DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction

TL;DR

DeepView introduces a visualization method that uses discriminative dimensionality reduction to plot deep neural network decision boundaries and data points in two dimensions, aiding interpretability.

Contribution

It presents a novel visualization approach for understanding deep neural networks by combining decision boundary visualization with data set inspection in 2D.

Findings

Enables visualization of decision boundaries and data properties in 2D

Helps identify outliers, adversaries, and poisoned data

Complementary to existing interpretation methods

Abstract

Machine learning algorithms using deep architectures have been able to implement increasingly powerful and successful models. However, they also become increasingly more complex, more difficult to comprehend and easier to fool. So far, most methods in the literature investigate the decision of the model for a single given input datum. In this paper, we propose to visualize a part of the decision function of a deep neural network together with a part of the data set in two dimensions with discriminative dimensionality reduction. This enables us to inspect how different properties of the data are treated by the model, such as outliers, adversaries or poisoned data. Further, the presented approach is complementary to the mentioned interpretation methods from the literature and hence might be even more useful in combination with those. Code is available at https://github.com/LucaHermes/DeepView .