Concept backpropagation: An Explainable AI approach for visualising learned concepts in neural network models

TL;DR

Concept backpropagation is a novel explainable AI method that visualizes how neural networks internalize specific concepts by perturbing inputs guided by concept probes, enhancing interpretability across various modalities.

Contribution

This work extends concept detection methods with concept backpropagation, enabling visualization of concept representations within neural networks through input perturbation guided by trained probes.

Findings

Effective visualization of concept internalization across modalities

Insights into concept entanglement within neural network representations

Potential for improved interpretability of black-box models

Abstract

Neural network models are widely used in a variety of domains, often as black-box solutions, since they are not directly interpretable for humans. The field of explainable artificial intelligence aims at developing explanation methods to address this challenge, and several approaches have been developed over the recent years, including methods for investigating what type of knowledge these models internalise during the training process. Among these, the method of concept detection, investigates which \emph{concepts} neural network models learn to represent in order to complete their tasks. In this work, we present an extension to the method of concept detection, named \emph{concept backpropagation}, which provides a way of analysing how the information representing a given concept is internalised in a given neural network model. In this approach, the model input is perturbed in a manner guided by a trained concept probe for the described model, such that the concept of interest is maximised. This allows for the visualisation of the detected concept directly in the input space of the model, which in turn makes it possible to see what information the model depends on for representing the described concept. We present results for this method applied to a various set of input modalities, and discuss how our proposed method can be used to visualise what information trained concept probes use, and the degree as to which the representation of the probed concept is entangled within the neural network model itself.