Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions

TL;DR

This paper introduces a neural network architecture that inherently explains its predictions by using prototypes and autoencoders, making deep learning models more interpretable without sacrificing accuracy.

Contribution

The authors propose a novel deep learning model with a prototype layer and autoencoder that provides built-in explanations for its predictions, enhancing interpretability.

Findings

The model achieves accurate classifications while offering explanations.

Prototypes are visualizable and resemble training inputs.

The training balances accuracy, prototype-input similarity, and autoencoder reconstruction.

Abstract

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability -- they are particularly difficult to understand because of their non-linear nature. As a result, neural networks are often treated as "black box" models, and in the past, have been trained purely to optimize the accuracy of predictions. In this work, we create a novel network architecture for deep learning that naturally explains its own reasoning for each prediction. This architecture contains an autoencoder and a special prototype layer, where each unit of that layer stores a weight vector that resembles an encoded training input. The encoder of the autoencoder allows us to do comparisons within the latent space, while the decoder allows us to visualize the learned prototypes. The training objective has four terms: an accuracy term, a term that encourages every prototype to be similar to at least one encoded input, a term that encourages every encoded input to be close to at least one prototype, and a term that encourages faithful reconstruction by the autoencoder. The distances computed in the prototype layer are used as part of the classification process. Since the prototypes are learned during training, the learned network naturally comes with explanations for each prediction, and the explanations are loyal to what the network actually computes.