Kentaro Toyama, Gregory D. Hager
One quality that makes biological systems appear intelligent is their robustness to difficult circumstances. Robustness is crucial to intelligent behavior and important to AI research. We distinguish between ante-failtire and post-failure robustness for causal tasks. Ante-failure robust systems resist failure, whereas post-failure systems incorporate the ability to recover from failure once it happens. We point out the power of post-failure robustness in AI problems, closely examining one example in visual motion tracking. Finally, we raise theoretical issues and argue for greater effort towards building post-failure robust systems.