東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

Learning How and Why: Causal Learning and Explanation from Physical, Interactive, and Communicative Environments.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Learning How and Why: Causal Learning and Explanation from Physical, Interactive, and Communicative Environments./
Author:	Edmonds, Mark Joseph.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
Description:	142 p.
Notes:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
Subject:	Artificial intelligence. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28718910
ISBN:	9798538140039

Learning How and Why: Causal Learning and Explanation from Physical, Interactive, and Communicative Environments.
Edmonds, Mark Joseph.

Learning How and Why: Causal Learning and Explanation from Physical, Interactive, and Communicative Environments. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 142 p.

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

Thesis (Ph.D.)--University of California, Los Angeles, 2021.

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

Artificial agents expected to operate alongside humans in daily life will be expected to handle novel circumstances and explain their behavior to humans. In this dissertation, we examine these two concepts from the perspective of generalization and explanation. Generalization relies on having a learning algorithm capable of performing well in unseen circumstances and updating the model to handle the novel circumstance. In practice, learning algorithms must be equipped with mechanisms that enable generalization. Here, we examine the generalization question from multiple perspectives, namely imitation learning and causal learning. We show that generalization performance benefits from understanding abstract high-level task structure and low-level perceptual inductive biases. We also examine explanations in imitation learning and communicative learning paradigms. These explanations are intended to foster human trust and address the value alignment problem between humans and machines. In the imitation learning setting, we show that the model components that best contribute to fostering human trust do not necessarily correspond to the model components contributing most to task performance. In the communicative learning paradigm, we show how theory of mind can align a machine's values to the preferences of a human user. Taken together, this dissertation helps address two of the most critical problems facing AI systems today: machine performance in unseen scenarios and human-machine trust.

ISBN: 9798538140039Subjects--Topical Terms:

516317
Artificial intelligence.
Subjects--Index Terms:

Causal learning

Learning How and Why: Causal Learning and Explanation from Physical, Interactive, and Communicative Environments.
LDR:02715nmm a2200373 4500 001 2348642
005 20220912135625.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798538140039
035 $a (MiAaPQ)AAI28718910
035 $a AAI28718910
040 $a MiAaPQ $c MiAaPQ
100 1 $a Edmonds, Mark Joseph. $3 3284676
245 1 0 $a Learning How and Why: Causal Learning and Explanation from Physical, Interactive, and Communicative Environments.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 142 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Zhu, Song-Chun.
502 $a Thesis (Ph.D.)--University of California, Los Angeles, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Artificial agents expected to operate alongside humans in daily life will be expected to handle novel circumstances and explain their behavior to humans. In this dissertation, we examine these two concepts from the perspective of generalization and explanation. Generalization relies on having a learning algorithm capable of performing well in unseen circumstances and updating the model to handle the novel circumstance. In practice, learning algorithms must be equipped with mechanisms that enable generalization. Here, we examine the generalization question from multiple perspectives, namely imitation learning and causal learning. We show that generalization performance benefits from understanding abstract high-level task structure and low-level perceptual inductive biases. We also examine explanations in imitation learning and communicative learning paradigms. These explanations are intended to foster human trust and address the value alignment problem between humans and machines. In the imitation learning setting, we show that the model components that best contribute to fostering human trust do not necessarily correspond to the model components contributing most to task performance. In the communicative learning paradigm, we show how theory of mind can align a machine's values to the preferences of a human user. Taken together, this dissertation helps address two of the most critical problems facing AI systems today: machine performance in unseen scenarios and human-machine trust.
590 $a School code: 0031.
650 4 $a Artificial intelligence. $3 516317
650 4 $a Accuracy. $3 3559958
650 4 $a Computer science. $3 523869
650 4 $a Human performance. $3 3562051
650 4 $a Experiments. $3 525909
650 4 $a Knowledge. $3 872758
650 4 $a Sensors. $3 3549539
650 4 $a Medical research. $2 bicssc $3 1556686
650 4 $a Robots. $3 529507
650 4 $a Copyright. $3 601694
650 4 $a Computer engineering. $3 621879
650 4 $a Data collection. $3 3561708
650 4 $a Probability. $3 518898
650 4 $a Friendship. $3 611043
650 4 $a Radiation. $3 673904
650 4 $a Human subjects. $3 3562959
650 4 $a Cognition & reasoning. $3 3556293
650 4 $a Interfaces. $2 gtt $3 834756
650 4 $a Robotics. $3 519753
653 $a Causal learning
653 $a Communicative learning
653 $a Imitation learning
653 $a Machine learning
690 $a 0800
690 $a 0771
690 $a 0984
690 $a 0464
710 2 $a University of California, Los Angeles. $b Computer Science 0201. $3 2049859
773 0 $t Dissertations Abstracts International $g 83-03B.
790 $a 0031
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28718910