# Interpretable Explanations of Black Boxes by Meaningful Perturbation

## TL;DR

This paper introduces a general, model-agnostic framework for generating interpretable explanations of black box models, focusing on identifying image regions responsible for classifier decisions through meaningful perturbations.

## Contribution

It proposes a novel, flexible explanation framework applicable to any black box, emphasizing explicit, interpretable image perturbations for better understanding.

## Key findings

- Framework is applicable to various black box models
- Method effectively identifies image regions responsible for decisions
- Approach is model-agnostic and testable

## Abstract

As machine learning algorithms are increasingly applied to high impact yet high risk tasks, such as medical diagnosis or autonomous driving, it is critical that researchers can explain how such algorithms arrived at their predictions. In recent years, a number of image saliency methods have been developed to summarize where highly complex neural networks "look" in an image for evidence for their predictions. However, these techniques are limited by their heuristic nature and architectural constraints. In this paper, we make two main contributions: First, we propose a general framework for learning different kinds of explanations for any black box algorithm. Second, we specialise the framework to find the part of an image most responsible for a classifier decision. Unlike previous works, our method is model-agnostic and testable because it is grounded in explicit and interpretable image perturbations.