Please wait a minute...
Vis Inf
Vis Inf  2018, Vol. 2 Issue (3): 147-154    DOI: 10.1016/j.visinf.2018.09.001
论文     
深度学习可视化综述：面向用户群体分类
Rulei Yu, Lei Shi
SKLCS, Institute of Software, Chinese Academy of Sciences;UCAS
A user-based taxonomy for deep learning visualization
Rulei Yu, Lei Shi
SKLCS, Institute of Software, Chinese Academy of Sciences;UCAS
 全文: PDF 
摘要： 背景：深度学习在多种任务中取得了令人瞩目的成功，近年来发展迅速。鉴于其目前仍然是个“黑匣子”，深度学习的解释性已经成为遏制其发展的一个重要因素。例如，在医学和金融等领域，需要可解释性模型来给从业人员提供相应的理论依据。然而直接分析解释深度学习模型是非常复杂抽象的，作为抽象数据与直观表示的桥梁，可视化提供了相应的技术方法。 创新：为了帮助不同知识背景的用户（初学者、新手、开发者、专家）了解深度学习可视分析这个领域，本文整理了近年来前沿与重要的工作，做成了一张分类表。分类表同时说明了每个工具或方法适用的模型结构、分类目标与发布时间，辅助用户进行快速查询。为了帮助用户了解对应分类目标下的研究进展，本文详述了相应分类目标下的代表性工作，尤其是可视解释性这个重要方向。

关键词： 深度学习;  可视化;  解释性    
Abstract: Deep learning has achieved impressive success in a variety of tasks and is developing rapidly in recent years. The problem of understanding the deep learning models has become an issue for the development of deep learning, for example, in domains like medicine and finance which require interpretable models. While it is challenging to analyze and interpret complicated deep neural networks, visualization is good at bridging between abstract data and intuitive representations. Visual analytics for deep learning is a rapidly growing research field. To help users better understand this field, we present a mini-survey including a user-based taxonomy that covers state-of-the-art works of the field. Regarding the requirements of different types of users (beginners, practitioners, developers, and experts), we categorize the methods and tools by four visualization goals respectively focusing on teaching deep learning concepts, architecture assessment, tools for debugging and improving models, and visual explanation. Notably, we present a table consisting of the name of the method or tool, the year, the visualization goal, and the types of networks to which the method or tool can be applied, to assist users in finding available tools and methods quickly. To emphasize the importance of visual explanation for deep learning, we introduce the studies in this research field in detail.
Key words: Deep learning    Visualization    Interpretation
出版日期: 2018-11-05
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Rulei Yu
Lei Shi

引用本文:

Rulei Yu, Lei Shi. A user-based taxonomy for deep learning visualization. Vis Inf, 2018, 2(3): 147-154.

链接本文:

http://www.zjujournals.com/vi/CN/10.1016/j.visinf.2018.09.001    或    http://www.zjujournals.com/vi/CN/Y2018/V2/I3/147

[1] Piyush Chawla, Subhashis Hazarika, Han-Wei Shen. 面向ConvNet的词语级情感分解：情感分类器的可视化 [J]. Vis Inf, 2020, 4(2): 72-85.
[2] Wenbin He, Junpeng Wang, Hanqi Guo, Han-Wei Shen, Tom Peterka. CECAV-DNN：使用深度神经网络进行集合比较和可视化 [J]. Vis Inf, 2020, 4(2): 109-121.
[3] Piyush Chawla, Subhashis Hazarika, Han-Wei Shen. 面向ConvNet的词语级情感分解：情感分类器的可视化 [J]. Vis Inf, 2020, 4(2): 132-141.
[4] Kadri Umbleja, Manabu Ichino, Hiroyuki Yaguchi. 改进符号数据可视化以促进模式识别和知识发现[J]. Vis Inf, 2020, 4(1): 23-31.
[5] Ruochen Cao, Subrata Dey, Andrew Cunningham, James Walsh, Ross T.Smith, Joanne E.Zucco, Bruce H. Thomas. 考察叙事结构在数据视频中的运用 [J]. Vis Inf, 2020, 4(1): 8-22.
[6] Lei Shi, Qi Liao, Hanghang Tong, Yifan Hu, Chaoli Wang, Chuang Lin, Weihong Qian. OnionGraph:层次拓扑与属性多变量，网络可视化 [J]. Vis Inf, 2020, 4(1): 43-57.
[7] Georgios Lampropoulos, Euclid Keramopoulos, Konstantinos Diamantaras. 使用深度学习、语义网络和知识图谱提高增强现实的功能 ——综述 [J]. Vis Inf, 2020, 4(1): 32-42.
[8] Kecheng Lu, Chaoli Wang, Keqin Wu, Minglun Gong, Yunhai Wang. 基于块对应的时变体数据挖掘的统一框架 [J]. Vis Inf, 2019, 3(4): 157-165.
[9] Davide Ceneda, Theresia Gschwandtne, Silvia Miksch. 在交互可视化中不同的引导方式对交互绩效和心理状态的影响 [J]. Vis Inf, 2019, 3(4): 177-191.
[10] Cui Xie, Mingkui Li, Haoying wang, Junyu Dong. 海洋数据可视化分析综述 [J]. Vis Inf, 2019, 3(3): 113-128.
[11] Xueyi Chen, Liming Shen, Ziqi Sha, Richen Liu, Siming Chen, Genlin Ji, ChaoTan. 时空模拟数据可视化的多空间分析技术综述 [J]. Vis Inf, 2019, 3(3): 129-139.
[12] Huan Liu, Sichen Jin, Yuyu Yan, Yubo Tao, Hai Lin. 利用主题子轨迹对出租车轨迹进行可视分析[J]. Vis Inf, 2019, 3(3): 140-149.
[13] Meng Zhang, Youyi Zheng. Hair-GAN：采用生成式对抗网络从单幅图像恢复3D头发结构[J]. Vis Inf, 2019, 3(2): 102-112.
[14] Junhua Lu, Xiao Xie,  Ji Lan,  Tai-Quan Peng,  Yingcai Wu,  Wei Chen. BeXplorer:大型多人在线角色扮演类游戏中玩家交流与消费行为动态关联的可视分析 [J]. Vis Inf, 2019, 3(2): 87-101.
[15] Mohammad Chegini, Jürgen Bernard, Philip Berger, Alexei Sourin, Keith Andrews, Tobias Schreck. 使用链接可视化，聚类和主动学习对监督机器学习进行多变量数据集的交互式标记[J]. Vis Inf, 2019, 3(1): 9-17.