Deep learning is to biological neural systems as quantum theory is to consciousness. @KordingLab @tyrell_turing @tdverstynen @GaryMarcus @GaryMarcus @danilobzdok @kendmil
-
There's a major difference: DL was guided in its infancy by ideas from neuroscience, so there is a relatively direct link between them. In contrast, the application of quantum mechanics to the c-word is taking two distinct fields and tying them together on speculative grounds.
The relation between deep learning - with its single neuron type and largely homogenous architecture - and the actual complexity of the human brain, with > 1000 neuron types, hundreds of proteins at each synapse and > 100 distinct brain regions - is risible.
-
-
In my day job as a neuroscientist, i spend a lot of time thinking about the complexity due to cell types, proteins etc. Some of these details may turn out to be crucial. But we can't be sure which ones (although i do have opinions)
-
for sure we can’t be sure, but to blithely assume that none of those details matter, or eg that deb dries are passive when they obviously aren’t, is folly
- 1 more reply
New conversation -
-
-
Every model is an abstraction. Newtonian mechanics ignores air turbulence, molecular interactions, etc. Climate models capture coarse grained interactions, not the multitude of animals, plants, and wind-currents that truly shape the climate. Neural networks are no different.
-
right, all models are wrong, and each has some value on some dimensions. i think DL is a more useful model for brains than quantum is for consciousness, though i also am scared how similar the two analogies are in kind.
- 1 more reply
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.