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

Large-scale Optimization and Deep Le...

DeGuchy, Omar.

FindBook

Google Book

Amazon

博客來

Large-scale Optimization and Deep Learning Techniques for Data-driven Signal Processing.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Large-scale Optimization and Deep Learning Techniques for Data-driven Signal Processing./
作者:	DeGuchy, Omar.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	165 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-01, Section: B.
Contained By:	Dissertations Abstracts International82-01B.
標題:	Mathematics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27962575
ISBN:	9798662406308

Large-scale Optimization and Deep Learning Techniques for Data-driven Signal Processing.
DeGuchy, Omar.

Large-scale Optimization and Deep Learning Techniques for Data-driven Signal Processing. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 165 p.

Source: Dissertations Abstracts International, Volume: 82-01, Section: B.

Thesis (Ph.D.)--University of California, Merced, 2020.

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

The collection of data has become an integral part of our everyday lives. The algorithms necessary to process this information become paramount to our ability to interpret this resource. This type of data is typically recorded in a variety of signals including images, sounds, time series, and bio-informatics. In this work, we develop a number of algorithms to recover these types of signals in a variety of modalities. This work is mainly presented in two parts.Initially, we apply and develop large-scale optimization techniques used for signal processing. This includes the use of quasi-Newton methods to approximate second derivative information in a trust-region setting to solve regularized sparse signal recovery problems. We also formulate the compact representation of a large family of quasi-Newton methods known as the Broyden class. This extension of the classic quasi-Newton compact representation allows different updates to be used at every iteration. We also develop the algorithm to perform efficient solves with these representations. Within the realm of sparse signal recovery, but particular to photon-limited imaging applications, we also propose three novel algorithms for signal recovery in a low-light regime. First, we recover the support and lifetime decay of a flourophore from time dependent measurements. This type of modality is useful in identifying different types of molecular structures in tissue samples. The second algorithm identifies and implements the Shannon entropy function as a regularization technique for the promotion of sparsity in reconstructed signals from noisy downsampled observations. Finally, we also present an algorithm which addresses the difficulty of choosing the optimal parameters when solving the sparse signal recovery problem. There are two parameters which effect the quality of the reconstruction, the norm being used, as well as the intensity of the penalization imposed by that norm. We present an algorithm which uses a parallel asynchronous search along with a metric in order to find the optimal pair.The second portion of the dissertation draws on our experience with large-scale optimization and looks towards deep learning as an alternative to solving signal recovery problems. We first look to improve the standard gradient based techniques used during the training of these deep neural networks by presenting two novel optimization algorithms for deep learning. The first algorithm takes advantage of the limited memory Broyden-Fletcher-Goldfarb-Shanno (BFGS) quasi-Newton algorithm in a trust-region setting in order to address the large scale minimization problem associated with deep learning. The second algorithm uses second derivative information in a trust region setting where the Hessian is not explicitly stored. We then use a conjugate based method in order to solve the trust-region subproblem.Finally, we apply deep learning techniques to a variety of applications in signal recovery. These applications include revisiting the photon-limited regime where we recover signals from noisy downsampled observations, image disambiguation which involves the recovery of two signals which have been superimposed, deep learning for synthetic aperture radar (SAR) where we recover information describing the imaging system as well as evaluate the impact of reconstruction on the ability to perform target detection, and signal variation detection in the human genome where we leverage the relationships between subjects to provide better detection.

ISBN: 9798662406308Subjects--Topical Terms:

515831
Mathematics.
Subjects--Index Terms:

Deep learning

Large-scale Optimization and Deep Learning Techniques for Data-driven Signal Processing.
LDR:04708nmm a2200373 4500 001 2271798
005 20201030112753.5
008 220629s2020 ||||||||||||||||| ||eng d
020 $a 9798662406308
035 $a (MiAaPQ)AAI27962575
035 $a AAI27962575
040 $a MiAaPQ $c MiAaPQ
100 1 $a DeGuchy, Omar. $3 3549213
245 1 0 $a Large-scale Optimization and Deep Learning Techniques for Data-driven Signal Processing.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 165 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-01, Section: B.
500 $a Advisor: Marcia, Roummel F.
502 $a Thesis (Ph.D.)--University of California, Merced, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a The collection of data has become an integral part of our everyday lives. The algorithms necessary to process this information become paramount to our ability to interpret this resource. This type of data is typically recorded in a variety of signals including images, sounds, time series, and bio-informatics. In this work, we develop a number of algorithms to recover these types of signals in a variety of modalities. This work is mainly presented in two parts.Initially, we apply and develop large-scale optimization techniques used for signal processing. This includes the use of quasi-Newton methods to approximate second derivative information in a trust-region setting to solve regularized sparse signal recovery problems. We also formulate the compact representation of a large family of quasi-Newton methods known as the Broyden class. This extension of the classic quasi-Newton compact representation allows different updates to be used at every iteration. We also develop the algorithm to perform efficient solves with these representations. Within the realm of sparse signal recovery, but particular to photon-limited imaging applications, we also propose three novel algorithms for signal recovery in a low-light regime. First, we recover the support and lifetime decay of a flourophore from time dependent measurements. This type of modality is useful in identifying different types of molecular structures in tissue samples. The second algorithm identifies and implements the Shannon entropy function as a regularization technique for the promotion of sparsity in reconstructed signals from noisy downsampled observations. Finally, we also present an algorithm which addresses the difficulty of choosing the optimal parameters when solving the sparse signal recovery problem. There are two parameters which effect the quality of the reconstruction, the norm being used, as well as the intensity of the penalization imposed by that norm. We present an algorithm which uses a parallel asynchronous search along with a metric in order to find the optimal pair.The second portion of the dissertation draws on our experience with large-scale optimization and looks towards deep learning as an alternative to solving signal recovery problems. We first look to improve the standard gradient based techniques used during the training of these deep neural networks by presenting two novel optimization algorithms for deep learning. The first algorithm takes advantage of the limited memory Broyden-Fletcher-Goldfarb-Shanno (BFGS) quasi-Newton algorithm in a trust-region setting in order to address the large scale minimization problem associated with deep learning. The second algorithm uses second derivative information in a trust region setting where the Hessian is not explicitly stored. We then use a conjugate based method in order to solve the trust-region subproblem.Finally, we apply deep learning techniques to a variety of applications in signal recovery. These applications include revisiting the photon-limited regime where we recover signals from noisy downsampled observations, image disambiguation which involves the recovery of two signals which have been superimposed, deep learning for synthetic aperture radar (SAR) where we recover information describing the imaging system as well as evaluate the impact of reconstruction on the ability to perform target detection, and signal variation detection in the human genome where we leverage the relationships between subjects to provide better detection.
590 $a School code: 1660.
650 4 $a Mathematics. $3 515831
650 4 $a Computer science. $3 523869
650 4 $a Medical imaging. $3 3172799
653 $a Deep learning
653 $a Image processing
653 $a Machine learning
653 $a Medical imaging
653 $a Optimization
690 $a 0405
690 $a 0984
690 $a 0574
710 2 $a University of California, Merced. $b Applied Mathematics. $3 2096524
773 0 $t Dissertations Abstracts International $g 82-01B.
790 $a 1660
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27962575