Guest Editorial Multimedia Computing With Interpretable Machine Learning

被引:1
作者
Tian, Y. [1 ,2 ]
Snoek, C. [3 ]
Wang, J. [4 ]
Liu, Z. [5 ]
Lienhart, R. [6 ]
Boll, S. [7 ]
机构
[1] Peking Univ, Sch EE&CS, Dept Comp Sci & Technol, Beijing 100871, Peoples R China
[2] PengCheng Lab, Artificial Intelligence Res Ctr, Shenzhen 518066, Peoples R China
[3] Univ Amsterdam, Informat Inst, NL-94323 Amsterdam, Netherlands
[4] Microsoft Res Asia, Beijing 100080, Peoples R China
[5] AT&T Labs Res, Middletown, NJ 07748 USA
[6] Univ Augsburg, Comp Sci Dept, D-86159 Augsburg, Germany
[7] Carl von Ossietzky Univ Oldenburg, Dept Comp Sci, D-26121 Oldenburg, Germany
关键词
Special issues and sections; Machine learning; Feature extraction; Visualization; Multimedia communication; Deep learning; Big Data;
D O I
10.1109/TMM.2020.2991292
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The papers in this special section is to broadly engage the machine learning and multimedia communities on the emerging yet challenging interpretable machine learning. Multimedia is increasingly becoming the "biggest big data," among the most important and valuable source for insight and information. Many powerful machine learning algorithms, especially deep learning models such as convolutional neural networks (CNNs), have recently achieved outstanding predictive performance in a wide range of multimedia applications, including visual object classification, scene understanding, speech recognition, and activity prediction. Nevertheless, most deep learning algorithms are generally conceived as blackbox methods, and it is difficult to intuitively and quantitatively understand the results of their prediction and inference. Since this lack of interpretability is a major bottleneck in designing more successful predictive models and exploring wider-range useful applications, there has been an explosion of interest in interpreting the representations learned by these models, with profound implications for research into interpretable machine learning in the multimedia community.
引用
收藏
页码:1661 / 1666
页数:6
相关论文
empty
未找到相关数据