Neurosymbolic AI refers to techniques that combine sub-symbolic neural networks with symbolic techniques. These may be fairly distinct modules in a hybrid archtecture, but also can be integrated at.a more fundamental way such as using neural techniques to reason over semantic networks or the way high-level counterfactual reasonng is used to guide low-level stimulus-response learning in the cognitive model of regret.
Defined on page 125
Used on Chap. 6: page 125; Chap. 24: page 584
Also known as neurosymbolic