國立虎尾科技大學 |

GT-CHES and DyCon : = Improved Classification for Human Evolutionary Systems.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	GT-CHES and DyCon :/
其他題名:	Improved Classification for Human Evolutionary Systems.
作者:	Johnson, Joseph S.
面頁冊數:	1 online resource (95 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:	9798382229614

GT-CHES and DyCon : = Improved Classification for Human Evolutionary Systems.
Johnson, Joseph S.

GT-CHES and DyCon :Improved Classification for Human Evolutionary Systems. - 1 online resource (95 pages)

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

Thesis (Ph.D.)--Brigham Young University, 2024.

Includes bibliographical references

The purpose of this work is to rethink the process of learning in human evolutionary systems. We take a sober look at how game theory, network theory, and chaos theory pertain specifically to the modeling, data, and training components of generalization in human systems. The value of our research is three-fold. First, our work is a direct approach to align machine learning generalization with core behavioral theories. We made our best effort to directly reconcile the axioms of these heretofore incompatible disciplines - rather than moving from AI/ML towards the behavioral theories while building exclusively on AI/ML intuition. Second, this approach simplifies the learning process and makes it more intuitive for non-technical domain experts. We see increasing complexity in the models introduced in academic literature and, hence, increasing reliance on abstract hidden states learned by automatic feature engineering. The result is less understanding of how the models work and how they can be interpreted. However, these increasingly complex models are effective on the particular benchmark datasets they were designed for, but do not generalize. Our research highlights why these models are not generalizable and why behavioral theoretic intuition must have priority over the black box reliance on automatic feature engineering. Third, we introduce two novel methods that can be applied off-the-shelf: graph transformation for classification in human evolutionary systems (GT-CHES) and dynamic contrastive learning (DyCon). These models are most effective in mixed-motive human systems. While, GT-CHES is most suitable for tasks that involve event-based data, DyCon can be used on any temporal task.

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

Mode of access: World Wide Web

ISBN: 9798382229614Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Dynamic contrastive learningIndex Terms--Genre/Form:

554714
Electronic books.

GT-CHES and DyCon : = Improved Classification for Human Evolutionary Systems.
LDR:03118ntm a22003977 4500 001 1148236
005 20240916070034.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382229614
035 $a (MiAaPQ)AAI31234430
035 $a (MiAaPQ)BrighamYoung11271
035 $a AAI31234430
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Johnson, Joseph S. $3 1474160
245 1 0 $a GT-CHES and DyCon : $b Improved Classification for Human Evolutionary Systems.
264 0 $c 2024
300 $a 1 online resource (95 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: Snell, Quinn.
502 $a Thesis (Ph.D.)--Brigham Young University, 2024.
504 $a Includes bibliographical references
520 $a The purpose of this work is to rethink the process of learning in human evolutionary systems. We take a sober look at how game theory, network theory, and chaos theory pertain specifically to the modeling, data, and training components of generalization in human systems. The value of our research is three-fold. First, our work is a direct approach to align machine learning generalization with core behavioral theories. We made our best effort to directly reconcile the axioms of these heretofore incompatible disciplines - rather than moving from AI/ML towards the behavioral theories while building exclusively on AI/ML intuition. Second, this approach simplifies the learning process and makes it more intuitive for non-technical domain experts. We see increasing complexity in the models introduced in academic literature and, hence, increasing reliance on abstract hidden states learned by automatic feature engineering. The result is less understanding of how the models work and how they can be interpreted. However, these increasingly complex models are effective on the particular benchmark datasets they were designed for, but do not generalize. Our research highlights why these models are not generalizable and why behavioral theoretic intuition must have priority over the black box reliance on automatic feature engineering. Third, we introduce two novel methods that can be applied off-the-shelf: graph transformation for classification in human evolutionary systems (GT-CHES) and dynamic contrastive learning (DyCon). These models are most effective in mixed-motive human systems. While, GT-CHES is most suitable for tasks that involve event-based data, DyCon can be used on any temporal task.
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 Computer science. $3 573171
653 $a Dynamic contrastive learning
653 $a Human evolutionary systems
653 $a Behavioral theories
653 $a Machine learning
655 7 $a Electronic books. $2 local $3 554714
690 $a 0511
690 $a 0984
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Brigham Young University. $3 1187870
773 0 $t Dissertations Abstracts International $g 85-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31234430 $z click for full text (PQDT)