iiinova — where your digital self keeps evolving

Jonathan Cornford @repromancer.bsky.social · 17/04/2026

Highly recommend working with Dan!

Reposted by Jonathan Cornford

Matt Perich @mattperich.bsky.social · 13/08/2025

🚨 I’m excited to say that my CIHR Project Grant was funded! My NHP lab is now full-speed-ahead, and I’m hiring experimentalists (postdoc, PhD student, and/or a tech/manager). We’ll do multi-region ephys during reaching/grasping in macaques, with behavioral and spinal perturbations.

28425

Reposted by Jonathan Cornford

Claudia Clopath Lab @clopathlab.bsky.social · 23/07/2025

Trying to train RNNs in a biol plausible (local) way? Well, try our new method using predictive alignment. Paper just out in Nat. Com. Toshitake Asabuki deserves all the credit! www.nature.com/articles/s41...

nature.com

15716

Jonathan Cornford @repromancer.bsky.social · 17/07/2025

I’ve just had a grant costed at 1.7x salary at Leeds. And I, clearly mistakenly, thought that must be pushing the limits..

010

Reposted by Jonathan Cornford

Mark D Humphries @markdhumphries.bsky.social · 11/07/2025

Fabulous day at UK Neural Computation 2025! Thanks to today’s invited speakers Jonathan Cornford, Jenny Bizley, Petr Znamenskiy and Flavia Mancini Congratulations to ECR speakers Ian Hawes and Andrea Colins Rodriguez, selected from 80+ outstanding abstract submissions Roll on Day 3! #UKNC25

093

Reposted by Jonathan Cornford

Blake Richards @tyrellturing.bsky.social · 09/07/2025

Together with @repromancer.bsky.social, I have been musing for a while that the exponentiated gradient algorithm we've advocated for comp neuro would work well with low-precision ANNs. This group got it working! arxiv.org/abs/2506.17768 May be a great way to reduce AI energy use!!! #MLSky 🧪

arxiv.org

Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks

Studies in neuroscience have shown that biological synapses follow a log-normal distribution whose transitioning can be explained by noisy multiplicative dynamics. Biological networks can function sta...

33913

Jonathan Cornford @repromancer.bsky.social · 30/06/2025

Very much agree with you that they have these troubles, and are important to focus on. But I think the disagreement becomes about strength of evidence (not no evidence) which is largely an emotional call. Hence why we need a peer review jury! :)

000

Jonathan Cornford @repromancer.bsky.social · 30/06/2025

So, being provocative, I’d ask if any of the qualitatively different approaches you mention can learn non-trivial things (which has to be important for a model of the mind). I agree with you re explaining (see above). But the point is our best model of intelligence also v naturally shares redundancy

110

Jonathan Cornford @repromancer.bsky.social · 30/06/2025

The neuropsych observations are interesting and valid, but aren’t inconsistent with PDP models. They could (imo do) just point to learning dynamics & resource pressures shaping the circuitry. Combined with PDP they generate hypothesis that can be tested. And this is true of other model approaches.

110

Jonathan Cornford @repromancer.bsky.social · 30/06/2025

I’m a bit confused reading this. Redundancy e.g. to cell loss is not a smoking gun but it certainly is evidence *supporting* PDP models as being a good model of the brain. If the reverse was true we would v likely discard ANNs as models as redundancy is such a basic issue in experimental neuro.

210

Reposted by Jonathan Cornford

Mark D Humphries @markdhumphries.bsky.social · 25/06/2025

Closing soon! Register by July 1st for UK Neural Computation 2025 neuralcomputation.uk ECR day: 9 July - careers, grants, starting a lab Main meeting: 10-11 July - 13 speakers, 70+ posters, sandpit Hosted by @imperialcollegeldn.bsky.social Sponsors @aria-research.bsky.social @crick.ac.uk

neuralcomputation.uk

UKNC25 |

012

Reposted by Jonathan Cornford

Danyal Akarca @danakarca.bsky.social · 18/06/2025

Excited for the UK Neural Computation Conference 2025 @ Imperial, 9th - 11th July! 🚀 World leading scientists working in brain computation - from experimental to modelling, mathematics & ML (+ all combinations thereof). Registration closes 1st July! Plz share: neuralcomputation.uk

1126

Reposted by Jonathan Cornford

Friedemann Zenke @fzenke.bsky.social · 27/05/2025

1/6 Why does the brain maintain such precise excitatory-inhibitory balance? Our new preprint explores a provocative idea: Small, targeted deviations from this balance may serve a purpose: to encode local error signals for learning. www.biorxiv.org/content/10.1... led by @jrbch.bsky.social

518257

Reposted by Jonathan Cornford

Aaron Milstein @neurosutras.bsky.social · 27/05/2025

New #NeuroAI #compneurosky preprint! To better understand how target-directed learning works in the brain, we sought to engineer an artificial neural network capable of solving complex image classification tasks that comprises only experimentally-supported biological building blocks. (1/15)

15719

Jonathan Cornford @repromancer.bsky.social · 25/04/2025

Can I register without booking a room? I’m based in Leeds!

