The 'Neuro: Symbolic -> Neuro' architecture follows a pipeline configuration where a neural module processes raw inputs into symbolic representations, which are then consumed by a symbolic reasoner, with feedback from the symbolic module used to iteratively refine the neural model.

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 (1)

• neural perception module concept