Addressing Mistake Severity in Neural Networks with Semantic Knowledge

Understand

Robustness in deep neural networks and machine learning algorithms in general is an open research challenge.

• In particular, it is difficult to ensure algorithmic performance is maintained on out-of-distribution inputs or anomalous instances that cannot be anticipated at training time.
• Embodied agents will be deployed in these conditions, and are likely to make incorrect predictions.
• An agent will be viewed as untrustworthy unless it can maintain its performance in dynamic environments.