[neuronerd]

In a range of domains, in particular higher level brain areas, DL models trained on imagine are already the best predictive models of brain function. If they are better than all other models at describing the data, why would we say they have nothing to do with neuroscience?

[briga]

As far as I know there is no evidence that the brain has any analogue to the back-propagation used to train pretty much all modern neural networks. Back-propagation is a good way to optimize neural networks, but it doesn't seem to be the way brains optimize neural networks.

[neuronerd]

well, the original paper has a pretty good summary of how the brain may actually do backdrop.

[joycian]

What do you mean by "original paper" here?

[canjobear]

DL models are also the best way to predict the behavior of three-body systems in physics. Would you say DL models tell us something about physics?

[etbebl]

You're talking about the output of a deep network predicting the solution to a problem it was trained on. They're talking about something completely different: the properties of the whole network (opening up the "black box") correlating with/predicting properties of brain regions while they perform similar tasks.

[mistrial9]

because any set of math functions might do really well at predicting within a certain domain, and then produce noise or worse with new cases outside of the trained area.. perhaps more importantly, from a psychological point of view, a substitution error by humans, of replacing one not-understood system (mind) with another (black box training via NNs) is common and may be incentivized, too