Inspired by the cell network of the retina, a new photonic computing system described in #ScienceAdvances can rapidly learn to solve complex visual tasks—from classification to image segmentation—from very restricted datasets. https://scim.ag/4xzsnIN

Few-shot neuromorphic vision in a nonlinear photonic network laser

With the growing prevalence of artificial intelligence (AI), demand increases for hardware that mimics the brain’s ability to extract structure from limited data. In the retina, ganglion cells detect ...

scim.ag

New paper from our group :) Inspired by retinal ganglion cell networks, we built an on-chip photonic lasing network that can rapidly learn to solve complex visual tasks, from classification to image segmentation, from scarce training data. Out in Science Advances @science.org t.co/enRyRVgzlI

If you're in or near London do think about coming along to this. Not just a talk about a really fun topic (neural heterogeneity) but a chance to grill the author (me) on whether we learn anything with the theoretical methods he's used, and indeed whether the questions he poses are even meaningful.

Marcus Ghosh@marcusghosh.bsky.social · last mo.

Our final workshop will be @crick.ac.uk 🔜 10.09 from 16:00. With a talk and discussion hosted by @neural-reckoning.org on: 🧠 Does heterogeneity help the brain and how could we know if it did? Registration is free but required: www.eventbrite.co.uk/e/understand...

What role does Emergence play in Neural Networks? We find that learning emergent low-dimensional representations is key for out-of-distribution generalisation. New Preprint out with @neural-reckoning.org arxiv.org/abs/2607.10430

Emergent Generalization by Representation Learning in Artificial Neural Networks

Dimensionality reduction has proven powerful for identifying neural manifolds, which are low-dimensional structures underlying high-dimensional neural activity. These low-dimensional representations h...

arxiv.org

New preprint (well, very updated). 🤖🧠🧪 We find that an abstract model of neuromodulation lets spiking neural networks perform much better, particularly in challenging noisy environments, using less energy. Relevant to #neuroscience and #neuromorphic computing. 🧵👇 www.biorxiv.org/content/10.1...

Neuromodulation enhances the capability and efficiency of spiking neural networks

Spiking neurons underlie the brain’s extreme energy efficiency, and therefore have great potential in neuromorphic computing, although realising this efficiency in practice has proven challenging. We ...

biorxiv.org

New neuromorphic/SNN paper with @pengfei-sun.bsky.social Zhe Su, @achterbrain.bsky.social @giacomoi.bsky.social and @danakarca.bsky.social: www.nature.com/articles/s42... Long story short: neat trick to augment SNNs with a tiny memory buffer to improve performance at low energy/param cost. 🤖🧠🧪

Job klaxon 📣 UCL is hiring two NeuroAI / computational neuroscience specialists (Lecturer or Associate Prof) — a big part of the new NeuroAI centre we're growing in Biosciences. Do consider applying if it's relevant to you. JD & details: https://www.jobs.ac.uk/job/DRX021 Happy to take questions.

We're hiring for a project on #SpikingNeuralNetworks and #neuromorphic computing, to start in October this year, for 36 months. Can hire at pre- or post-PhD level. Email me informally, or apply at the link below. Share with your networks / anyone who would be interested. 🤖🧠🧪

George A. Constantinides@gconstantinides.bsky.social · 6mo ago

Interested in a PhD or postdoc in digital neuromorphic computing? @neural-reckoning.org, Christos Bouganis and I are recruiting! Please share with anyone who may be interested. Applications close on 15 May 2026. www.imperial.ac.uk/jobs/search-...

If you're in London next Thursday afternoon/evening, come along to our seminar/workshop on how to get theory and experiment working together better in neuroscience. There'll be a short talk by @marcusghosh.bsky.social on "A taxonomy of recurrence" (see below) and a long discussion with free food.

News from the lab! 🤩 Is it possible to switch a material from being an absorber to an amplifier just by changing the phase of light? By treating a thin film of ITO as a time-varying medium, we achieved 400% amplification and 80% absorption within the same structure. www.nature.com/articles/s41...

Optical coherent perfect absorption and amplification in a time-varying medium - Nature Photonics

The researchers show that a subwavelength film of indium tin oxide, the bulk permittivity of which is strategically modulated via optical pumping, can be dynamically tuned to act as both a non-resonan...

nature.com

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...

PhD opportunities

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

imperial.ac.uk

Looking for PhD opportunities? Position open between our group & @ajdavison.bsky.social: Embodied Neuromorphic AI for Few-Shot, Continual Robot Learning www.imperial.ac.uk/school-of-co... Physical Neural Nets X Robots - DM, email or apply above! :)

New preprint from our lab - Learning Nonlinear Heterogeneity in Physical Kolmogorov–Arnold Networks: arxiv.org/abs/2601.15340 We asked what if instead of training linear weights in physical neural networks, we train nonlinear physical dynamics. We find better performance, with fewer devices.

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...

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 ...

biorxiv.org