100

Reposted by Jonathan Cornford

Dr Sasha Luccioni @sashamtl.bsky.social · 02/04/2025

Discussions around AI ethics and sustainability tend to happen in different circles, with different people and from different perspectives... but what if we had these important conversations together? 🤝

1237

Reposted by Jonathan Cornford

Nanda H Krishna @nandahkrishna.bsky.social · 05/04/2025

Really enjoyed TAing for this tutorial, had great discussions with several attendees. Do check out `torch_brain` and the other packages here: github.com/neuro-galaxy

github.com

Neuro Galaxy

Foundation models for neural data. Neuro Galaxy has 5 repositories available. Follow their code on GitHub.

0193

Reposted by Jonathan Cornford

Arna Ghosh @arnaghosh.bsky.social · 01/04/2025

Are you training self-supervised/foundation models, and worried if they are learning good representations? We got you covered! 💪 🦖Introducing Reptrix, a #Python library to evaluate representation quality metrics for neural nets: github.com/BARL-SSL/rep... 🧵👇[1/6] #DeepLearning

3279

Jonathan Cornford @repromancer.bsky.social · 29/03/2025

Come by Poster 068 to learn about why comp neuro studies should use exponentiated gradient descent!

1222

Jonathan Cornford @repromancer.bsky.social · 27/03/2025

Yes exactly! Not sure how it would play out in implementation. But I can see a role in providing an enriched learning objective for a mech model as the foundation model has extracted and compressed into a representation what is meaningful in the neural data.

020

Jonathan Cornford @repromancer.bsky.social · 27/03/2025

Do you see a usecase in distilling the neural-structure understanding of foundational models into a mechanistic model?

130

Jonathan Cornford @repromancer.bsky.social · 21/03/2025

Can you point me to one or two? I don’t see anywhere where you say why language isn’t one? My take is that language is compressing information about the world. Eg take a newspaper article. How is that not an encoding of reality?

000

Jonathan Cornford @repromancer.bsky.social · 20/03/2025

You don’t view language as an encoding of the world? Obviously there are differences to sense inputs, but that seems pretty obvious to me. I presume this been hashed out and argued about before though? What do you disagree with?

100

Jonathan Cornford @repromancer.bsky.social · 20/03/2025

Am I missing something? If language is an encoding of the world, just like pixel values are, and sensory input in general is, why can’t an llm in principle do all of the above just in an RL-like setting? And then we’re just debating how much of the cake the RL cherry is?

110

Reposted by Jonathan Cornford

Claudia Clopath Lab @clopathlab.bsky.social · 20/03/2025

The Clopath Lab has a fully funded PhD position open for Oct in Computational Neuroscience at Imperial College London. If you are interested, just send us an informal e-mail!

22019

Reposted by Jonathan Cornford

Shahab Bakhtiari @shahabbakht.bsky.social · 14/03/2025

📢 We have a new #NeuroAI postdoctoral position in the lab! If you have a strong background in #NeuroAI or computational neuroscience, I’d love to hear from you. (Repost please) 🧠📈🤖

25940

Jonathan Cornford @repromancer.bsky.social · 14/02/2025

¯\_(ツ)_/¯ All press is good press

030

Jonathan Cornford @repromancer.bsky.social · 14/02/2025

Sad to see in my opinion. AI Safety & Security was also possible.

140

Reposted by Jonathan Cornford

Dan Goodman @neural-reckoning.org · 11/02/2025

I'm giving an online talk tomorrow as part of UCL's NeuroAI series on neural architectures and our current line of research trying to figure out what they might be good for (including some philosophy: what might an answer to this question even look like?). www.eventbrite.co.uk/e/ucl-neuroa...

eventbrite.co.uk

UCL NeuroAI Talk Series

A series of NeuroAI themed talks organised by the UCL NeuroAI community. Talks will continue on a monthly basis.

0429

Jonathan Cornford @repromancer.bsky.social · 28/01/2025

Is there an agreed "this email was schedule sent" time? I'm thinking 8.49 am

030

Reposted by Jonathan Cornford

Yiota Poirazi @yiotapoirazi.bsky.social · 25/01/2025

Spiros Chavlis and I are very excited to share our latest #dendritic ANN research published in Nature Comms. @natureportfolio.bsky.social. We show that adopting the structure and sparse sampling features of biological #dendrites makes ANNs accurate, highly efficient and robust to overfitting.

