Semantics for Global and Local Interpretation of Deep Neural Networks

21 Oct 2019  ·  Jindong Gu, Volker Tresp ·

Deep neural networks (DNNs) with high expressiveness have achieved state-of-the-art performance in many tasks. However, their distributed feature representations are difficult to interpret semantically. In this work, human-interpretable semantic concepts are associated with vectors in feature space. The association process is mathematically formulated as an optimization problem. The semantic vectors obtained from the optimal solution are applied to interpret deep neural networks globally and locally. The global interpretations are useful to understand the knowledge learned by DNNs. The interpretation of local behaviors can help to understand individual decisions made by DNNs better. The empirical experiments demonstrate how to use identified semantics to interpret the existing DNNs.

PDF Abstract
No code implementations yet. Submit your code now

Tasks


Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here