Richard Gao (@_rdgao) 's Twitter Profile
Richard Gao

@_rdgao

postdoc @mackelab; machine learning in (neuro)science. 🧠 🌊 💻 tweets are for bad jokes and hot takes exclusively, go to the blog for longer thoughts

ID: 2577855113

linkhttp://www.rdgao.com calendar_today02-06-2014 16:16:58

4,4K Tweet

3,3K Followers

1,1K Following

Richard Gao (@_rdgao) 's Twitter Profile Photo

give a messy problem to people that are great at optimizing for a number and they... *checks notes* successfully optimized for a number. 🤯 (Goodhart's law)

HelfrichLab (@helfrichlab) 's Twitter Profile Photo

Are different sleep stages only defined by neural oscillations? Our new work led by Janna Lendner now out in JNeuro SfN Journals demonstrates that several aperiodic (intrinsic) timescales shape the iEEG power spectrum during sleep: jneurosci.org/content/44/42/… (1/7)

Dan Levenstein (@dlevenstein) 's Twitter Profile Photo

Interesting how we always talk about "academia or industry" as the two alternatives, but certainly "policy" is somewhere we want folks with PhDs and the third thing we should be thinking about students' potential careers in, no?

Machine Learning in Science (@mackelab) 's Twitter Profile Photo

We are looking to hire multiple PhD students on (1) deep learning for mechanistic models of neural computation, (2) simulation-based Bayesian inference, (3) ML for clinical neuroscience. Reach out if you are excited about these topics! Details here: mackelab.org/media/Ad_Macke…

Brandon Munn (@drbmunn) 's Twitter Profile Photo

I am absolutely stoked to share our new study on multiscale neural dynamics across species and behaviour + network simulations exploring their benefits! The best lab going around! Captained by THE Mac Shine 🙌

I am absolutely stoked to share our new study on multiscale neural dynamics across species and behaviour +  network simulations exploring their benefits! The best lab going around! Captained by THE <a href="/jmacshine/">Mac Shine</a> 🙌
sbi developers (@sbi_devs) 's Twitter Profile Photo

The sbi package is growing into a community project 🌎 To reflect this and the algorithms, neural nets, and diagnostics that have been added since its initial release, we have written a new software paper. Reach out if you want to get involved: arxiv.org/abs/2411.17337

Machine Learning in Science (@mackelab) 's Twitter Profile Photo

Thrilled to announce we have three #NeurIPS2024 papers! Interested in simulating realistic neural data with diffusion models or recurrent neural networks, or in source distribution sorcery? Have a look 👇 1/4

Guy Moss (@guymoss13) 's Twitter Profile Photo

Julius Vetter (on Bluesky) and I are excited to present our work at #Neurips2024! We present Sourcerer: a maximum-entropy, sample-based solution to source distribution estimation. Paper: openreview.net/forum?id=0cgDD… Code: github.com/mackelab/sourc… (1/8)

Richard Gao (@_rdgao) 's Twitter Profile Photo

the latest and greatest installment on our mission to generate really good counterfeit neural recordings... now with latents! (which makes it both AI4Neuro and neuroAI)

Cole Hurwitz (@cole_hurwitz) 's Twitter Profile Photo

Come checkout our poster at #NeurIPS2024 😀 We are presenting a new approach for pretraining neurofoundation models that can learn interactions between brain areas.

Come checkout our poster at #NeurIPS2024 😀 We are presenting a new approach for pretraining neurofoundation models that can learn interactions between brain areas.
Richard Gao (@_rdgao) 's Twitter Profile Photo

now that neurips 2024 is over, I can confidently say that this was by far the most unhinged poster I saw (and also my favorite).