Towards Explainable Neural-Symbolic Visual Reasoning
This work addresses the need for explainable AI for non-technical users, but it appears incremental as it builds on existing definitions and methods.
The paper tackles the problem of lack of interpretability in high-performance models by proposing a neural-symbolic reasoning model to explain neural network decisions and correct bias, with an example application in image captioning.
Many high-performance models suffer from a lack of interpretability. There has been an increasing influx of work on explainable artificial intelligence (XAI) in order to disentangle what is meant and expected by XAI. Nevertheless, there is no general consensus on how to produce and judge explanations. In this paper, we discuss why techniques integrating connectionist and symbolic paradigms are the most efficient solutions to produce explanations for non-technical users and we propose a reasoning model, based on definitions by Doran et al. [2017] (arXiv:1710.00794) to explain a neural network's decision. We use this explanation in order to correct bias in the network's decision rationale. We accompany this model with an example of its potential use, based on the image captioning method in Burns et al. [2018] (arXiv:1803.09797).