Under adversarial attacks or distributional shifts, increases in metrics such as predictive entropy and variance indicate a machine learning model's uncertainty and potential struggle to produce reliable predictions.

Authors

• Person: Not available Organization: Springer
  A Comprehensive Review of Neuro-symbolic AI for Robustness ...

Sources

• A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Springer via serper

Referenced by nodes (3)

• machine learning models concept
• adversarial attack concept
• variance concept