Profile avatar
braindersnn.bsky.social
Neuromorph at #ProjectPhasor | Ex: Loihi @Intel Labs; MLPerf, TPU, Chrome GPU, Android GPU; HT patch clamp | Runner https://www.project-phasor.org https://www.linkedin.com/in/brian-anderson-6739ba25
62 posts 385 followers 963 following
Regular Contributor
Active Commenter
Posts 19 Comments 31

The main barriers to commercial adoption of #neuromorphic technology in 2025 are not technological — Neuromorphic #processors are already available, with #benchmark #applications in #audio and #vision processing showing massive advantages over conventional processing.

submitted 15 days ago • 1 comment

Our latest ASIC, taped out on Intel’s new 1m process

submitted 33 days ago • 3 comments

Just out in J Neuromorph Comput & Eng: Loss shaping enhances exact gradient learning with Eventprop in Spiking Neural Networks doi.org/10.1088/2634.... With @neworderofjamie.bsky.social. We report how Eventprop scales to harder learning tasks. TL;DR: It works great but not without extra effort. 🧪🧵

submitted 36 days ago • 1 comment

Very exciting this is FINALLY out! Big step in efficient gradient-based training of SNNs

submitted 36 days ago • 0 comments

Pretty sure the “salute” was a well planned troll to distract from the petty stolen valor story where he claimed as his own the skill and hard work of others in a video game and doubled down on the obvious lie. Eyes on the ball ppl…

submitted 36 days ago • 0 comments

Curious - is anyone doing #neuromorphic or #neuroai research directly affected by delayed government funding and willing to share their experience? I’m trying to understand the landscape better to see how much a potential joint research fund of #projectphasor might be able to help…

submitted 47 days ago • 0 comments

I've been watching with amusement the kerfuffle of Nvidia's CEO saying quantum computing is 15+ years away. Setting aside all of the self-interest of the leading GPU company bashing an emerging technology, it is illustrative to think about what it means for neuromorphic technologies and NeuroAI. 🧪🧠🧵

submitted 48 days ago • 6 comments

Friedemann Zenke has joined Bluesky @fzenke.bsky.social. This gives me an opportunity to repost my spiking neurons and neuromorphic starter pack. I've been quietly adding names to it, but I'm sure there are people I've missed so let me know to add you/someone else! 🤖🧠🧪 go.bsky.app/46Eu9GG

submitted 50 days ago • 8 comments

Project Phasor kickoff meetings and small groups are Jan 8-15. Check out this document for details and links to the relevant calendar events: docs.google.com/document/d/1...

submitted 51 days ago • 1 comment

ELI5, Bananas, and what Project Phasor is NOT: Someone asked for an ELI5 on Project Phasor in the Open Neuromorphic discord channel. Expand this thread for my reply. How things actually shape out will depend on the community. Register for our January meetings here: docs.google.com/forms/d/e/1F...

submitted 54 days ago • 1 comment

Register your interest for January Project Phasor meetings to help solve the #NeuroAI and #neuromorphic issues best solved together! forms.gle/LYxu7ru72KmL... #projectphasor

submitted 56 days ago • 1 comment

There's a movement in neuroscience suggesting we should be pursuing bigger bets with larger teams. I think there's a case for doing a bit of this, but I think it's a bad idea to prioritise it for two reasons, and a good case for saying we should be moving in the exact opposite direction. 🧠🧪

submitted 70 days ago • 14 comments

It is kind of amazing the scale and speed of the original neural simulations. We have come a long way from 386 processors and 8 MB of RAM ~35 years ago (Wilson and Bower 88) My PhD work ~20 years ago was 20x more neurons, albeit much simpler, and many more time steps. Today we can sim billions 🧠🧪

submitted 70 days ago • 0 comments

Please don't. Just give 1M to fund 1000 new labs, with potentially 1000 news ideas.

submitted 71 days ago • 3 comments

Here are 5 reasons why Project Phasor proposes a joint #neuromorphic + #neuroAI early-access research fund: If you are interested in being a founding member of such a research fund, please reach out -- you'll get insight into where the future of AI is headed! A thread >>>

submitted 71 days ago • 1 comment

This paper on the usefulness of diversity of neuron types is pretty cool: journals.plos.org/ploscompbiol...

submitted 71 days ago • 6 comments

#NeuroAI workshop #NeurIPS, some highlights Panel w Karl Friston & Yoshua Bengio Keynotes by Karl, @wellingmax.bsky.social @maryamshanechi.bsky.social Eva Dyer, Doina Precup, Rafael Bogacz Terry Sejnowski’s guest appearance at workshop/dinner Joseph Monaco on #NeuroAI NIH/BRAIN >1400 attendees

submitted 72 days ago • 0 comments

Panel at #NeurIPS2024, as part of #NeuroAI workshop, with Karl Friston and Yoshua Bengio, moderated by myself. Recordings available after the event: tinyurl.com/39a9xy8x Workshop: tinyurl.com/5aysw5v3 Moein Khajehnejad @foroughhas.bsky.social @noorsajidt.bsky.social @tonyzador.bsky.social

submitted 74 days ago • 3 comments

Given the #NeuroAI workshop at #NeurIPS2024 is on Saturday, here is a fun poll: T/F: Future NeuroAI learning algorithms will show just how fragile backprop-trained models inherently are. LinkedIn poll here: www.linkedin.com/posts/brian-... NeurIPS NeuroAI workshop info: neurips.cc/virtual/2024...

submitted 75 days ago • 1 comment