Measuring Classification Decision Certainty and Doubt

The rising use of artificial intelligence and machine learning technologies to power intelligent systems has led to a growing desire for automating, accelerating, and enhancing decision-making processes in safety-critical applications. These technologies offer decision-makers the ability to gain an information and decision-making advantage at the speed of machines. However, in safety-constrained decision-making, it is crucial to estimate and factor in the level of certainty and doubt associated with each classification decision[3]. In such scenarios, even small chances of risky outcomes may have a significant impact on classification decisions, regardless of the most probable predicted outcome, and safety-critical applications need to be sensitive to such tail probabilities [1], [2]. Furthermore, in the(multi-class) classification decision setting when model-assigned probabilities are close to uniformly distributed, we have cause to doubt the model's prediction, even if it is accurate. Moreover, from a theoretical view of probability, we have cause to doubt the model architecture if the greatest predicted probability is arbitrarily close to the second greatest probability. An intuitive score that can capture this sense of certainty and doubt about our predictions is desirable.