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

New Directions in Robust Time-Series...

Belkhouja, Taha.

FindBook

Google Book

Amazon

博客來

New Directions in Robust Time-Series Machine Learning: Theory, Algorithms, and Applications.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	New Directions in Robust Time-Series Machine Learning: Theory, Algorithms, and Applications./
作者:	Belkhouja, Taha.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2024,
面頁冊數:	275 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
標題:	Computer science. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31144157
ISBN:	9798383097816

New Directions in Robust Time-Series Machine Learning: Theory, Algorithms, and Applications.
Belkhouja, Taha.

New Directions in Robust Time-Series Machine Learning: Theory, Algorithms, and Applications. - Ann Arbor : ProQuest Dissertations & Theses, 2024 - 275 p.

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

Thesis (Ph.D.)--Washington State University, 2024.

Despite the rapid progress in research on the robustness of deep neural networks (DNNs) for images and text, there is little principled work for the time-series domain. Since timeseries data arises in diverse applications, including mobile health, finance, and smart grid, it is important to verify and improve the robustness of DNNs for the time-series domain. Safe deployment of time-series DNNs for real-world applications relies on their ability to be resilient against natural/adversarial perturbations and anomalous inputs that may affect their predictive performance. This dissertation studies the design of robust machine learning (ML) algorithms that aim to minimize both the risk and uncertainty of wrongful decisions made by time-series-based ML systems from both theoretical and algorithmic perspectives. First, we investigate the robustness against adversarial time-series inputs. Adversarial examples were shown to be successful in exposing fundamental blind spots in ML models. While adversarial examples expose how to break the models, the process of creating adversarial examples can itself improve the robustness of ML models by adding them to the training set. The time-series modality poses unique challenges for studying adversarial robustness that are not seen in images and text. The key challenge is how to assess the similarity in the time-series input space to efficiently create valid time-series adversarial examples. Second, we investigate the challenge of Out-of-Distribution (OOD) detection, where the ML system is required to identify time-series inputs that do not follow the distribution of training data. This is a critical task as deep models often make predictions that are very confident yet incorrect on such examples. Detecting OOD examples is challenging, and the potential risks are high for sensitive applications. The key challenge for time-series inputs is how to identify the features that improve the separability between OOD examples and training examples.Motivated by these goals, this dissertation proposes and evaluates a suite of novel solutions to push the frontiers of robust time-series ML: 1) The practical threats of adversarial examples to time-series ML systems; 2) The use of constraints on statistical features of the time-series data to construct adversarial examples, and providing formal robustness certificates for time-series data; 3) The use of elastic measures such as Dynamic Time Warping to quantify the similarity between time-series examples and developing theoretically-sound algorithms to efficiently construct valid adversarial examples, and to train robust ML models by explicitly solving a min-max optimization problem; 4) Adapting and applying the developed algorithms to real-world applications including wearable sensors enabled ML systems for healthcare to handle both natural perturbations and missing sensor data; and 5) A novel OOD detection algorithm based on deep generative models for the time-series domain and explain why prior OOD methods from the other domains perform poorly.

ISBN: 9798383097816Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Deep neural networks

New Directions in Robust Time-Series Machine Learning: Theory, Algorithms, and Applications.
LDR:04235nmm a2200385 4500 001 2401910
005 20241022111604.5
006 m o d
007 cr#unu||||||||
008 251215s2024 ||||||||||||||||| ||eng d
020 $a 9798383097816
035 $a (MiAaPQ)AAI31144157
035 $a AAI31144157
035 $a 2401910
040 $a MiAaPQ $c MiAaPQ
100 1 $a Belkhouja, Taha. $3 3545048
245 1 0 $a New Directions in Robust Time-Series Machine Learning: Theory, Algorithms, and Applications.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 275 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
500 $a Advisor: Doppa, Janardhan Rao.
502 $a Thesis (Ph.D.)--Washington State University, 2024.
520 $a Despite the rapid progress in research on the robustness of deep neural networks (DNNs) for images and text, there is little principled work for the time-series domain. Since timeseries data arises in diverse applications, including mobile health, finance, and smart grid, it is important to verify and improve the robustness of DNNs for the time-series domain. Safe deployment of time-series DNNs for real-world applications relies on their ability to be resilient against natural/adversarial perturbations and anomalous inputs that may affect their predictive performance. This dissertation studies the design of robust machine learning (ML) algorithms that aim to minimize both the risk and uncertainty of wrongful decisions made by time-series-based ML systems from both theoretical and algorithmic perspectives. First, we investigate the robustness against adversarial time-series inputs. Adversarial examples were shown to be successful in exposing fundamental blind spots in ML models. While adversarial examples expose how to break the models, the process of creating adversarial examples can itself improve the robustness of ML models by adding them to the training set. The time-series modality poses unique challenges for studying adversarial robustness that are not seen in images and text. The key challenge is how to assess the similarity in the time-series input space to efficiently create valid time-series adversarial examples. Second, we investigate the challenge of Out-of-Distribution (OOD) detection, where the ML system is required to identify time-series inputs that do not follow the distribution of training data. This is a critical task as deep models often make predictions that are very confident yet incorrect on such examples. Detecting OOD examples is challenging, and the potential risks are high for sensitive applications. The key challenge for time-series inputs is how to identify the features that improve the separability between OOD examples and training examples.Motivated by these goals, this dissertation proposes and evaluates a suite of novel solutions to push the frontiers of robust time-series ML: 1) The practical threats of adversarial examples to time-series ML systems; 2) The use of constraints on statistical features of the time-series data to construct adversarial examples, and providing formal robustness certificates for time-series data; 3) The use of elastic measures such as Dynamic Time Warping to quantify the similarity between time-series examples and developing theoretically-sound algorithms to efficiently construct valid adversarial examples, and to train robust ML models by explicitly solving a min-max optimization problem; 4) Adapting and applying the developed algorithms to real-world applications including wearable sensors enabled ML systems for healthcare to handle both natural perturbations and missing sensor data; and 5) A novel OOD detection algorithm based on deep generative models for the time-series domain and explain why prior OOD methods from the other domains perform poorly.
590 $a School code: 0251.
650 4 $a Computer science. $3 523869
650 4 $a Electrical engineering. $3 649834
653 $a Deep neural networks
653 $a Machine learning
653 $a Time-series domain
653 $a Robustness
690 $a 0984
690 $a 0544
690 $a 0800
710 2 $a Washington State University. $b School of Electrical Engineering and Computer Science. $3 3764368
773 0 $t Dissertations Abstracts International $g 85-12B.
790 $a 0251
791 $a Ph.D.
792 $a 2024
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31144157