國立虎尾科技大學 |

Beyond Text : = Applying Deep Learning to Signal Data.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Beyond Text :/
其他題名:	Applying Deep Learning to Signal Data.
作者:	Karan Goel.
面頁冊數:	1 online resource (153 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
標題:	Computer engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9798382232119

Beyond Text : = Applying Deep Learning to Signal Data.
Karan Goel.

Beyond Text :Applying Deep Learning to Signal Data. - 1 online resource (153 pages)

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

Thesis (Ph.D.)--Stanford University, 2024.

Includes bibliographical references

Sequence modeling primitives have been responsible for breakthroughs across domains like natural language processing and genomics. Despite these advances, existing primitives still struggle to model the large class of signal data acquired from physical sensors. This data has unique characteristics that make it challenging to model: signal data resolution affects the training and generalization of models, signal data is sampled at high rates, resulting in dense data with long-range dependencies, and signal data is highly diverse, with application areas including healthcare, video processing, and industrial sensing. All of these properties raise the bar for universal approaches to modeling this data. This thesis develops a new set of approaches for modeling signal data using state space models. First, we introduce a sequence model called S4 that serves as a general building block for modeling signal data. Second, we generalize this modeling layer to multidimensional signals like images and videos, yielding the first state-of-the-art signal model on large-scale benchmarks such as ImageNet. Incorporating S4 into a multiscale architecture makes it possible to model extremely long sequences of audio, including on a previously unsolved task involving unconditional autoregressive generation of raw audio samples. Finally, we demonstrate the widespread applicability of our approach to a variety of signal data, including a real-world application involving impedance sensor data used in the diagnosis of gastroesophageal reflux disease. Taken together, this new set of approaches provides a universal and versatile set of primitives for modeling diverse, multidimensional signals.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798382232119Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Sequence modeling primitivesIndex Terms--Genre/Form:

554714
Electronic books.

Beyond Text : = Applying Deep Learning to Signal Data.
LDR:03021ntm a22003737 4500 001 1151264
005 20241104055841.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382232119
035 $a (MiAaPQ)AAI31255665
035 $a (MiAaPQ)qb603fk1926
035 $a AAI31255665
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Karan Goel. $3 1477997
245 1 0 $a Beyond Text : $b Applying Deep Learning to Signal Data.
264 0 $c 2024
300 $a 1 online resource (153 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: Dissertations Abstracts International, Volume: 85-11, Section: B.
500 $a Advisor: Re, Christopher.
502 $a Thesis (Ph.D.)--Stanford University, 2024.
504 $a Includes bibliographical references
520 $a Sequence modeling primitives have been responsible for breakthroughs across domains like natural language processing and genomics. Despite these advances, existing primitives still struggle to model the large class of signal data acquired from physical sensors. This data has unique characteristics that make it challenging to model: signal data resolution affects the training and generalization of models, signal data is sampled at high rates, resulting in dense data with long-range dependencies, and signal data is highly diverse, with application areas including healthcare, video processing, and industrial sensing. All of these properties raise the bar for universal approaches to modeling this data. This thesis develops a new set of approaches for modeling signal data using state space models. First, we introduce a sequence model called S4 that serves as a general building block for modeling signal data. Second, we generalize this modeling layer to multidimensional signals like images and videos, yielding the first state-of-the-art signal model on large-scale benchmarks such as ImageNet. Incorporating S4 into a multiscale architecture makes it possible to model extremely long sequences of audio, including on a previously unsolved task involving unconditional autoregressive generation of raw audio samples. Finally, we demonstrate the widespread applicability of our approach to a variety of signal data, including a real-world application involving impedance sensor data used in the diagnosis of gastroesophageal reflux disease. Taken together, this new set of approaches provides a universal and versatile set of primitives for modeling diverse, multidimensional signals.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 569006
650 4 $a Information technology. $3 559429
653 $a Sequence modeling primitives
653 $a Natural language processing
653 $a Multidimensional signals
655 7 $a Electronic books. $2 local $3 554714
690 $a 0489
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Stanford University. $3 1184533
773 0 $t Dissertations Abstracts International $g 85-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31255665 $z click for full text (PQDT)