Explaining Deep Learning Models using Causal Inference

Understand

Although deep learning models have been successfully applied to a variety of tasks, due to the millions of parameters, they are becoming increasingly opaque and complex.

• In order to establish trust for their widespread commercial use, it is important to formalize a principled framework to reason over these models.
• In this work, we use ideas from causal inference to describe a general framework to reason over CNN models.
• Specifically, we build a Structural Causal Model (SCM) as an abstraction over a specific aspect of the CNN.