ISSN 1000-1239 CN 11-1777/TP

Journal of Computer Research and Development ›› 2020, Vol. 57 ›› Issue (6): 1208-1217.doi: 10.7544/issn1000-1239.2020.20190485

Previous Articles     Next Articles

Research Advances in the Interpretability of Deep Learning

Cheng Keyang1,2, Wang Ning1, Shi Wenxi2,3, Zhan Yongzhao1   

  1. 1(School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013);2(National Engineering Laboratory for Public Safety Risk Perception and Control by the Big Data (China Academy of Electronic Sciences), Beijing 100041);3(Xinjiang Lianhaichuangzhi Information Technology Co. LTD, Urumqi 830001)
  • Online:2020-06-01
  • Supported by: 
    This work was supported by the National Natural Science Foundation of China (61972183, 61672268) and the Director Foundation Project of National Engineering Laboratory for Public Safety Risk Perception and Control by the Big Data.

Abstract: The research on the interpretability of deep learning is closely related to various disciplines such as artificial intelligence, machine learning, logic and cognitive psychology. It has important theoretical research significance and practical application value in too many fields, such as information push, medical research, finance, and information security. In the past few years, there were a lot of well studied work in this field, but we are still facing various issues. In this paper, we clearly review the history of deep learning interpretability research and related work. Firstly, we introduce the history of interpretable deep learning from following three aspects: origin of interpretable deep learning, research exploration stage and model construction stage. Then, the research situation is presented from three aspects, namely visual analysis, robust perturbation analysis and sensitivity analysis. The research on the construction of interpretable deep learning model is introduced following four aspects: model agent, logical reasoning, network node association analysis and traditional machine learning model. Moreover, the limitations of current research are analyzed and discussed in this paper. At last, we list the typical applications of the interpretable deep learning and forecast the possible future research directions of this field along with reasonable and suitable suggestions.

Key words: artificial intelligence, deep learning, interpretability, neural network, visualization

CLC Number: