DROPS

Document

DOI: 10.4230/OASIcs.PLATEAU.2019.7

Live Programming Environment for Deep Learning with Instant and Editable Neural Network Visualization

Authors: Chunqi Zhao, Tsukasa Fukusato, Jun Kato, and Takeo Igarashi

Published in: OASIcs, Volume 76, 10th Workshop on Evaluation and Usability of Programming Languages and Tools (PLATEAU 2019)

Abstract

Artificial intelligence (AI) such as deep learning has achieved significant success in a variety of application domains. Several visualization techniques have been proposed for understanding the overall behavior of the neural network defined by deep learning code. However, they show visualization only after the code or network definition is written and it remains complicated and unfriendly for newbies to build deep neural network models on a code editor. In this paper, to help user better understand the behavior of networks, we augment a code editor with instant and editable visualization of network model, inspired by live programming which provides continuous feedback to the programmer.

Cite as

Chunqi Zhao, Tsukasa Fukusato, Jun Kato, and Takeo Igarashi. Live Programming Environment for Deep Learning with Instant and Editable Neural Network Visualization. In 10th Workshop on Evaluation and Usability of Programming Languages and Tools (PLATEAU 2019). Open Access Series in Informatics (OASIcs), Volume 76, pp. 7:1-7:5, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2020)

Copy BibTex To Clipboard

@InProceedings{zhao_et_al:OASIcs.PLATEAU.2019.7,
  author =	{Zhao, Chunqi and Fukusato, Tsukasa and Kato, Jun and Igarashi, Takeo},
  title =	{{Live Programming Environment for Deep Learning with Instant and Editable Neural Network Visualization}},
  booktitle =	{10th Workshop on Evaluation and Usability of Programming Languages and Tools (PLATEAU 2019)},
  pages =	{7:1--7:5},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-135-1},
  ISSN =	{2190-6807},
  year =	{2020},
  volume =	{76},
  editor =	{Chasins, Sarah and Glassman, Elena L. and Sunshine, Joshua},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.PLATEAU.2019.7},
  URN =		{urn:nbn:de:0030-drops-119613},
  doi =		{10.4230/OASIcs.PLATEAU.2019.7},
  annote =	{Keywords: Neural network visualization, Live programming, Deep learning}
}

Document

DOI: 10.4230/DagRep.7.6.48

Computational Interactivity (Dagstuhl Seminar 17232)

Authors: Xiaojun Bi, Otmar Hilliges, Takeo Igarashi, and Antti Oulasvirta

Published in: Dagstuhl Reports, Volume 7, Issue 6 (2018)

Abstract

This report documents the program and the outcomes of Dagstuhl Seminar on Computational Interaction organized in June 2017. The seminar focused on the use of computational methods to represent and enhance human-computer interaction. This topic is gaining traction, but efforts have been diluted over multiple research areas ranging from HCI to computer graphics and design. The main objective of the seminar was to get an overview and, moreover, discuss shared fundaments, such as what computational interaction is, formally and in practice. The seminar invitees were 22 researchers from areas such as Human-Computer Interaction, Computer Graphics, Operations Research, and more. The seminar consisted of three days of events, with emphasis on presentations, panels, and group discussions. The following summarizes the main outcomes.

Cite as

Xiaojun Bi, Otmar Hilliges, Takeo Igarashi, and Antti Oulasvirta. Computational Interactivity (Dagstuhl Seminar 17232). In Dagstuhl Reports, Volume 7, Issue 6, pp. 48-67, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2017)

Copy BibTex To Clipboard

@Article{bi_et_al:DagRep.7.6.48,
  author =	{Bi, Xiaojun and Hilliges, Otmar and Igarashi, Takeo and Oulasvirta, Antti},
  title =	{{Computational Interactivity (Dagstuhl Seminar 17232)}},
  pages =	{48--67},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2017},
  volume =	{7},
  number =	{6},
  editor =	{Bi, Xiaojun and Hilliges, Otmar and Igarashi, Takeo and Oulasvirta, Antti},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.7.6.48},
  URN =		{urn:nbn:de:0030-drops-82865},
  doi =		{10.4230/DagRep.7.6.48},
  annote =	{Keywords: crowd-computing, graphics, HCI, Machine learning, optimization, simulation}
}

Search Results

Documents authored by Igarashi, Takeo

Live Programming Environment for Deep Learning with Instant and Editable Neural Network Visualization

Abstract

Cite as

Computational Interactivity (Dagstuhl Seminar 17232)

Abstract

Cite as

Thanks for your feedback!

Could not send message