# Reflecting After Learning for Understanding

arXiv: https://arxiv.org/abs/1910.08243 · HTML: https://mlsanity.com/paper/1910.08243/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2019.

## Built on by (most cited first, 1 of 1)

- [Computational Metacognition](https://mlsanity.com/paper/2201.12885/) (2022)

## Abstract (arXiv)

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.