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

FindBook

Google Book

Amazon

博客來

Interpretable Machine Learning and Applications.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Interpretable Machine Learning and Applications./
作者:	Pan, Deng.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	100 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-12, Section: B.
Contained By:	Dissertations Abstracts International83-12B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28967204
ISBN:	9798819362525

Interpretable Machine Learning and Applications.
Pan, Deng.

Interpretable Machine Learning and Applications. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 100 p.

Source: Dissertations Abstracts International, Volume: 83-12, Section: B.

Thesis (Ph.D.)--Wayne State University, 2022.

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

Deep neural networks (DNNs) has attracted much attention in machine learning community due to its state-of-the-art performance on various tasks. Despite the successes, interpreting a complex DNN still remains an open problem, hindering its wide deployment in safety and security-critical domains. Hence understanding the interpretability and explainability of the DNNs become a critical problem in machine learning.In this dissertation, we first survey fundamental works and recent advancements in the interpretable machine learning research domain in Chapter 1. In Chapter 2, we tackle the interpretability problem in recommender systems by designing and implementing a feature mapping strategy into the recommender systems, so-called Attentive Multitask Collaborative Filtering (AMCF). We also evaluate the performance of AMCF in terms of model-level interpretability and user-level explanability. In Chapter 3, we propose a gradient based DNN interpretation strategy called Adversarial Gradient Integration (AGI) utilizing the back-propagation and adversarial effects. Decomposing a classification problem into multiple discriminating problems, we eliminates the inconsistency issues of the competing methods introduced by arbitrary baselines and selection of paths. And in Chapter 4, we propose a novel direction for DNN interpretation called gradient accumulation methods, which views the model's output as the accumulation of gradients over the input space. We also implement Negative Flux Aggregation (NeFLAG), which calculates the gradient accumulation exploiting the concept of divergence and flux in vector analysis. In Chapter 5, we conclude the dissertation by summarizing original contributions to the area of interpretable machine learning, and point out some more promising directions.

ISBN: 9798819362525Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Computer vision

Interpretable Machine Learning and Applications.
LDR:02873nmm a2200337 4500 001 2352183
005 20221118093835.5
008 241004s2022 ||||||||||||||||| ||eng d
020 $a 9798819362525
035 $a (MiAaPQ)AAI28967204
035 $a AAI28967204
040 $a MiAaPQ $c MiAaPQ
100 1 $a Pan, Deng. $0 (orcid)0000-0003-3037-8912 $3 3689978
245 1 0 $a Interpretable Machine Learning and Applications.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 100 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-12, Section: B.
500 $a Advisor: Zhu, Dongxiao.
502 $a Thesis (Ph.D.)--Wayne State University, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Deep neural networks (DNNs) has attracted much attention in machine learning community due to its state-of-the-art performance on various tasks. Despite the successes, interpreting a complex DNN still remains an open problem, hindering its wide deployment in safety and security-critical domains. Hence understanding the interpretability and explainability of the DNNs become a critical problem in machine learning.In this dissertation, we first survey fundamental works and recent advancements in the interpretable machine learning research domain in Chapter 1. In Chapter 2, we tackle the interpretability problem in recommender systems by designing and implementing a feature mapping strategy into the recommender systems, so-called Attentive Multitask Collaborative Filtering (AMCF). We also evaluate the performance of AMCF in terms of model-level interpretability and user-level explanability. In Chapter 3, we propose a gradient based DNN interpretation strategy called Adversarial Gradient Integration (AGI) utilizing the back-propagation and adversarial effects. Decomposing a classification problem into multiple discriminating problems, we eliminates the inconsistency issues of the competing methods introduced by arbitrary baselines and selection of paths. And in Chapter 4, we propose a novel direction for DNN interpretation called gradient accumulation methods, which views the model's output as the accumulation of gradients over the input space. We also implement Negative Flux Aggregation (NeFLAG), which calculates the gradient accumulation exploiting the concept of divergence and flux in vector analysis. In Chapter 5, we conclude the dissertation by summarizing original contributions to the area of interpretable machine learning, and point out some more promising directions.
590 $a School code: 0254.
650 4 $a Computer science. $3 523869
653 $a Computer vision
653 $a Interpretable machine learning
653 $a Machine learning
653 $a Recommender system
690 $a 0984
710 2 $a Wayne State University. $b Computer Science. $3 1030863
773 0 $t Dissertations Abstracts International $g 83-12B.
790 $a 0254
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28967204