Hybrid formalisms that blend production rules with neural computation, as well as transparent architectures like the discretized interpretable multilayer perceptron (DIMLP), are used to explain machine learning model predictions in high-stakes domains like oncology and radiology.

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)

• oncology concept