Abstract:

With the characteristics of data-driven learning, deep learning technology has made great achievements in the fields of natural language processing, image processing, and speech recognition. However, due to the deep learning model featured by deep networks, many parameters, high complexity and other characteristics, the decisions and intermediate processes made by the model are difficult for humans to understand. Therefore, exploring the interpretability of deep learning has become a new topic in the current artificial intelligence field. This review takes the interpretability of deep learning models as the research object and summarizes its progress. Firstly, the main interpretability methods are summarized and analyzed from four aspects：self-explanatory model, model-specific explanation, model-agnostic explanation, and causal interpretability. At the same time, it enumerates the application of interpretability related technologies, and finally discusses the existing problems of current interpretability research to promote the further development of the deep learning interpretability research framework.

Key words: deep learning, interpretability, artificial intelligence, causal interpretability, self-explanatory

摘要：

深度学习技术以数据驱动学习的特点，在自然语言处理、图像处理、语音识别等领域取得了巨大成就。但由于深度学习模型网络过深、参数多、复杂度高等特性，该模型做出的决策及中间过程让人类难以理解，因此探究深度学习的可解释性成为当前人工智能领域研究的新课题。以深度学习模型可解释性为研究对象，对其研究进展进行总结阐述。从自解释模型、特定模型解释、不可知模型解释、因果可解释性四个方面对主要可解释性方法进行总结分析。列举出可解释性相关技术的应用，讨论当前可解释性研究存在的问题并进行展望，以推动深度学习可解释性研究框架的进一步发展。

关键词: 深度学习, 可解释性, 人工智能, 因果可解释, 自解释