)AAI27961423
035 $a AAI27961423
040 $a MiAaPQ $c MiAaPQ
100 1 $a liu, feng. $3 3551962
245 1 0 $a Meta-learning and Ensemble Methods for Deep Neural Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 127 p.
500 $a Source: Dissertations Abstracts International, Volume: 81-12, Section: B.
500 $a Advisor: Wang, Dingding.
502 $a Thesis (Ph.D.)--Florida Atlantic University, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Deep Neural Networks have been widely applied in many different applications and achieve significant improvement over classical machine learning techniques. However, training a neural network usually requires large amount of data, which is not guaranteed in some applications such as medical image classification. To address this issue, people propose to implement meta learning and ensemble learning techniques to make deep learning trainers more powerful. This thesis focuses on using deep learning equipped with meta learning and ensemble learning to study specific problems. In the first part, we consider the suggestion mining problems and apply the ensemble method, Random Multi-model Deep Learning (RMDL). In the second part, we propose a new meta-learning method-named HARMLESS (Hawkes Relational Meta Learning method for Short Sequences) for learning heterogeneous point process models from short event sequence data along with a relational network. In the third part, we propose two generic ensemble approaches, gradient boosting and meta-learning, to solve the catastrophic forgetting problem in tuning pre-trained neural network models. Numerical experiments on multiple datasets are presented to justify the good performance of our methods.
590 $a School code: 0119.
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
653 $a Deep learning
653 $a Ensemble method
653 $a Meta-learning
690 $a 0984
690 $a 0800
710 2 $a Florida Atlantic University. $b Computer Science. $3 3184790
773 0 $t Dissertations Abstracts International $g 81-12B.
790 $a 0119
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27961423