# On Network Science and Mutual Information for Explaining Deep Neural Networks

## TL;DR

This paper introduces NIF, a novel method combining mutual information and network science to interpret deep neural networks by quantifying information flow between neurons.

## Contribution

It presents a new approach, NIF, that approximates mutual information to analyze and explain the internal information dynamics of deep learning models.

## Key findings

- NIF effectively quantifies information flow between neurons.
- The method exposes internal model internals and aids feature attribution.
- Provides a new perspective on deep learning interpretability.

## Abstract

In this paper, we present a new approach to interpret deep learning models. By coupling mutual information with network science, we explore how information flows through feedforward networks. We show that efficiently approximating mutual information allows us to create an information measure that quantifies how much information flows between any two neurons of a deep learning model. To that end, we propose NIF, Neural Information Flow, a technique for codifying information flow that exposes deep learning model internals and provides feature attributions.