Dissonance Between Human and Machine Understanding

TL;DR

This study investigates the differences between human and machine understanding in image classification, revealing how well models align with human reasoning and the impact of task difficulty on feature selection.

Contribution

It provides a large-scale crowdsourcing analysis quantifying the dissonance between human and machine understanding in complex models.

Findings

Certain well-performing models align closely with human feature use.

Task difficulty influences the similarity between human and machine feature selection.

Humans generally outperform machines in selecting features for accurate image recognition.

Abstract

Complex machine learning models are deployed in several critical domains including healthcare and autonomous vehicles nowadays, albeit as functional black boxes. Consequently, there has been a recent surge in interpreting decisions of such complex models in order to explain their actions to humans. Models that correspond to human interpretation of a task are more desirable in certain contexts and can help attribute liability, build trust, expose biases and in turn build better models. It is, therefore, crucial to understand how and which models conform to human understanding of tasks. In this paper, we present a large-scale crowdsourcing study that reveals and quantifies the dissonance between human and machine understanding, through the lens of an image classification task. In particular, we seek to answer the following questions: Which (well-performing) complex ML models are closer to humans in their use of features to make accurate predictions? How does task difficulty affect the feature selection capability of machines in comparison to humans? Are humans consistently better at selecting features that make image recognition more accurate? Our findings have important implications on human-machine collaboration, considering that a long term goal in the field of artificial intelligence is to make machines capable of learning and reasoning like humans.