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

Automatic Designs in Deep Neural Net...

Liu, Lanlan.

FindBook

Google Book

Amazon

博客來

Automatic Designs in Deep Neural Networks.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Automatic Designs in Deep Neural Networks./
作者:	Liu, Lanlan.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	129 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-07, Section: B.
Contained By:	Dissertations Abstracts International82-07B.
標題:	Design. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28240180
ISBN:	9798684619502

Automatic Designs in Deep Neural Networks.
Liu, Lanlan.

Automatic Designs in Deep Neural Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 129 p.

Source: Dissertations Abstracts International, Volume: 82-07, Section: B.

Thesis (Ph.D.)--University of Michigan, 2020.

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

To train a Deep Neural Network (DNN) that performs well for a task, many design steps are taken including data designs, model designs and loss designs. Despite that remarkable progress has been made in all these domains of designing DNNs, the unexplored design space of each component is still vast. That brings the research field of developing automated techniques to lift some heavy work from human researchers when exploring the design space. The automated designs can help human researchers to make massive or challenging design choices and reduce the expertise required from human researchers.Much effort has been made towards automated designs of DNNs, including synthetic data generation, automated data augmentation, neural architecture search and so on.Despite the huge effort, the automation of DNN designs is still far from complete. This thesis contributes in two ways: identifying new problems in the DNN design pipeline that can be solved automatically, and proposing new solutions to problems that have been explored by automated designs.The first part of this thesis presents two problems that were usually solved with manual designs but can benefit from automated designs. To tackle the problem of inefficient computation due to using a static DNN architecture for different inputs, some manual efforts have been made to use different networks for different inputs as needed, such as cascade models. We propose an automated dynamic inference framework that can cut this manual effort and automatically choose different architectures for different inputs during inference.To tackle the problem of designing differentiable loss functions for non-differentiable performance metrics, researchers usually design the loss manually for each individual task.We propose an unified loss framework that reduces the amount of manual design of losses in different tasks. The second part of this thesis discusses developing new techniques in domains where the automated design has been shown effective.In the synthetic data generation domain, we propose a novel method to automatically generate synthetic data for small-data object detection. The synthetic data generated can amend the limited annotated real data of the small-data object detection tasks, such as rare disease detection.In the architecture search domain, we propose an architecture search method customized for generative adversarial networks (GANs). GANs are commonly known unstable to train where we propose this new method that can stabilize the training of GANs in the architecture search process.

ISBN: 9798684619502Subjects--Topical Terms:

518875
Design.
Subjects--Index Terms:

Computer vision

Automatic Designs in Deep Neural Networks.
LDR:03904nmm a2200433 4500 001 2282149
005 20211001100709.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798684619502
035 $a (MiAaPQ)AAI28240180
035 $a (MiAaPQ)umichrackham003249
035 $a AAI28240180
040 $a MiAaPQ $c MiAaPQ
100 1 $a Liu, Lanlan. $3 3560906
245 1 0 $a Automatic Designs in Deep Neural Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 129 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-07, Section: B.
500 $a Advisor: Baveja, Satinder Singh;Deng, Jia.
502 $a Thesis (Ph.D.)--University of Michigan, 2020.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
520 $a To train a Deep Neural Network (DNN) that performs well for a task, many design steps are taken including data designs, model designs and loss designs. Despite that remarkable progress has been made in all these domains of designing DNNs, the unexplored design space of each component is still vast. That brings the research field of developing automated techniques to lift some heavy work from human researchers when exploring the design space. The automated designs can help human researchers to make massive or challenging design choices and reduce the expertise required from human researchers.Much effort has been made towards automated designs of DNNs, including synthetic data generation, automated data augmentation, neural architecture search and so on.Despite the huge effort, the automation of DNN designs is still far from complete. This thesis contributes in two ways: identifying new problems in the DNN design pipeline that can be solved automatically, and proposing new solutions to problems that have been explored by automated designs.The first part of this thesis presents two problems that were usually solved with manual designs but can benefit from automated designs. To tackle the problem of inefficient computation due to using a static DNN architecture for different inputs, some manual efforts have been made to use different networks for different inputs as needed, such as cascade models. We propose an automated dynamic inference framework that can cut this manual effort and automatically choose different architectures for different inputs during inference.To tackle the problem of designing differentiable loss functions for non-differentiable performance metrics, researchers usually design the loss manually for each individual task.We propose an unified loss framework that reduces the amount of manual design of losses in different tasks. The second part of this thesis discusses developing new techniques in domains where the automated design has been shown effective.In the synthetic data generation domain, we propose a novel method to automatically generate synthetic data for small-data object detection. The synthetic data generated can amend the limited annotated real data of the small-data object detection tasks, such as rare disease detection.In the architecture search domain, we propose an architecture search method customized for generative adversarial networks (GANs). GANs are commonly known unstable to train where we propose this new method that can stabilize the training of GANs in the architecture search process.
590 $a School code: 0127.
650 4 $a Design. $3 518875
650 4 $a Computer science. $3 523869
650 4 $a Technical communication. $3 3172863
650 4 $a Information technology. $3 532993
650 4 $a Artificial intelligence. $3 516317
650 4 $a Information science. $3 554358
653 $a Computer vision
653 $a Machine learning
653 $a Deep neural networks
653 $a Automated data
653 $a Manual designs
690 $a 0984
690 $a 0389
690 $a 0643
690 $a 0489
690 $a 0723
690 $a 0800
710 2 $a University of Michigan. $b Computer Science & Engineering. $3 3285590
773 0 $t Dissertations Abstracts International $g 82-07B.
790 $a 0127
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28240180