Visualizing Examples of Deep Neural Networks at Scale

要旨

Many programmers want to use deep learning due to its superior accuracy in many challenging domains. Yet our formative study with ten programmers indicated that, when constructing their own deep neural networks (DNNs), they often had a difficult time choosing appropriate model structures and hyperparameter values. This paper presents ExampleNet---a novel interactive visualization system for exploring common and uncommon design choices in a large collection of open-source DNN projects. ExampleNet provides a holistic view of the distribution over model structures and hyperparameter settings in the corpus of DNNs, so users can easily filter the corpus down to projects tackling similar tasks and compare design choices made by others. We evaluated ExampleNet in a within-subjects study with sixteen participants. Compared with the control condition (i.e., online search), participants using ExampleNet were able to inspect more online examples, make more data-driven design decisions, and make fewer design mistakes.

受賞
Honorable Mention
著者
Litao Yan
Harvard University, Cambridge, Massachusetts, United States
Elena L.. Glassman
Harvard University, Cambridge, Massachusetts, United States
Tianyi Zhang
Harvard University, Cambridge, Massachusetts, United States
DOI

10.1145/3411764.3445654

論文URL

https://doi.org/10.1145/3411764.3445654

動画

会議: CHI 2021

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2021.acm.org/)

セッション: Engineering Development Support

[A] Paper Room 05, 2021-05-10 17:00:00~2021-05-10 19:00:00 / [B] Paper Room 05, 2021-05-11 01:00:00~2021-05-11 03:00:00 / [C] Paper Room 05, 2021-05-11 09:00:00~2021-05-11 11:00:00
Paper Room 05
14 件の発表
2021-05-10 17:00:00
2021-05-10 19:00:00
日本語まとめ
読み込み中…