Sign in

Brad Aimone

@jbimaknee.bsky.social
651 followers 162 following 372 posts

Computational neuroscientist-in-exile; computational neuromorphic computing; putting neurons in HPC since 2011; dreaming of a day when AI will actually be brain-like.

PostsRepliesMedia
Brad Aimone @jbimaknee.bsky.social · 07/08/2026
BlueSky has been trying to enforce some awkward age verification on Texas residents, so I couldn't log in until I was in Chicago for ICONS this week. Lo and behold, there are many neuroscience posts about new findings... of things that people have known forever. We really are the Sisyphus field🧠🧪🤖
021
Brad Aimone @jbimaknee.bsky.social · 15/04/2026
AnD tHe BRaiN is JuST liKe aN AnN... JusT... goTTa ... FINd ... tHe ... bACkpRop... Seriously though... Neuromodulators are cooler than anything anyone in NeuroAI gives them credit for. Maybe norepinephrine and the LC's few hundred neurons is actually all you need.
020
Brad Aimone @jbimaknee.bsky.social · 04/04/2026
We should fund science more not less. But the cynical part of me thinks this is an opportunity to maybe stop funding the same neuroscience questions with just a fancier microscope or just one region over time and time again. We need to cure diseases and fix AI. Not keep doing the same thing.
020
Brad Aimone @jbimaknee.bsky.social · 23/02/2026
Excited to be in San Antonio for the UTSA AI Matrix THOR Neuromorphic Commons kickoff! THOR will be one of the first community resources fully dedicated for accessing scalable neuromorphic hardware! Check it out! #NeuroAI #Neuromorphic 🧪🧠🤖 www.neuromorphiccommons.com/events/thor_...
040
Brad Aimone @jbimaknee.bsky.social · 09/02/2026
Am I alone in being skeptical when seeing "We need WORLD MODELS because that's what the BRAIN does!"? Won't this just be another 'AI tech bros use the brain to get attention and $$$ but ignore it at the first opportunity'? Why trust any of the AI crowd to talk about the brain? We need real #NeuroAI
000
Brad Aimone @jbimaknee.bsky.social · 26/01/2026
Maybe cynical, but any time a scientist says "We should leave AI to industry" it is because they are scared about $$ going to something they don't work on I've heard for >10 years "let industry lead" and we have LLMs, power plants & data centers #NeuroAI needs research, not just venture capital
150
Brad Aimone @jbimaknee.bsky.social · 01/01/2026
My prediction / hope for 2026: this will be the year we start seeing the theoretical neuroscience and #NeuroAI fields start embracing spiking as something beyond a poor man's ReLU. Spikes aren't just the brain's activation function but they are fundamentally different. 1/ 🧠🧪🤖
2355
Brad Aimone @jbimaknee.bsky.social · 26/11/2025
I find it annoying that people who for many years have been at the forefront of "Scale, baby, scale!" are now lecturing on the importance of actually thinking. There is a community of people who have been thinking all along. Without expending terawatt-hours of electricity for no good reason
020
Brad Aimone @jbimaknee.bsky.social · 25/11/2025
This gets to the heart of a big problem in neuroscience. Since we don't have a formal model of neural computation and since everything is important to people who study it, we are trapped in this "but my thing matters too!" mode Prioritization of what is important is necessary, even if harsh
120
Brad Aimone @jbimaknee.bsky.social · 20/11/2025
I can't stop reading Konrad's thread here, and it just drives something home that I'm increasingly appreciating: Neuroscientists really really really REALLY want the brain to be low dimensional. So much so that the low dimensionality is often assumed, and as Konrad gets to here, that causes problems
1164
Brad Aimone @jbimaknee.bsky.social · 19/11/2025
Konrad is doing an amazing take-down here, and at least on this point I fully agree. The "brain is analog" argument is a terrible strawman that holds back neuro. Analog dynamics may help, but the theoretical scaling of neurons mostly come from event-driven parallelism. arxiv.org/abs/2507.17886
arxiv.org
Neuromorphic Computing: A Theoretical Framework for Time, Space, and Energy Scaling
Neuromorphic computing (NMC) is increasingly viewed as a low-power alternative to conventional von Neumann architectures such as central processing units (CPUs) and graphics processing units (GPUs), h...
