= The missing link between continuous and discrete AI
<Ciro Santilli> has felt that perhaps what is missing in 2020's <AGI> research is:
* the interface between:
* the continuous/noisy level (now well developed under <artificial neural network> techniques of the 2010's)
* and <symbolic AI> level AI
The key question is somewhat how to extract symbols out of the space-time continuous experiences.
* more specialized accelerators that somehow interface with more generic <artificial neural networks>. Notably some kind of speialized processing of spacial elements is obviously hardcoded into the brain, see e.g. <grid cell>{full}
Forcing these boundaries to be tested was one of the main design goals of <Ciro's 2D reinforcement learning games>.
In those games, for example:
* when you press a button here, a door opens somewhere far away
* when you touch certain types of objects, a chemical reaction may happen, but not other types of objects
Therefore, those continuous objects would also have "magic" effects that could not be explained by "simple" "what is touching what" ideas.
Bibliography:
* https://mitpress.mit.edu/9780262632683/the-algebraic-mind/