Re:Neural Networks and the Chomsky Hierarchy [DeepMind, 2022]
by naasking on Monday January 23, 2023 @09:43AM
(#34489292)
> In other words, when you have reasonably big practical finite problem with limited memory. FSA runs quickly out of memory.
Yes this is a difference in the expressiveness of each model, because FSAs can require a combinatorial explosion in the number of states to model a finite Turing machine. The parent is still technically correct though.
Yes this is a difference in the expressiveness of each model, because FSAs can require a combinatorial explosion in the number of states to model a finite Turing machine. The parent is still technically correct though.