國立虎尾科技大學 |

A Unified Framework with Benchmarks for Human-Like Visual and Relational Reasoning in the Real World.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	A Unified Framework with Benchmarks for Human-Like Visual and Relational Reasoning in the Real World./
作者:	Ma, Xiaojian.
面頁冊數:	1 online resource (204 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-11, Section: B.
Contained By:	Dissertations Abstracts International84-11B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798379523497

A Unified Framework with Benchmarks for Human-Like Visual and Relational Reasoning in the Real World.
Ma, Xiaojian.

A Unified Framework with Benchmarks for Human-Like Visual and Relational Reasoning in the Real World. - 1 online resource (204 pages)

Source: Dissertations Abstracts International, Volume: 84-11, Section: B.

Thesis (Ph.D.)--University of California, Los Angeles, 2023.

Includes bibliographical references

Cogito, ergo sum. Building machines that can think and reason like humans is a longstanding goal of AI. Despite the tremendous progress in AI we witnessed in recent years, it is still not clear whether these learning machines at scale can solve problems that require sophisticated thinking and reasoning, especially when the problems are also tied to ontologies (entities, relations) in the real world and raw sensory observations, i.e. visual and relational reasoning. Further, human-level reasoning and thinking also call for the capability of generalizing what the machine has learned to problem instances with their novel forms and combinations. We anticipate such generalization should be possible even with few data as well as on diverse modalities, e.g. vision, text, embodied 3D scenes, etc, which creates a significant gap between humans and machines.This dissertation studies human-like visual and relational reasoning in the real world, aiming at closing the aforementioned gap between humans and machines. The first part of this thesis focuses on deepening the current understanding of the limitations of existing ML-based reasoning systems when compared to humans. To this end, a series of benchmarks are developed in hope of examining the full spectrum of anticipated capabilities of these systems, including zero-shot, few-shot generalization, and adaptation to difficult modalities including embodied 3D scenes. Based off these new quests for AI reasoning, thorough evaluations are conducted with recently proposed reasoning systems, and their limitations are discussed.The second part of this dissertation introduces a unified framework by drawing inspiration from the human language system, which is grounded, entity-centric, semantically rich, and could be the key to human-level generalization in reasoning [Fod75, Cho06, And18]. Specifically, the problem of learning language-like representations from a generative learning perspective is investigated. The resulting models can facilitate learning object-centric representations from images and discrete-continuous hybrid representations from text using an energy-based formulation. Further, intuitive and scalable inductive biases are developed to leverage the semantic supervision from the English language to learn object-centric and relational representations, to directly tackle the challenging zero-shot systematic generalization problem in visual and relational reasoning. Finally, what could be the next major move in the field is highlighted.

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

Mode of access: World Wide Web

ISBN: 9798379523497Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Human-like visualIndex Terms--Genre/Form:

554714
Electronic books.

A Unified Framework with Benchmarks for Human-Like Visual and Relational Reasoning in the Real World.
LDR:03911ntm a22003857 4500 001 1146386
005 20240812064602.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379523497
035 $a (MiAaPQ)AAI30487400
035 $a AAI30487400
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Ma, Xiaojian. $3 1471769
245 1 2 $a A Unified Framework with Benchmarks for Human-Like Visual and Relational Reasoning in the Real World.
264 0 $c 2023
300 $a 1 online resource (204 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: 84-11, Section: B.
500 $a Advisor: Zhu, Song-Chun.
502 $a Thesis (Ph.D.)--University of California, Los Angeles, 2023.
504 $a Includes bibliographical references
520 $a Cogito, ergo sum. Building machines that can think and reason like humans is a longstanding goal of AI. Despite the tremendous progress in AI we witnessed in recent years, it is still not clear whether these learning machines at scale can solve problems that require sophisticated thinking and reasoning, especially when the problems are also tied to ontologies (entities, relations) in the real world and raw sensory observations, i.e. visual and relational reasoning. Further, human-level reasoning and thinking also call for the capability of generalizing what the machine has learned to problem instances with their novel forms and combinations. We anticipate such generalization should be possible even with few data as well as on diverse modalities, e.g. vision, text, embodied 3D scenes, etc, which creates a significant gap between humans and machines.This dissertation studies human-like visual and relational reasoning in the real world, aiming at closing the aforementioned gap between humans and machines. The first part of this thesis focuses on deepening the current understanding of the limitations of existing ML-based reasoning systems when compared to humans. To this end, a series of benchmarks are developed in hope of examining the full spectrum of anticipated capabilities of these systems, including zero-shot, few-shot generalization, and adaptation to difficult modalities including embodied 3D scenes. Based off these new quests for AI reasoning, thorough evaluations are conducted with recently proposed reasoning systems, and their limitations are discussed.The second part of this dissertation introduces a unified framework by drawing inspiration from the human language system, which is grounded, entity-centric, semantically rich, and could be the key to human-level generalization in reasoning [Fod75, Cho06, And18]. Specifically, the problem of learning language-like representations from a generative learning perspective is investigated. The resulting models can facilitate learning object-centric representations from images and discrete-continuous hybrid representations from text using an energy-based formulation. Further, intuitive and scalable inductive biases are developed to leverage the semantic supervision from the English language to learn object-centric and relational representations, to directly tackle the challenging zero-shot systematic generalization problem in visual and relational reasoning. Finally, what could be the next major move in the field is highlighted.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
653 $a Human-like visual
653 $a Relational reasoning
653 $a Real world
653 $a 3D scenes
653 $a Learn object-centric
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Los Angeles. $b Computer Science 0201. $3 1182286
773 0 $t Dissertations Abstracts International $g 84-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30487400 $z click for full text (PQDT)