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

On the Evaluation of Deep Generative Models.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	On the Evaluation of Deep Generative Models./
作者:	Zhou, Sharon.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	127 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
Contained By:	Dissertations Abstracts International83-05B.
標題:	Neural networks. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28688334
ISBN:	9798544203735

On the Evaluation of Deep Generative Models.
Zhou, Sharon.

On the Evaluation of Deep Generative Models. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 127 p.

Source: Dissertations Abstracts International, Volume: 83-05, Section: B.

Thesis (Ph.D.)--Stanford University, 2021.

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

Evaluation drives and tracks progress in every field. Metrics of evaluation are designed to assess important criteria in an area, and aid us in understanding the quantitative differences between one breakthrough and another. In machine learning, evaluation metrics have historically acted as north stars towards which researchers have optimized and organized their methods and findings. While evaluation metrics have been straightforward to construct and implement in some subfields of machine learning, they have been notoriously difficult to design in generative models. Several reasons emerge to explain this: (1) there are no gold standard outputs to compare against, unlike held-out test sets, (2) because of their diverse training methods and formulations, inherent model properties are difficult to measure consistently, and sampled outputs are often used for evaluation instead, (3) dependence on external (pretrained) models that add another layer of bias and uncertainty, and (4) inconsistent results without a large number of samples. As a result, generative models have suffered from noisy assessments that occupy a changing evaluation landscape, in contrast to the relative stability of their discriminative counterparts. In this manuscript, we examine several important criteria for generative models and introduce evaluation metrics to address each one while discussing the aforementioned issues in generative model evaluation. In particular, we examine the challenge of measuring the perceptual realism of generated outputs and introduce a human-in-the-loop evaluation system that leverages psychophysics theory to ground the method in human perception literature and crowdsourcing techniques to construct an efficient, reliable, and consistent method for comparing different models. In addition to this, we analyze disentanglement, an increasingly important property for assessing learned representations, by measuring an intrinsic property of a generative model's data manifold using persistent homology. The final work in this manuscript takes a step towards assessing a generative model and its different modes with a key application in mind, specifically the stylistic fidelity across different generated modes in a multimodal setting.

ISBN: 9798544203735Subjects--Topical Terms:

677449
Neural networks.

On the Evaluation of Deep Generative Models.
LDR:03275nmm a2200325 4500 001 2344864
005 20220531062200.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798544203735
035 $a (MiAaPQ)AAI28688334
035 $a (MiAaPQ)STANFORDfr445th8838
035 $a AAI28688334
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhou, Sharon. $3 3683689
245 1 0 $a On the Evaluation of Deep Generative Models.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 127 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
500 $a Advisor: Ermon, Stefano; Ng, Andrew.
502 $a Thesis (Ph.D.)--Stanford University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Evaluation drives and tracks progress in every field. Metrics of evaluation are designed to assess important criteria in an area, and aid us in understanding the quantitative differences between one breakthrough and another. In machine learning, evaluation metrics have historically acted as north stars towards which researchers have optimized and organized their methods and findings. While evaluation metrics have been straightforward to construct and implement in some subfields of machine learning, they have been notoriously difficult to design in generative models. Several reasons emerge to explain this: (1) there are no gold standard outputs to compare against, unlike held-out test sets, (2) because of their diverse training methods and formulations, inherent model properties are difficult to measure consistently, and sampled outputs are often used for evaluation instead, (3) dependence on external (pretrained) models that add another layer of bias and uncertainty, and (4) inconsistent results without a large number of samples. As a result, generative models have suffered from noisy assessments that occupy a changing evaluation landscape, in contrast to the relative stability of their discriminative counterparts. In this manuscript, we examine several important criteria for generative models and introduce evaluation metrics to address each one while discussing the aforementioned issues in generative model evaluation. In particular, we examine the challenge of measuring the perceptual realism of generated outputs and introduce a human-in-the-loop evaluation system that leverages psychophysics theory to ground the method in human perception literature and crowdsourcing techniques to construct an efficient, reliable, and consistent method for comparing different models. In addition to this, we analyze disentanglement, an increasingly important property for assessing learned representations, by measuring an intrinsic property of a generative model's data manifold using persistent homology. The final work in this manuscript takes a step towards assessing a generative model and its different modes with a key application in mind, specifically the stylistic fidelity across different generated modes in a multimodal setting.
590 $a School code: 0212.
650 4 $a Neural networks. $3 677449
650 4 $a Design. $3 518875
650 4 $a Confidence intervals. $3 566017
650 4 $a Ablation. $3 3562462
650 4 $a Realism. $3 528996
650 4 $a Asymmetry. $3 3562922
650 4 $a Artificial intelligence. $3 516317
650 4 $a Philosophy. $3 516511
690 $a 0389
690 $a 0800
690 $a 0422
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 83-05B.
790 $a 0212
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28688334