Explainable AI for the Choquet Integral

The modern era of machine learning is focused on data-driven solutions. While this has resulted in astonishing leaps in numerous applications, explainability has not witnessed the same growth. The reality is, most machine learning solutions are black boxes. Herein, we focus on data/information fusion in machine learning. Specifically, we explore four eXplainable Artificial Intelligence (XAI) questions relative to Choquet integral; (i) what is the quality of our inputs and their interactions, (ii) how is the information being combined, (iii) what is the quality of our training data (and thus our learned models), and (iv) what trust do we place in an output? Previously, we derived an initial set of indices for (i)-(iv) on the premise of perfect knowledge. Herein, we make XAI more accurate by taking into consideration what the machine learned. A combination of synthetic data and real-world experiments from remote sensing for fusing deep learners in the context of classification are explored. Our approach leads to performance gain, insights into what was learned, and it helps us realize better future solutions.

I. Introduction

Since the dawn of computing, machines have been designed to carry out lists of deterministic operations given to them. In the last few decades, factors like Big Data and machine learning (ML) have given rise to a so-called data-driven era of artificial intelligence (AI). On one hand, we have data to help approximate parameters. On the other hand, the vast majority of algorithms are black box solutions. Sometimes, it might not be imperative to have an explanation as to what was learned; the solution in itself is all that is required. However, in other settings it may be vital to understand why a decision was reached. This need is a driving factor behind explainable artificial intelligence (XAI). Another advantage of XAI is finding gaps in current AI to accelerate the field.