國立虎尾科技大學 |

Improving and Unfolding Statistical Models of Nonstationary Signals.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Improving and Unfolding Statistical Models of Nonstationary Signals./
作者:	Wisdom, Scott Thomas.
面頁冊數:	1 online resource (156 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-05(E), Section: B.
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9780355594591

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

Improving and Unfolding Statistical Models of Nonstationary Signals. - 1 online resource (156 pages)

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

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

Includes bibliographical references

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.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355594591Subjects--Topical Terms:

596380
Electrical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Improving and Unfolding Statistical Models of Nonstationary Signals.
LDR:03705ntm a2200361K 4500 001 912173
005 20180608102941.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355594591
035 $a (MiAaPQ)AAI10624410
035 $a (MiAaPQ)washington:17944
035 $a AAI10624410
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Wisdom, Scott Thomas. $3 1184411
245 1 0 $a Improving and Unfolding Statistical Models of Nonstationary Signals.
264 0 $c 2017
300 $a 1 online resource (156 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
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.
504 $a Includes bibliographical references
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.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
650 4 $a Computer science. $3 573171
650 4 $a Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Washington. $b Electrical Engineering. $3 1180628
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10624410 $z click for full text (PQDT)