141
Brad Aimone @jbimaknee.bsky.social · 16/11/2025
Our paper on a neuromorphic algorithm for solving finite element models is out, which is exciting for a number of reasons. But really I want to talk a bit about how this relates to understanding the brain and #NeuroAI. 🤖🧪🧠🧵 1/ www.nature.com/articles/s42...
nature.com
Solving sparse finite element problems on neuromorphic hardware - Nature Machine Intelligence
Theilman and Aimone introduce a natively spiking algorithm for solving partial differential equations on large-scale neuromorphic computers and demonstrate the algorithm on Intel’s Loihi 2 neuromorphi...
193
Brad Aimone @jbimaknee.bsky.social · 15/11/2025
Nothing like flying out of a city when all the SfN folks are flying in. Satellite meetings are where it's at. 3 over 3 days was a little intense. But smaller meetings are more fun. Enjoy SfN everyone!
000
Brad Aimone @jbimaknee.bsky.social · 02/11/2025
I was amused to find myself quoted, kind of, in the last paragraph of this; don't know if I've ever been the punchline quote before!
020
Brad Aimone @jbimaknee.bsky.social · 21/09/2025
This is a great thread, and I think it hits on one of the biggest challenges in neuroscience that I hope NeuroAI can impact. Until we can rigorously define what computations are occurring in the brain, we can't make any real progress in our functional understanding. We need constraints. 🧠🤖🧪
2172
Brad Aimone @jbimaknee.bsky.social · 26/08/2025
We put the FlyWire connectome on the Loihi 2 neuromorphic platform 🤖🧠🧪🪰 arxiv.org/abs/2508.16792
arxiv.org
Neuromorphic Simulation of Drosophila Melanogaster Brain Connectome on Loihi 2
We demonstrate the first-ever nontrivial, biologically realistic connectome simulated on neuromorphic computing hardware. Specifically, we implement the whole-brain connectome of the adult Drosophila ...
092
Brad Aimone @jbimaknee.bsky.social · 15/08/2025
An interesting comment and discussion that gets to the deeper question of whether NeuroAI is a move towards something new or repackaging of old tired approaches with a shiny AI paint job.
220
Brad Aimone @jbimaknee.bsky.social · 13/08/2025
Traffic in Seattle is really bad...
000
Brad Aimone @jbimaknee.bsky.social · 09/08/2025
I'm a big fan of computing with neurons, stem cells, organoids, and energy efficient AI. But we really have to stop coming up with systems (bio or inorganic) that are a few thousand neurons and claiming wins. AI models have BILLIONS of neurons. GPUs are quite efficient for the models they run 🤖🧠🧪
281
Reposted by Brad Aimone
Dan Goodman @neural-reckoning.org · 07/08/2025
Spiking neural networks people, this message is for you! The annual SNUFA workshop is now open for abstract submission (deadline Sept 26) and (free) registration. This year's speakers include Elisabetta Chicca, Jason Eshraghian, Tomoki Fukai, Chengcheng Huang, and... you? snufa.net/2025/ 🤖🧠🧪
snufa.net
SNUFA 2025
Spiking Neural networks as Universal Function Approximators
23216
Brad Aimone @jbimaknee.bsky.social · 29/07/2025
For a few years I have said that neuromorphic is specialized general purpose, like GPUs, but with different advantages. In this preprint I try to put some substance to that claim. There are real theoretical advantages, but they aren't obvious. 🧪🧠🤖 www.arxiv.org/abs/2507.17886
arxiv.org
Neuromorphic Computing: A Theoretical Framework for Time, Space, and Energy Scaling
Neuromorphic computing (NMC) is increasingly viewed as a low-power alternative to conventional von Neumann architectures such as central processing units (CPUs) and graphics processing units (GPUs), h...