04211

Reposted by Jonathan Cornford

Brokoslaw Laschowski @drlaschowski.bsky.social · 13/01/2025

Talk by Blake Richards at the Montreal AI and Neuroscience (MAIN) Conference on brain-like learning with exponentiated gradients. www.youtube.com/watch?v=Awji... #neuroscience #neuroAI #AI #compneuro @tyrellturing.bsky.social

youtube.com

Blake Richards - Brain-like learning with exponentiated gradients

YouTube video by MAIN Conference

0298

Reposted by Jonathan Cornford

Guillaume Lajoie @glajoie.bsky.social · 09/01/2025

Long time coming. A very cool project that showcases the advantages of single neuron adaptation in RNNs. #PLOSCompBio: Neural networks with optimized single-neuron adaptation uncover biologically plausible regulari ... dx.plos.org/10.1371/jour... Props to V. Geadah and co-authors!

dx.plos.org

Neural networks with optimized single-neuron adaptation uncover biologically plausible regularization

Author summary Evolution has shaped neural circuits in the brain to support complex tasks and behavior. In doing so, single neurons have developed intriguing coding properties such as heterogeneous an...

03410

Reposted by Jonathan Cornford

Rui Ponte Costa @somnirons.bsky.social · 02/01/2025

🚨Our paper on how the cerebellum learns to drive cortical dynamics for rapid task learning and switching, which we propose can then be consolidated in the cortex @naturecomms.bsky.social nature.com/articles/s41... 🧠 #compneuro

14915

Jonathan Cornford @repromancer.bsky.social · 18/12/2024

I’m a bit surprised at how much attention and controversy that slide generated 🤷‍♂️

010

Jonathan Cornford @repromancer.bsky.social · 18/12/2024

So I’m not sure this is true for the majority of current NeurIPS attendees. Maybe I’m wrong but I think neuro as one’s main motivation would be unusual, and I think that slide is good for dialogue between fields. But mainly I just like how there’s no secret sauce.

110

Jonathan Cornford @repromancer.bsky.social · 18/12/2024

Great to see: “The goal of the Frugal AI Challenge is to encourage both academic and industry actors to keep efficiency in mind when deploying AI models.” Given the constraints of the brain, I’m excited to see if & how neuroscience inspired approaches can contribute here too. #NeuroAI 🧪

030

Reposted by Jonathan Cornford

Dr Sasha Luccioni @sashamtl.bsky.social · 18/12/2024

Today we’re launching the text challenge of the Frugal AI Challenge for the AI Action Summit: detecting climate misinformation in the media (Press, TV, Radio), sponsored by the French non-profit QuotaClimat. The goal of the task is to detect climate-based misinformation and to categorize its type 📃

1267

Jonathan Cornford @repromancer.bsky.social · 18/12/2024

IMO the brilliance lies in not killing your drive because of a known imperfect idea: “If you *allow* yourself to believe, … it gives confidence" (to work on ANNs). Worms are graded, we use spikes: should we worry about the details when waking in morning?

120

Reposted by Jonathan Cornford

Erin Grant @eringrant.me · 13/12/2024

If you missed it at the #NeurIPS2024 posters! Work led by @leonlufkin.bsky.social on analytical dynamics of localization in simple neural nets, as seen in real+artificial nets and distilled by @aingrosso.bsky.social @sebgoldt.bsky.social. Leon is a fantastic collaborator + looking for PhD positions!

Leon presenting poster at the NeurIPS poster session to an intrigued audience

1223

Reposted by Jonathan Cornford

Arna Ghosh @arnaghosh.bsky.social · 13/12/2024

The problem with current SSL? It's hungry. Very hungry. 🤖 Training time: Weeks Dataset size: Millions of images Compute costs: 💸💸💸 Our #NeurIPS2024 poster makes SSL pipelines 2x faster and achieves similar accuracy at 50% pretraining cost! 💪🏼✨ 🧵 1/8

23010

Jonathan Cornford @repromancer.bsky.social · 04/12/2024

Definitely. And also an energy consumption label like electrical devices. en.m.wikipedia.org/wiki/Europea...

020

Jonathan Cornford @repromancer.bsky.social · 29/11/2024

Delighted to be in Leeds joining the School of Computing! Fantastic first impressions — like a "less offensive London" (youtu.be/watch?v=_6_VVLgrgFI). Stay tuned for a PhD position starting next October. Meanwhile, drop me a message with your CV and research interests—I'd love to hear from you!

0349

Jonathan Cornford @repromancer.bsky.social · 22/11/2024

Yes I think it is going to be a fun challenge understanding how to make the optimisation problem easier (typically done using scale and A2A connections) using a combo of developmental & sleep inspired activity programs, unsupervised learning rules, and sparse connectivity patterns.

050

Jonathan Cornford @repromancer.bsky.social · 11/11/2024

Sad to have been unable to join. Are recordings of this available?

120