Dissonance Between Human and Machine Understanding

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.

23 pages, 5 figures

References in corpus (4)

• Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
• 'It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisions
• Embracing Error to Enable Rapid Crowdsourcing
• Learning Credible Models

Cited by in corpus (6)

• Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs
• Extending MAPE-K to support Human-Machine Teaming
• Vision Skills Needed to Answer Visual Questions
• Interpretability is in the eye of the beholder: Human versus artificial classification of image segments generated by humans versus XAI
• Supporting Serendipity: Opportunities and Challenges for Human-AI Collaboration in Qualitative Analysis
• How Can One Choose the Best CAM-Based Explainability Method for a CNN Model?