Pengfei

London #neuroscience people you may like this. We're hosting a series of talks at Imperial & Crick on how to get experiment and theory working together better. Each session will have a talk around this and extended networking / group discussion on the questions raised. Plus, free food!

🤖🧠🧪

PhD opportunities The School of Convergence Science at Imperial College London is inviting applications for fully funded PhD studentships on research projects that sup...

PhD opportunity in "The role of neural development in multimodal intelligence" with me, @marcusghosh.bsky.social and @flor-iacaruso.bsky.social. Read details below 👇.

Note there's a very short window for applying (deadline Feb 27).

🤖🧠🧪

www.imperial.ac.uk/school-of-co...

Toy models, just in time for Christmas!

Excited to share my first article for @thetransmitter.bsky.social

#neuroskyence

Brains have many pathways / subnetworks but which principles underlie their formation?

In our #NeurIPS paper lead by Jack Cook we identify biologically relevant inductive biases that create pathways in brain-like Mixture-of-Experts models🧵

#neuroskyence #compneuro #neuroAI
arxiv.org/abs/2506.02813

thanks! will check and follow this.

Thanks for this insightful comment. I expect that low-precision weights and Gaussian noise could play a similar role as sources of imprecision, and that delays (or other parameters) offer additional degrees of freedom that can compensate for it. Good way to further explore

This might suggest that a large fraction of computational power may actually live in the temporal parameters, not just in the weights.

With my great advisors and colleagues, @achterbrain.bsky.social @zhe @danakarca.bsky.social @neural-reckoning.org, we show that if heterogeneous axonal delays (imprecise) can capture the essential temporal structure of a task, spiking networks do not need precise synaptic weights to perform well.

Exploiting heterogeneous delays for efficient computation in low-bit neural networks Neural networks rely on learning synaptic weights. However, this overlooks other neural parameters that can also be learned and may be utilized by the brain. One such parameter is the delay: the brain...

Psst - neuromorphic folks. Did you know that you can solve the SHD dataset with 90% accuracy using only 22 kb of parameter memory by quantising weights and delays? Check out our preprint with @pengfei-sun.bsky.social and @danakarca.bsky.social, or read the TLDR below. 👇🤖🧠🧪 arxiv.org/abs/2510.27434

SNUFA 2025 Workshop - YouTube Spiking neural networks as universal function approximators (SNUFA) online workshop 2025. For more see http://snufa.net/2025/

Talks from #SNUFA 2025 are now available on YouTube:
youtube.com/playlist?lis...
🤖🧠🧪

A figure showing a range of neural network architectures. From Ghosh & Goodman, 2025, bioRxiv.

Interested in #neuroscience + #AI and looking for a PhD position?

I can support your application @imperialcollegeldn.bsky.social

✅ Check your eligibility (below)
✅ Contact me (DM or email)

UK nationals: www.imperial.ac.uk/life-science...

Otherwise: www.imperial.ac.uk/study/fees-a...

Spiking NN fans - the #SNUFA workshop (Nov 5-6) agenda is finalised and online now. Make sure to register (free) soon. (Note you can register for either day and come to both.)

Agenda: snufa.net/2025/
Registration: www.eventbrite.co.uk/e/snufa-2025...

Thanks to all who voted on abstracts!

🤖🧠🧪

Message for participants of the #SNUFA 2025 spiking neural network workshop. We got almost 60 awesome abstract submissions, and we'd now like your help to select which ones should be offered talks. Follow the "abstract voting" link at snufa.net/2025/ to take part. It should take <15m. Thanks! ❤️

Neuromodulation enhances dynamic sensory processing in spiking neural network models Neuromodulators allow circuits to dynamically change their biophysical properties in a context-sensitive way. In addition to their role in learning, neuromodulators have been suggested to play a role ...

New preprint! What happens if you add neuromodulation to spiking neural networks and let them go wild with it? TLDR: it can improve performance especially in challenging sensory processing tasks. Explainer thread below. 🤖🧠🧪 www.biorxiv.org/content/10.1...

