←
Niru Maheswaranathan1,788 posts
Niru Maheswaranathan avatar

Niru Maheswaranathan

@niru_m
◷ Joined March 2009▧ 93 Photos and videos
AI at Meta avatar
⟳ Niru Maheswaranathan retweeted
AI at Meta@AIatMeta·23 Jul 2025

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/s41586-0… Find more details on this work and the models on @github: github.com/facebookresearch/…

1:03
Niru Maheswaranathan avatar
Niru Maheswaranathan@niru_m·25 May 2021

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! 🧠 💪

Niru Maheswaranathan avatar
Niru Maheswaranathan@niru_m·1 May 2021

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!

A classic kinematics example—a pillbug on a spinning disk walks back and forth on (what it thinks is) a straight path. However, its trajectory looks much more complicated and beautiful to a stationary observer!

Daniel Freeman avatar
⟳ Niru Maheswaranathan retweeted
Daniel Freeman@bucketofkets·26 Feb 2021

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

Niru Maheswaranathan avatar
Niru Maheswaranathan@niru_m·16 Feb 2021

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!

New preprint alert! We show that predictive coding is an emergent property of input-driven RNNs trained to be energy efficient. No hierarchical hard-wiring required. A thread: 1/ biorxiv.org/content/10.1101/…

Niru Maheswaranathan avatar
Niru Maheswaranathan@niru_m·12 Jan 2021

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!

This tweet is unavailable