Thomas Nowotny

@drtnowotny.bsky.social

Professor of Informatics at the University of Sussex, Brighton, UK. President of @cnsorg.bsky.social I do research in bio-inspired AI and computational neuroscience. See more at https://profiles.sussex.ac.uk/p206151-thomas-nowotny/about

Very nice paper that came out of a new collaboration between @jsenk.bsky.social and @neworderofjamie.bsky.social we started a while ago. Structural plasticity helps strike the balance between using sparse connectivity (*not* full matrices with loads of zeros) and being able to change it on the go.

Jamie@neworderofjamie.bsky.social · 7mo ago

New paper out at iopscience.iop.org/article/10.1... with @jsenk.bsky.social & @drtnowotny.bsky.social. We present what I think is the first framework for flexibly implementing GPU-accelerated structural plasticity rules (in GeNN obvs!) and demonstrate it with DEEP-R & topographic map formation.

Happy to share our preprint on ephaptic interactions between olfactory receptor neurons in Drosophila by Lydia Ellison. doi.org/10.64898/202... We set out to see how near-instantaneous electrical interactions are good for processing tiny odour onset delays, only to find that they weren't.

History-dependent ephaptic interactions in paired olfactory receptor neurons

Olfactory sensing begins with the transduction of odors into receptor currents on the dendrites of olfactory receptor neurons (ORNs). In insects and many other arthropods, ORNs are grouped stereotypically in hair-like sensilla on the surface of olfactory organs, enabling mutual inhibition through non-synaptic 'ephaptic' interactions (NSIs). Given the electrical, and therefore virtually instantaneous, nature of NSIs, it has been hypothesized that they contribute to processing fast temporal elements of mixed odor plumes. Here, we present single sensillum recordings and computational modeling that characterize NSIs during short offset dual-odor stimulations in the olfactory sensilla of adult female Drosophila melanogaster. We find in the experiments that the magnitude of inhibition between co-housed ORNs cannot be predicted by their instantaneous activity (firing rate) alone. It is adaptation-dependent, with strong effects only occurring when the inhibited ORN is adapted. This limits the usefulness of NSIs for fast odor processing when ORNs lack time to adapt. We reproduced the observed phenomena in a computational model and use this model to explain how the adaptation-dependence of NSI-mediated inhibition arises from nonlinearities in neural responses. We conclude that NSIs are unlikely to support the encoding of fast temporal dynamics in mixed odor stimuli, instead contributing to slower peripheral processing, supporting roles such as novelty detection. More broadly, we demonstrate how the nonlinear interactions of fairly simple electrical components lead to non-intuitive results, offering insight into the longstanding debate around ephaptic interactions in other systems, such as the mammalian CNS. ### Competing Interest Statement The authors have declared no competing interest. Leverhulme Trust, https://ror.org/012mzw131, RPG-2019-232 Engineering and Physical Sciences Research Council, https://ror.org/0439y7842, EP/P006094/1, EP/S030964/1

doi.org

Excited to see the paper fully published. It's an important milestone for training SNNs with exact gradients, replacing our earlier tricks of a "delay line augmentation" to capture temporal relationships. Delays can now be learnt alongside weights naturally. Amazing work @mbalazs98.bsky.social !

Balázs@mbalazs98.bsky.social · 10mo ago

Our paper on event-based delay learning is now published! @neworderofjamie.bsky.social @drtnowotny.bsky.social TL;DR: It’s now possible to train synaptic delays in large-scale spiking neural networks with high temporal precision—even in recurrent connections. www.nature.com/articles/s41...

Excellent paper and great new project. Very interesting how the race of technology between GPU and FPGA shapes up.

Jamie@neworderofjamie.bsky.social · last yr.

Belated exciting news! First paper from my new(ish) project with the very talented Zainab Aizaz is out at ieeexplore.ieee.org/document/110.... Results from the first prototype of our fully-programmable FPGA-based SNN accelerator, showing off its stochastic rounding capabilities and speediness.

Posting this after some recent conversations with potential international applicants - still time to apply to our Masters courses and International PhD Academy for 2025 entry - join the diverse and vibrant Neuroscience community on our beautiful campus next to Brighton

Sussex Neuroscience@sussexneuro.bsky.social · 2y ago

Want to join our vibrant postgrad community? Discover all our Neuroscience courses here: www.sussex.ac.uk/study/subjects/neuroscience Including: 🏫 International PhD Academy 🏫 Masters courses 🏫 Opportunities across several schools: Life Science; Psychology; Computer Science & AI; and BSMS

Just out in J Neuromorph Comput & Eng: Loss shaping enhances exact gradient learning with Eventprop in Spiking Neural Networks doi.org/10.1088/2634.... With @neworderofjamie.bsky.social. We report how Eventprop scales to harder learning tasks. TL;DR: It works great but not without extra effort. 🧪🧵

Loss shaping enhances exact gradient learning with Eventprop in spiking neural networks - IOPscienceSearch

Loss shaping enhances exact gradient learning with Eventprop in spiking neural networks, Nowotny, Thomas, Turner, James P, Knight, James C

doi.org

More than 60 German-speaking universities and research institutes have just jointly announced they will cease activities on X because “the current orientation of the platform is not compatible with their core values” incl. scientific integrity, transparency and democratic discourse” 🧪

BildBildBild

💯 Hallucination is totally the wrong word, implying it is perceiving the world incorrectly. But it's generating false, plausible sounding statements. Confabulation is literally the perfect word. So, let's all please start referring to any junk that an LLM makes up as "confabulations".

Cian O'Donnell@cianodonnell.bsky.social · 2y ago

petition to change the word describing ChatGPT's mistakes from 'hallucinations' to 'confabulations' A hallucination is a false subjective sensory experience. ChatGPT doesn't have experiences! It's just making up plausible-sounding bs, covering knowledge gaps. That's confabulation

If you're interested in a PhD in the AI centre of excellence at Sussex, now's your chance! lncluding several Spiking Neural Network project suggestions from @drtnowotny.bsky.social and I!

Ivor Simpson@ivorsimpson.bsky.social · 2y ago

We’ve just announced this year’s call for applications to our Sussex AI PhD studentships at the University of Sussex! You can find all the details www.sussex.ac.uk/study/fees-f.... This year we’ve included a few suggested project directions to give some inspirations tinyurl.com/2e3mxbch.