2386
Brad Aimone @jbimaknee.bsky.social · 20/07/2025
This is an interesting thread getting to th heart of the neuroscience / AI disconnect. I think we need better "comp neuro for dummies" options, but there is a widely held view among engineers and computing people that neuroscientists obsess over details for no reason.
1130
Brad Aimone @jbimaknee.bsky.social · 03/06/2025
Dear editors: If you want me to review a paper, give me a form with two entries: comments for authors, optional comments for editor. Maybe (maybe) ask for accept/revise/reject recommendation, but that is really your job. Please don't ask me to answer 12!!! separate questions... 🧪
020
Brad Aimone @jbimaknee.bsky.social · 02/06/2025
Lately my feed has been full of stories like "The brain's learning is more complex than Hebb thought!" and "Does the adult brain have new neurons?". Hebb was almost 100 years ago and the neurogenesis "debate" is 30 years old. We are worse than Hollywood in terms of rehashing the same old stories 🧠🧪
091
Brad Aimone @jbimaknee.bsky.social · 15/05/2025
Bill Dally presenting the rise in necessary compute for AI I see why this is good for Nvidia. But why would this be considered good for anyone else?
010
Brad Aimone @jbimaknee.bsky.social · 15/05/2025
At the @cra-hq.bsky.social CCC Computing Futures Symposium this week - exciting (and interesting) times to be talking about the future of computing research! As part of this event, last night we demo'd neuromorphic and its potential impact on ModSim and #NeuroAI at the US Senate!
010
Brad Aimone @jbimaknee.bsky.social · 12/05/2025
With the demise of Twitter, I greatly miss the often critical but honest takes on new results. LinkedIn's AI community is all hype and often wrong. I would like to see Bsky prioritize honesty and truth over becoming an echo chamber, particularly with #NeuroAI new results that risk being misused 🧠🧪🤖
072
Brad Aimone @jbimaknee.bsky.social · 07/05/2025
This RealID chaos is so strange. I am quite certain I have had a compliant ID for about 10, maybe even 15 years. What is going on that some states are so backwards that they can't figure this out? And I used to live in some pretty dysfunctional states that could even mange this.
000
Brad Aimone @jbimaknee.bsky.social · 29/04/2025
I'm unsure whether I agree with this. On the one hand, questions matter the most. On the other hand, I'm not convinced we (as neuroscientists) know the right questions to ask.
000
Brad Aimone @jbimaknee.bsky.social · 23/04/2025
I'm not a fan of either, but at least with "ANNs to describe the brain" the idea is new. For 50+ years physicists have been trying to shoehorn the brain into mean field approaches with little justification beyond "it would be so convenient" If you don't want to think about the brain, don't study it
000
Brad Aimone @jbimaknee.bsky.social · 04/04/2025
All right world, I think it is time to write...
000
Brad Aimone @jbimaknee.bsky.social · 27/02/2025
Has anyone looked into using LLMs to interpret the information content of words in different languages? For instance, German has many words for 'the' (thus presumably higher information content), and Spanish verbs capture contextual uncertainty much differently than English
110
Brad Aimone @jbimaknee.bsky.social · 13/02/2025
My only comment about NIH indirects is that universities should pay postdocs and grad students more (a direct cost), and maybe-just maybe-seriously looking at where the money is going may eventually end up directing more $ to those who actually do the research.
210
Brad Aimone @jbimaknee.bsky.social · 28/01/2025
If the endless "some people optimized LLMs" news is starting to bore you, check out our preprint on neuromorphic-compatible neural circuits that can solve sparse linear systems. arxiv.org/abs/2501.10526 This opens up some exciting new doors for brain-like algorithms! 🧪🧠🤖 #NeuroAI #Neuromorphic
2255
Brad Aimone @jbimaknee.bsky.social · 24/01/2025
I've never been directly funded by NIH, but in honor of this amazing organization with great people, here is my talk from last fall when they hosted me. One of the best visits I have had anywhere. oir.nih.gov/wals/2024-20...
