Lightnews — Scholar-powered news

Reposted by Jonathan Cornford

Matt Perich @mattperich.bsky.social · Aug 13

🚨 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.

2 25 83

Reposted by Jonathan Cornford

Claudia Clopath Lab @clopathlab.bsky.social · Jul 23

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...

www.nature.com

1 16 56

Jonathan Cornford @repromancer.bsky.social · Jul 17

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

1

Reposted by Jonathan Cornford

Mark D Humphries @markdhumphries.bsky.social · Jul 11

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

3 9

Reposted by Jonathan Cornford

Blake Richards @tyrellturing.bsky.social · Jul 9

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 🧪

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...

arxiv.org

3 13 39

Jonathan Cornford @repromancer.bsky.social · Jul 10

💯 Great to see!

2

Jonathan Cornford @repromancer.bsky.social · Jul 4

Really like this work!

Rui Ponte Costa @somnirons.bsky.social · Jul 4

Pleased to say that our story of how a theory of self-supervised learning in cortical layers accounts for several experimental observations is now out 🎉
www.nature.com/articles/s41...

Self-supervised predictive learning accounts for cortical layer-specificity - Nature Communications

How the cortex learns an internal representation of the world and why the cortex relies on a layered structure remain poorly understood. Here, the authors propose a computational theory in which the n...

www.nature.com

1 9

Jonathan Cornford @repromancer.bsky.social · Jun 30

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! :)

Jonathan Cornford @repromancer.bsky.social · Jun 30

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

1 1

Jonathan Cornford @repromancer.bsky.social · Jun 30

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.

1 1

Jonathan Cornford @repromancer.bsky.social · Jun 30

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.

2 1

Reposted by Jonathan Cornford

Mark D Humphries @markdhumphries.bsky.social · Jun 25

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

UKNC25 |

neuralcomputation.uk

2 1

Reposted by Jonathan Cornford

Danyal @danakarca.bsky.social · Jun 18

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

1 6 12

Reposted by Jonathan Cornford

Friedemann Zenke @fzenke.bsky.social · May 27

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

4 56 170

Reposted by Jonathan Cornford

Aaron Milstein @neurosutras.bsky.social · May 27

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)

1 18 43

Jonathan Cornford @repromancer.bsky.social · Apr 25

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

1

Reposted by Jonathan Cornford

Dr Sasha Luccioni @sashamtl.bsky.social · Apr 2

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? 🤝

1 7 23

Reposted by Jonathan Cornford

Nanda H Krishna @nandahkrishna.bsky.social · Apr 5

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

3 19

Reposted by Jonathan Cornford

Arna Ghosh @arnaghosh.bsky.social · Apr 1

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

3 9 27

Jonathan Cornford @repromancer.bsky.social · Mar 30

Thanks!

1

Jonathan Cornford @repromancer.bsky.social · Mar 29

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

1 2 22

Jonathan Cornford @repromancer.bsky.social · Mar 27

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.

2

Jonathan Cornford @repromancer.bsky.social · Mar 27

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

1 3

Jonathan Cornford @repromancer.bsky.social · Mar 25

Congratulations Guillaume!

1 1

Jonathan Cornford @repromancer.bsky.social · Mar 21

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?