That's why I had the ~ sign in front of ~everybody (and it is anyway somewhat facetious since both communities seem quite small)! And certainly a handful or two of others still working on it. But we agree there is a major shift in the overall zeitgeist...
-
New conversation
-
-
True, but those constraints are hard to use to get new ML to scale. So far we published this at NeurIPS: http://arxiv.org/abs/1911.05072v1 …, but it helps only robustness not raw performance. Robustness IS a kind of generalization, but we’re not yet going far from training data.
-
Functional connectome for mouse visual cortex (1mm^3 of V1,LM,AL,RL) is coming soon
@AToliasLab@viajake@AllenInstitute@SebastianSeung. Should have many good constraints! But we still don’t have a good way of measuring in vivo synaptic plasticity at scale. Maybe@IsacoffLab? - 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.