Re:Deep Learning Alone Isn’t Getting Us to Human-Like AI
by zmgsabst on Saturday August 20, 2022 @12:48PM
(#32533393)
I tend to think of it in terms of topology — since that’s my background.
The semantics of a system is mapping the topology of the input space to output space.
DL expresses that relationship geometrically; symbolic reasoning expresses that relationship algebraically. For every geometric expression of semantics, there is some corresponding algebraic one — which we can view as the “internal language” of the DNN.
The semantics of a system is mapping the topology of the input space to output space.
DL expresses that relationship geometrically; symbolic reasoning expresses that relationship algebraically. For every geometric expression of semantics, there is some corresponding algebraic one — which we can view as the “internal language” of the DNN.