This paper changed my life: Dan Goodman on a paper that reignited the field of spiking neural networks Friedemann Zenke’s 2019 paper, and its related coding tutorial SpyTorch, made it possible to apply modern machine learning to spiking neural networks. The innovation reinvigorated the field.

In our latest “This paper changed my life,” @neural-reckoning.org explains how @fzenke.bsky.social's 2019 paper, and its related coding tutorial SpyTorch, made it possible to apply modern machine learning to spiking neural networks.

#neuroskyence

www.thetransmitter.org/this-paper-c...

Submissions (short!) due for SNUFA spiking neural networks conference in <2 weeks! 🤖🧠🧪

forms.cloud.microsoft/e/XkZLavhaJe

More info at snufa.net/2025/

Note that we normally get around 700 participants and recordings go on YouTube and get 100s-1000s views.

Please repost.

Diagram of how the "collaborative modelling of the brain" (COMOB) project started. Starting material lead to group research or solo research, coming together in online workshops (monthly) in an iterative cycle, finishing with writing up together. The diagram is illustrated with colourful cartoon blob characters.

Is anarchist science possible? As an experiment, we got together a large group of computational neuroscientists from around the world to work on a single project without top down direction. Read on to find out what happened. 🤖🧠🧪

Yeah robots are definitely not taking over the world.

Not the red one, at least. 🤣

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/

🤖🧠🧪

A diagram showing 128 neural network architectures.

How does the structure of a neural circuit shape its function?

@neuralreckoning.bsky.social & I explore this in our new preprint:

doi.org/10.1101/2025...

🤖🧠🧪

🧵1/9

Description Please note that job descriptions are not exhaustive, and you may be asked to take on additional duties that align with the key responsibilities ment...

Hiring a post-doc at Imperial in EEE. Broad in scope + flexible on topics: neural networks & new AI accelerators from a HW/SW co-design perspective!

w/ @neuralreckoning.bsky.social @achterbrain.bsky.social in Intelligent Systems and Networks group.

Plz share! 🚀: www.imperial.ac.uk/jobs/search-...

GitHub - neural-reckoning/temporal-shd: Variant of the SHD dataset with only timing information retained Variant of the SHD dataset with only timing information retained - neural-reckoning/temporal-shd

🔗 Try it now: github.com/neural-recko...

Together with my supervisor and the Neural Reckoning team neuralreckoning.bsky.social, we’ve developed a new SHD/SSC variant that strips out rate information but spike‑timing information—designed to really challenge SNNs. Your feedback is welcome—let us know how it performs in your models!

Fusing multisensory signals across channels and time.

Now published at PLOS Comp Biol! 🎉 With @swathianil.bsky.social and @marcusghosh.bsky.social.

journals.plos.org/ploscompbiol...

TLDR, when multisensory signals vary over time, neural architecture becomes important. Biggest not always best.

Learning spatial hearing via innate mechanisms The acoustic cues used by humans and other animals to localise sounds are subtle, and change during and after development. This means that we need to constantly relearn or recalibrate the auditory spa...

How do babies and blind people learn to localise sound without labelled data? We propose that innate mechanisms can provide coarse-grained error signals to boostrap learning. New preprint from @yang-chu.bsky.social. 🤖🧠🧪

arxiv.org/abs/2001.10605

Abstract submissions are now open for the UK Neural Computation Conference! (Deadline 12th May).

We also have ARIA sponsored travel funds for ECRs! 💥

Submit here: neuralcomputation.uk/submission.html

Genreal info: neuralcomputation.uk

Registration open May. Any qs get in touch + plz share!

Science must step away from nationally managed infrastructure Scientific data and independence are at risk. We need to work with community-driven services and university libraries to create new multi-country organizations that are resilient to political…

Scientific data and independence are at risk: We need to work with community-driven services and university libraries to create new multi-country organizations that are resilient to political interference.

By @neuralreckoning.bsky.social

#neuroskyence

www.thetransmitter.org/policy/scien...

For our next UCL #NeuroAI online seminar, we are happy to be hosting Dr Dan Goodman @neuralreckoning.bsky.social (@imperialcollegeldn.bsky.social).

🗓️Wed 12 Feb 2025
⏰2-3pm GMT

Talk title: Neural architectures: what are they good for anyway?