If you need an escape from politics right now, I'm giving a talk at the DeepMath conference (deepmath) this afternoon (2:20pm PST) on understanding the dynamics of learned optimizers. There is a livestream: youtube.com/watch?v=x-VPsH… - the talks so far have all been fantastic!

Awesome work! Congrats Basile Confavreux et al!

Really enjoyed this post on Stein's paradox! The writing is impressively clear.

Are Experts Real? Some thoughts on expertise, credentialism, and feedback loops. fantasticanachronism.com/2021/01/11/are…

The only reason this image is “powerful” is as a reminder of how misleading data visualization can be. It uses a diverging colormap for sequential data, and caps the range at 4% so the UK pops out as if they’ve vaccinated a majority of citizens. Good example of what *not* to do!

Cool result: minimizing activation norms in a network (a proxy for energy efficiency) in a predictable environment yields a network that learns aspects of predictive coding. Would love to see what happens in richer environments and with deeper architectures!

QC taylor expansions are the turtles in the turtles all the way down joke except it isn’t a joke

"Intuition is the foundation upon which comprehensive understanding is built. But ... unverified intuition can be misleading." A fantastic article on rigorous interpretability research by Matthew Leavitt and Ari Morcos (arxiv.org/pdf/2010.12016…) h/t Kording Lab 🦖 for highlighting it!

Often in science something seems complicated until you look at it the right way. The hard part is figuring out the right frame of reference!

Some personal news: I recently joined Facebook Reality Labs, working on neural interfaces research with the CTRL labs team. Sad to leave fantastic colleagues at Google Brain, but looking forward to a new challenge! 🧠 💪

Interesting paper making connections between representational drift in biological brains and dropout in ANNs!

This gradient might look good in expectation, but what about the variance? 🤔

Heading to Lisbon for #cosyne2022! Looking forward to talking science in person!

cc Alex Williams

1/Our paper Neuron "Interpreting the retinal code for natural scenes" develops explainable AI (#XAI) to derive a SOTA deep network model of the retina and *understand* how this net captures natural scenes plus 8 seminal experiments over >2 decades sciencedirect.com/science/articl…

I'm incredibly saddened today to hear about the passing of Prof. Craig Henriquez, one of my first research advisors when I was an undergrad. Craig was an incredible mentor, scientist, and compassionate human being; he will be deeply missed. today.duke.edu/2023/08/craig-…

How long until there is a feature length film that is completely AI generated? I’m guessing ~2028

Excited to speak with this fine gang in St Louis next month, including @neurograce Karim Jerbi Niru Maheswaranathan Martin Schrimpf Chethan Pandarinath Xue-Xin Wei Carlos R. Ponce . Bring on the future of NeuroAI! transdisciplinaryfutures.wustl.edu/events/neuroai…

We’re thrilled to see our advanced ML models and EMG hardware — that transform neural signals controlling muscles at the wrist into commands that seamlessly drive computer interactions — appearing in the latest edition of nature. Read the story: nature.com/articles/s4158… Find