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

Improving and Unfolding Statistical ...

Wisdom, Scott Thomas.

FindBook

Google Book

Amazon

博客來

Improving and Unfolding Statistical Models of Nonstationary Signals.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Improving and Unfolding Statistical Models of Nonstationary Signals./
作者:	Wisdom, Scott Thomas.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
面頁冊數:	156 p.
附註:	Source: Dissertation Abstracts International, Volume: 79-05(E), Section: B.
Contained By:	Dissertation Abstracts International79-05B(E).
標題:	Electrical engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10624410
ISBN:	9780355594591

Improving and Unfolding Statistical Models of Nonstationary Signals.
Wisdom, Scott Thomas.

Improving and Unfolding Statistical Models of Nonstationary Signals. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 156 p.

Source: Dissertation Abstracts International, Volume: 79-05(E), Section: B.

Thesis (Ph.D.)--University of Washington, 2017.

Improving the modeling and processing of nonstationary signals remains an important yet challenging problem. In the past, the most effective approach for processing these signals has been statistical modeling. Statistical models can effectively encode domain knowledge and lead to principled algorithms for the fundamental tasks of enhancement, detection, and classification. However, the performance of statistical models can be limited because they inherently make assumptions about the distribution of the data. Deep neural networks, in contrast, have recently outperformed state-of-the-art statistical models of nonstationary signals. Deep neural networks are completely data-driven, and learn to set their parameters by training on large datasets that are assumed to match the distribution of the data.

ISBN: 9780355594591Subjects--Topical Terms:

649834
Electrical engineering.

Improving and Unfolding Statistical Models of Nonstationary Signals.
LDR:03492nmm a2200337 4500 001 2157656
005 20180608102941.5
008 190424s2017 ||||||||||||||||| ||eng d
020 $a 9780355594591
035 $a (MiAaPQ)AAI10624410
035 $a (MiAaPQ)washington:17944
035 $a AAI10624410
040 $a MiAaPQ $c MiAaPQ
100 1 $a Wisdom, Scott Thomas. $3 3171142
245 1 0 $a Improving and Unfolding Statistical Models of Nonstationary Signals.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 156 p.
500 $a Source: Dissertation Abstracts International, Volume: 79-05(E), Section: B.
500 $a Advisers: Les Atlas; James Pitton.
502 $a Thesis (Ph.D.)--University of Washington, 2017.
520 $a Improving the modeling and processing of nonstationary signals remains an important yet challenging problem. In the past, the most effective approach for processing these signals has been statistical modeling. Statistical models can effectively encode domain knowledge and lead to principled algorithms for the fundamental tasks of enhancement, detection, and classification. However, the performance of statistical models can be limited because they inherently make assumptions about the distribution of the data. Deep neural networks, in contrast, have recently outperformed state-of-the-art statistical models of nonstationary signals. Deep neural networks are completely data-driven, and learn to set their parameters by training on large datasets that are assumed to match the distribution of the data.
520 $a This dissertation follows two approaches for improving modeling and processing of nonstationary signals. The first approach examines conventional model assumptions and suggests improvements that lead to improved performance for processing nonstationary signals. Specifically, noncircular distributions of the complex-valued short-time Fourier transform are shown to improve detection of realistic nonstationary signals. Then the parameterization of a recently-proposed recurrent neural network for processing nonstationary signals is reexamined. By using an optimization method that preserves the capacity of the recurrence matrix, superior performance is achieved on a battery of benchmarks that test the ability of recurrent neural networks to process nonstationary signals.
520 $a The second approach uses the recently-proposed framework of deep unfolding, which provides a principled means of transforming statistical model inference algorithms into deep networks. This dissertation expands the deep unfolding framework specifically for nonstationary signals. Using this framework, a model-based explanation is provided for state-of-the-art recurrent neural architectures, including gated recurrent unit and unitary recurrent neural networks. Additionally, deep unfolding results in deep network architectures that arise in principled ways from statistical model assumptions. This statistical model foundation provides initializations for the unfolded networks, which lead to better generalization, faster training, and competitive or superior performance on a variety of tasks, including single- and multichannel acoustic source separation and classification of acoustic signals.
590 $a School code: 0250.
650 4 $a Electrical engineering. $3 649834
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
690 $a 0544
690 $a 0984
690 $a 0800
710 2 $a University of Washington. $b Electrical Engineering. $3 2102369
773 0 $t Dissertation Abstracts International $g 79-05B(E).
790 $a 0250
791 $a Ph.D.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10624410