Jakob Macke
@jakhmack.bsky.social
#AI4Science #CompNeuro #NeuroAI #SBI
www.mackelab.org @mackelab.bsky.social
· Prof Uni Tuebingen ML4Science BCCN tue.ai
· Adjunct MPI IS · Fellow ellis.eu
· currently hiring postdocs and PhD students
· sometimes goes for a run
www.mackelab.org @mackelab.bsky.social
· Prof Uni Tuebingen ML4Science BCCN tue.ai
· Adjunct MPI IS · Fellow ellis.eu
· currently hiring postdocs and PhD students
· sometimes goes for a run
My point is not that you should include our work — but that more computational folks should actually tackle this wonderful data now that it is abailable, with ML or without (although we certainly have found ML useful)!
June 12, 2025 at 10:11 PM
My point is not that you should include our work — but that more computational folks should actually tackle this wonderful data now that it is abailable, with ML or without (although we certainly have found ML useful)!
Sounds interesting! Loved how your pitch includes the availability of the drosophila connectome, unfortunately none of the abstracts seem to mention it?
June 11, 2025 at 10:26 PM
Sounds interesting! Loved how your pitch includes the availability of the drosophila connectome, unfortunately none of the abstracts seem to mention it?
Oh I am more optimistic and even even excited, one can disect it, and it has interpretable units and sub circuits … we might need better tools though to make it easier for people to play with it!!
June 6, 2025 at 8:41 PM
Oh I am more optimistic and even even excited, one can disect it, and it has interpretable units and sub circuits … we might need better tools though to make it easier for people to play with it!!
was our paper used as evidence for or against this thesis? (My biased view is that this approach shows how one can big data and mechanistic insights can be friends …)
June 6, 2025 at 2:35 PM
was our paper used as evidence for or against this thesis? (My biased view is that this approach shows how one can big data and mechanistic insights can be friends …)
Reposted by Jakob Macke
I always find the figures from the @mackelab.bsky.social really clear and pretty!
For example in arxiv.org/abs/2404.09636.
For example in arxiv.org/abs/2404.09636.
All-in-one simulation-based inference
Amortized Bayesian inference trains neural networks to solve stochastic inference problems using model simulations, thereby making it possible to rapidly perform Bayesian inference for any newly obser...
arxiv.org
June 3, 2025 at 6:17 AM
I always find the figures from the @mackelab.bsky.social really clear and pretty!
For example in arxiv.org/abs/2404.09636.
For example in arxiv.org/abs/2404.09636.
Thanks! Trying to make good figures is an important part of the @mackelab.bsky.social experience ;-). Indeed, this design was initiated by @janmatthis.bsky.social and then passed on and refined by @deismic.bsky.social and others! We still use it, although sometimes in white-on-black for talks ...
June 3, 2025 at 9:49 PM
Thanks! Trying to make good figures is an important part of the @mackelab.bsky.social experience ;-). Indeed, this design was initiated by @janmatthis.bsky.social and then passed on and refined by @deismic.bsky.social and others! We still use it, although sometimes in white-on-black for talks ...