Explaining Deep Learning Models using Causal Inference release_q3t2jhgq4fhonoinwjaq2frv2y

by Tanmayee Narendra, Anush Sankaran, Deepak Vijaykeerthy, Senthil Mani

Released as a article .

2018  

Abstract

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. We also formulate a method to quantitatively rank the filters of a convolution layer according to their counterfactual importance. We illustrate our approach with popular CNN architectures such as LeNet5, VGG19, and ResNet32.
In text/plain format

Archived Files and Locations

application/pdf  335.9 kB
file_vpbubzzaxnasnnolyu55xoyeda
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2018-11-11
Version   v1
Language   en ?
arXiv  1811.04376v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 613f090f-4764-458a-9472-0f4889bf05c2
API URL: JSON