How far from automatically interpreting deep learning
This addresses the cognitive gap in deep learning interpretability for researchers, but it appears incremental as it builds on existing work without introducing a new paradigm.
The paper tackles the problem of evaluating and improving the interpretability of deep learning models, proposing a universal learning framework to balance interpretability and generalization performance, with proofs of solution uniqueness and probability bounds.
In recent years, deep learning researchers have focused on how to find the interpretability behind deep learning models. However, today cognitive competence of human has not completely covered the deep learning model. In other words, there is a gap between the deep learning model and the cognitive mode. How to evaluate and shrink the cognitive gap is a very important issue. In this paper, the interpretability evaluation, the relationship between the generalization performance and the interpretability of the model and the method for improving the interpretability are concerned. A universal learning framework is put forward to solve the equilibrium problem between the two performances. The uniqueness of solution of the problem is proved and condition of unique solution is obtained. Probability upper bound of the sum of the two performances is analyzed.