Illuminated Decision Trees with Lucid

TL;DR

This paper introduces the Illuminated Decision Tree method, combining neural network feature extraction with decision trees and Lucid visualizations to interpret models trained on microscope images of white blood cells, aiding development and explanation.

Contribution

It presents a novel approach that integrates feature visualization with decision trees for interpreting neural networks on challenging, less visually rich datasets.

Findings

Effective visualization of decision nodes in complex tasks

Improved model debugging and understanding

Enhanced explanation of model outputs to non-experts

Abstract

The Lucid methods described by Olah et al. (2018) provide a way to inspect the inner workings of neural networks trained on image classification tasks using feature visualization. Such methods have generally been applied to networks trained on visually rich, large-scale image datasets like ImageNet, which enables them to produce enticing feature visualizations. To investigate these methods further, we applied them to classifiers trained to perform the much simpler (in terms of dataset size and visual richness), yet challenging task of distinguishing between different kinds of white blood cell from microscope images. Such a task makes generating useful feature visualizations difficult, as the discriminative features are inherently hard to identify and interpret. We address this by presenting the "Illuminated Decision Tree" approach, in which we use a neural network trained on the task as a feature extractor, then learn a decision tree based on these features, and provide Lucid visualizations for each node in the tree. We demonstrate our approach with several examples, showing how this approach could be useful both in model development and debugging, and when explaining model outputs to non-experts.