The fact that you can selectively turn off parts of cortex (e.g. via cooling) and the brain keeps working fine with only very specific deficits probably tells us all we need to know about the importance of backprop in biological learning.
-
-
And I am pretty sure I could construct memory ANNs that will be ok for non-memory tasks if you remove the memory module.
-
But here is something that DNNs can't currently do and we should teach them: mental rehearsing. I can simulate my body, or my visual system, or my auditory system, or my pathfinding system, or my high level planning system, by itself, at varying simulation speed. And fix them.
- Još 9 drugih odgovora
Novi razgovor -
-
-
Can't we just make the generalization that different parts of the brain are in conversation with other parts and then perform the necessary credit assignment to adjust its subsequent behavior? Why can't we just accept BP for parts of the brain but not across the entire brain?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
