Thomas Nowotny
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
profiles.sussex.ac.uk/p206151-thomas-nowo…
- 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.
- To our surprise, the non-linearity of frequency-input relations (F-I curve) of spiking olfactory receptor neurons (ORNs) means that the ephaptic inhibition is all but invisible if ORNs are highly activated at odour onset. Adaptation additionally masks the effects.
- So, ephaptic interactions mainly seem to matter when one of the ORNs in the sensillum is adapted due to longer odour exposure, pointing to a more significant role of ephaptic interactions for novelty detection, as previously described. All our observations are backed up by a computational model.
- Finally, our work was done in two sensillum types out of dozens, so we can't be sure that other ORN types may not have different F-I curves and adaptation; however, nonlinear F-I curves are ubiquitous and strong adaptation has been seen in many studies...
- Reposted by Thomas NowotnyHappy to share our preprint with @neworderofjamie.bsky.social , @danakarca.bsky.social and @drtnowotny.bsky.social ! We’ve been working on a neuron position learning algorithm by coupling space and time! See manuscript below 👇
- 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 !
- 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...
- Reposted by Thomas NowotnyIf you're interested in doing a PhD at Sussex, lots of exciting PhD project ideas at www.sussex.ac.uk/research/cen... including several Spiking Neural Network projects with myself and @drtnowotny.bsky.social . Funding available via www.sussex.ac.uk/study/fees-f... or www.sussex.ac.uk/study/fees-f...
- Excellent paper and great new project. Very interesting how the race of technology between GPU and FPGA shapes up.
- 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.
- Strong results on Speech commands with GLE presented by Paul Haider at #cns2025florence today . @cnsorg.bsky.social
- And we are off - excited that #cns2025florence is under way with record attendance - first keynote starts in 5 minutes.
- Reposted by Thomas Nowotny
Very excited by our new Sussex AI promotional video www.youtube.com/watch?v=D5dS... - Reposted by Thomas NowotnyPosting 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
- 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
- ... and you can see the great lineup of tutorials and workshops here: ocns.memberclicks.net/cns-2025-mee... Of course, tutorial and workshop registration can also be added later if you have already registered for the main meeting. @cnsorg.bsky.social
- The deadline is tomorrow - last push! @cnsorg.bsky.social
- The deadline is tomorrow - last push! @cnsorg.bsky.social
- Only 5 days to go to the (extended) deadline. Make them count. A great lineup of keynotes, tutorials and workshops is secured - add your research as an oral or poster by submitting an abstract.
- Abstract submission is open for the 34th Annual Computational Neuroscience Meeting CNS*2025 in Florence, Italy, July 5-9, 2025! Submit your abstract latest March 15th: www.cnsorg.org/cns-2...
- Reposted by Thomas Nowotny@drtnowotny.bsky.social and I are again participating in Google Summer of Code under the @incforg.bsky.social. We have 3 paid projects involving GeNN for contributors with a range of skills and experience levels. If you're interested, please get in touch via the forums linked from the thread:
- Reposted by Thomas NowotnyCall for Abstracts: 34th Annual Computational Neuroscience Meeting, CNS*2025 🌟 📍 Join us in Florence 🇮🇹 July 5-9, 2025! 🧠✨ 🗓️ Abstract Deadline: March 11, 2025 🔗 Submit here: www.cnsorg.org/cns-2025-abs... 📚 Workshops: www.cnsorg.org/cns-2025-cal... 🎓 Tutorials: www.cnsorg.org/cns-2025-cal...
- Reposted by Thomas NowotnyThis is awesome work from Balazs! Not only does our Eventprop-based method supports multiple spikes per neuron and recurrent connectivity but uses less than half the memory of the current state-of-the-art delay-learning method and is up to 26x faster.
- New preprint out with @drtnowotny.bsky.social and @neworderofjamie.bsky.social arxiv.org/abs/2501.07331
- Reposted by Thomas NowotnyWikipedia is one of the last major bastions of verified information. Which, of course, is why the oligarchs want to destroy it. You can donate to them here. donate.wikimedia.org/w/index.php?...
- 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. 🧪🧵
- We implemented Eventprop (Wunderlich & Pehle, 2021) in our GeNN (genn-team.github.io) simulator and attempted to classify the Spiking Heidelberg Digits (SHD, zenkelab.org/resources/sp...) in a 3-layer network. 2/5
- This initially failed due to average cross-entropy loss creating unhelpful gradients in the hidden layer and the fact that spike creation and deletion is not “visible” in the exact gradients calculated by Eventprop. 3/5
-
View full threadWe also classified the Spiking Speech Commands (SSC) with good success. Finally, the GeNN implementation of Eventprop has very beneficial computational scaling properties compared to BPTT in Spyx (github.com/kmheckel/spyx). All details at doi.org/10.1088/2634.... @sussexai.bsky.social 5/5
- Reposted by Thomas Nowotny"A study of federally funded research projects in the United States estimated that principal investigators spend on average about 45% of their time on administrative activities related to applying for and managing projects rather than conducting active research" www.pnas.org/doi/10.1073/...
