Alert button
Picture for Ryan R. Anderson

Ryan R. Anderson

Alert button

Reflecting After Learning for Understanding

Oct 18, 2019
Lee Martie, Mohammad Arif Ul Alam, Gaoyuan Zhang, Ryan R. Anderson

Figure 1 for Reflecting After Learning for Understanding
Figure 2 for Reflecting After Learning for Understanding
Figure 3 for Reflecting After Learning for Understanding
Figure 4 for 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% to 46% of predictions in general and unify 67% to 75% of predictions when the systems 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% of predictions in general and 69% of predictions when their differences can be explained conceptually by the system. In a survey given to 24 participants, we found that 87% of the unified predictions describe their corresponding images.

* Presented at the Advances in Cognitive Systems conference (http://www.cogsys.org/conference/2019) and to be published in the Advances in Cognitive Systems journal (http://www.cogsys.org/journal) 
Viaarxiv icon