oir.nih.gov
How Neuromorphic Computing Can Help Us Understand the Brain | NIH Office of Intramural Research
051
Brad Aimone @jbimaknee.bsky.social · 23/01/2025
I'm very excited that this review on scalable neuromorphic hardware, headed up by Dhireesha Kudithipudi, has finally come out in Nature🧪🧠🤖 rdcu.be/d7atq Neuromorphic hardware is ready for prime time. There are things to keep advancing, but I think the bigger opportunities lie in how we use it!
rdcu.be
Neuromorphic computing at scale
Nature - Approaches for the development of future at-scale neuromorphic systems based on principles of biointelligence are described, along with potential applications of scalable neuromorphic...
0248
Brad Aimone @jbimaknee.bsky.social · 09/01/2025
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. 🧪🧠🧵
6205
Brad Aimone @jbimaknee.bsky.social · 24/12/2024
Nothing like journals pre-emptively guilting about reviews due on December 26th...
000
Brad Aimone @jbimaknee.bsky.social · 20/12/2024
People may enjoy this 🧵 about why scale matters for adult neurogenesis. An oldie paper that probably has meaning for machine learning and #NeuroAI today. 🧪🧠💻
050
Brad Aimone @jbimaknee.bsky.social · 19/12/2024
We have a News and Views in Nature Computational Science with a back of envelope estimate on how expensive whole brain neural simulations can be. 🧠🧪 Long story short... very very expensive This maybe ends up behind a pay wall (sorry ...), but check it out! www.nature.com/articles/s43...
nature.com
On the path toward brain-scale simulations - Nature Computational Science
Today’s high-performance computing systems are nearing an ability to simulate the human brain at scale. This presents a new challenge: going forward, will the bigger challenge be the brain’s size or i...
5157
Brad Aimone @jbimaknee.bsky.social · 18/12/2024
Has anyone applied the Stanford Marshmallow experiment to academic disciplines? In particular it seems highly relevant re. the penchant of comp sci and EE for conference papers with shallow results over more impactful journal papers that take more work but clearly have greater staying power. 🧪🧠
080
Brad Aimone @jbimaknee.bsky.social · 18/12/2024
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 🧠🧪
092
Brad Aimone @jbimaknee.bsky.social · 15/12/2024
One of my worries about #NeuroAI is that if it gets defined too broadly the AI bros will just steal it as a marketing term for their near-term optimizations of commercial apps. NeuroAI requires the brain. Being lazy and ignoring the brain just because the brain is hard should be out of scope.
4363
Brad Aimone @jbimaknee.bsky.social · 14/12/2024
My new office art
010
Brad Aimone @jbimaknee.bsky.social · 11/12/2024
I don't know what the next wave of AI will be, but I strongly suspect it won't be another "please ignore the nuclear power plant behind the curtain" boondoggle for GPU companies. Efficiency matters. The future of AI is the brain. 🧠🧪 #NeuroAI
0111
Brad Aimone @jbimaknee.bsky.social · 02/12/2024
So cool! But I think neural plasticity has this even this dynamic range beat!
000
Brad Aimone @jbimaknee.bsky.social · 29/11/2024
Any last minute submissions for neuromorphic computing, spiking algorithms, or neural theory? Send them over to NICE 2025, we will be in Heidelberg in March. Deadline in two days! niceworkshop.org/nice-2025/
niceworkshop.org
NICE 2025 – NICE Conference Series
1103
Brad Aimone @jbimaknee.bsky.social · 29/11/2024
072
Brad Aimone @jbimaknee.bsky.social · 27/11/2024
All fields need to do this periodically so that their value proposition can be clearly articulated to the people who provide the funding. Agreeing on goals and the key questions to answer is not the same as prescribing solutions (which is where I think past large neuro efforts tripped up).
250
Brad Aimone @jbimaknee.bsky.social · 22/11/2024
Also, while I'm talking about getting to know neuromorphic... As in the discussion on #NeuroAI, there are a lot of definitions and views of what #neuromorphic is. Not all of it is what neuroscientists would consider brain-inspired (just like not all AI is related to the brain).
161