Interpretable Explanations of Black Boxes by Meaningful Perturbation

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 dev...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings / IEEE International Conference on Computer Vision s. 3449 - 3457
Hlavní autori: Fong, Ruth C., Vedaldi, Andrea
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.10.2017
Predmet:
Backpropagation
Gradient methods
Machine learning algorithms
Neural networks
Perturbation methods
Prediction algorithms
Visualization
ISSN:2380-7504
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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.
ISSN:2380-7504
DOI:10.1109/ICCV.2017.371