Interpretability of Machine Learning: Recent Advances and Future Prospects
Lei Gao, Ling Guan
Abstract
The proliferation of machine learning (ML) has drawn unprecedented interest in the study of various multimedia contents such as text, image, audio, and video, among others. Consequently, understanding and learning ML-based representations have taken center stage in knowledge discovery in intelligent multimedia research and applications. Nevertheless, the black-box nature of contemporary ML, especially in deep neural networks, has posed a primary challenge for ML-based representation learning. To address this black-box problem, studies on the interpretability of ML have attracted tremendous interest in recent years. This article presents a survey on recent advances in and future prospects for the interpretability of ML, with several application examples pertinent to multimedia computing, including text–image cross-modal representation learning, face recognition, and the recognition of objects. It is evidently shown that the study of the interpretability of ML promises an important research direction, one that is worth further investment in.