Reflecting After Learning for Understanding
Today, image classification is a common way for systems to process visual content. Although neural network approaches to classification have seen great progress in reducing error rates, it is not clear what this means for a cognitive system that needs to make sense of the multiple and competing predictions from its own classifiers. As a step to address this, we present a novel framework that uses meta-reasoning and meta-operations to unify predictions into abstractions, properties, or relationships. Using the framework on images from ImageNet, we demonstrate systems that unify 41 of predictions in general and unify 67 can explain their conceptual differences. We also demonstrate a system in "the wild" by feeding live video images through it and show it unifying 51 predictions in general and 69 explained conceptually by the system. In a survey given to 24 participants, we found that 87
READ FULL TEXT