文章基本信息

标题：Live Programming Environment for Deep Learning with Instant and Editable Neural Network Visualization
本地全文：下载
作者：Chunqi Zhao ; Tsukasa Fukusato ; Jun Kato 等
期刊名称：OASIcs : OpenAccess Series in Informatics
电子版ISSN：2190-6807
出版年度：2020
卷号：76
页码：7:1-7:5
DOI：10.4230/OASIcs.PLATEAU.2019.7
出版社：Schloss Dagstuhl -- Leibniz-Zentrum fuer Informatik
摘要：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.
关键词：Neural network visualization; Live programming; Deep learning