- We are proposing PhD project ideas along these lines:
- More exciting opportunities for fully-funded PhDs with @sussexai.bsky.social on topics including Event-based machine learning and neuromorphic computing with me and @drtnowotny.bsky.social. www.sussex.ac.uk/study/fees-f...
- Reposted by Thomas NowotnyMore 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” 🧪
- New paper on spike sorting www.sciencedirect.com/science/arti... with Lydia Ellison, Georg Raiser, Alicia Garrido Peña and George Kemenes. TL;DR: SSSort software now handles overlapping spikes in addition to the extreme spike shape changes it was already good at. github.com/grg2rsr/SSSort
- Reposted by Thomas NowotnyFirst paper by our excellent PhD student @mbalazs98.bsky.social on trying to unpick the relation between delay learning and structural plasticity in SNNs and visualise what gets learned www.frontiersin.org/articles/10....
- Reposted by Thomas Nowotny💯 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".
- Reposted by Thomas NowotnyGoogling Stuff: Then v Now.
- Here is another way to apply to join our group. Deadline 13 January.
- Our Sussex Neuroscience 4-year PhD Programme is open for applications! Deadline Jan 13th, for Sept 2025 entry. Brilliant community of students and supervisors, and a choice of >60 labs for rotations- come and join us by the sea! www.sussex.ac.uk/research/cen...
- Sussex AI, the multi-disciplinary centre of things AI and data science at University of Sussex is now also on BlueSky: @sussexai.bsky.social
- Reposted by Thomas NowotnyIf 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!
- Reposted by Thomas NowotnySharing this again, in case anyone has only read the first side of the arguments here. So much noise and conclusion jumping out there. Read on: @garymarcus.bsky.social open.substack.com/pub/garymarc...
- We are using the GeNN family of simulation software github.com/genn-team/genn, github.com/genn-team/ml.... Disclaimer: we are also the developers 😅
- What simulation engines are you all using for your embodied (neuro)AI research? #NeuroAI
- Sorry, got carried away equating AI with LLM. Regarding using LLMs to query databases, that's interesting but the LLMs would have to change significantly as their current operating principle of generating text essentially based on word distributions in the training data will "innovate" by design.
- But @tyrellturing.bsky.social which LLM is producing facts? I don't know any. They all only produce plausible sounding texts without reference to facts.
- Our lab as well ... if you are interested in comp neuro.
- Very interesting blog. I would particularly agree with the point that anything gets published eventually in the current model; and that doesn't even take into account predatory publishers.
- Great blog by Bodo Stern (@hhmi.bsky.social) about the recent Clarivate decision on @elife.bsky.social’s impact factor. www.coalition-s.org/blog/how-the...
- Published/branded?
- Reposted by Thomas NowotnyWhy do people want AI to produce academic text (papers, reviews)? If we humans aren't even willing to write those texts, why in the bloody hell would we want to read them? How about: if no one cares about a text, let's leave it be. No need to review literally everything.🙅🙅♀️ #AcademicSky #SciPub
- Very interesting analysis. Clearly, this cannot continue like this.
- The strain on scientific publishing: we set out to characterise the remarkable growth of the scientific literature in the last few years, in spite of declining growth in total scientists. What is going on? direct.mit.edu/qss/article/... A 🧵 1/n #AcademicSky #PhDchat #ScientificPublishing #SciPub
- The Organization for Computational Neuroscience (OCNS) which runs the annual CNS meetings and comp-neuro email list is now on Bsky: @cnsorg.bsky.social
- For the geeks, I have some variables x_1, ... , x_n forming some expressions e_1, ..., e_m (e.g. e1= x_1 + x_2). How can I find the minimal set of expressions e'_i that allow me to express all the e_i? Example: if e_1=x_1+x_2 and e_2=(x_1+x_2)^2, I want e'_1=x_1+x_2 and not {e'_1 = x_1, e'_2= x_2}
- Hi there! Short #introduction I am interested in bio-inspired AI and computational neuroscience. Currently, we are interested in training spiking neural networks with exact gradients; including SSNs with delays and training delays. I work @ University of Sussex and am the president of OCNS.
