ISSN 1000-1239 CN 11-1777/TP

Journal of Computer Research and Development ›› 2020, Vol. 57 ›› Issue (9): 1971-1986.doi: 10.7544/issn1000-1239.2020.20190456

Previous Articles     Next Articles

Interpretation and Understanding in Machine Learning

Chen Kerui1, Meng Xiaofeng2   

  1. 1(School of Computer & Information Engineering, Henan University of Economics and Law, Zhengzhou 450002);2(School of Information, Renmin University of China, Beijing 100872)
  • Online:2020-09-01
  • Supported by: 
    This work was supported by the National Natural Science Foundation of China (91646203, 61941121, 61532010, 91846204, 61532016, 91746115) and the Young Talents Fund of Henan University of Economics and Law.

Abstract: In recent years, machine learning has developed rapidly, especially in the deep learning, where remarkable achievements are obtained in image, voice, natural language processing and other fields. The expressive ability of machine learning algorithm has been greatly improved; however, with the increase of model complexity, the interpretability of computer learning algorithm has deteriorated. So far, the interpretability of machine learning remains as a challenge. The trained models via algorithms are regarded as black boxes, which seriously hamper the use of machine learning in certain fields, such as medicine, finance and so on. Presently, only a few works emphasis on the interpretability of machine learning. Therefore, this paper aims to classify, analyze and compare the existing interpretable methods; on the one hand, it expounds the definition and measurement of interpretability, while on the other hand, for the different interpretable objects, it summarizes and analyses various interpretable techniques of machine learning from three aspects: model understanding, prediction result interpretation and mimic model understanding. Moreover, the paper also discusses the challenges and opportunities faced by machine learning interpretable methods and the possible development direction in the future. The proposed interpretation methods should also be useful for putting many research open questions in perspective.

Key words: machine learning, interpretation, neural network, black box, mimic model

CLC Number: