Sign in

Thomas Nowotny

@drtnowotny.bsky.social
677 followers 163 following 43 posts

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-thoma…

PostsRepliesMedia
Thomas Nowotny @drtnowotny.bsky.social · 11/07/2026
CNS*2026 just kicked off with a great keynote by Bratislav Misic. @cnsorg.bsky.social in a great setting at Halifax.
000
Thomas Nowotny @drtnowotny.bsky.social · 17/03/2026
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.
094
Thomas Nowotny @drtnowotny.bsky.social · 27/01/2026
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.
doi.org
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
153
Reposted by Thomas Nowotny
Balázs @mbalazs98.bsky.social · 27/01/2026
Happy 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 👇
1179
Thomas Nowotny @drtnowotny.bsky.social · 25/11/2025
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 !
0218
Reposted by Thomas Nowotny
Jamie @neworderofjamie.bsky.social · 31/10/2025
If 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...
sussex.ac.uk
Project suggestions : Sussex AI PhD Programme : ... : AI Research Group : University of Sussex
123
Thomas Nowotny @drtnowotny.bsky.social · 16/07/2025
Excellent paper and great new project. Very interesting how the race of technology between GPU and FPGA shapes up.
081
Thomas Nowotny @drtnowotny.bsky.social · 06/07/2025
Strong results on Speech commands with GLE presented by Paul Haider at #cns2025florence today . @cnsorg.bsky.social
100
Thomas Nowotny @drtnowotny.bsky.social · 05/07/2025
And we are off - excited that #cns2025florence is under way with record attendance - first keynote starts in 5 minutes.
1102
Reposted by Thomas Nowotny
Ian Wakeman @ianwakeman.bsky.social · 13/05/2025
Very excited by our new Sussex AI promotional video www.youtube.com/watch?v=D5dS...
youtube.com
Towards a Better Future: How Sussex Students are Using AI to Change the World!
YouTube video by University of Sussex
021
Reposted by Thomas Nowotny
Miguel Maravall @mmaravall.bsky.social · 13/05/2025
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
076
Thomas Nowotny @drtnowotny.bsky.social · 17/03/2025
... 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
000
Thomas Nowotny @drtnowotny.bsky.social · 17/03/2025
The deadline is tomorrow - last push! @cnsorg.bsky.social
000
Thomas Nowotny @drtnowotny.bsky.social · 13/03/2025
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.
000
Reposted by Thomas Nowotny
Jamie @neworderofjamie.bsky.social · 06/03/2025
@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:
144
Reposted by Thomas Nowotny
cnsorg.bsky.social @cnsorg.bsky.social · 24/01/2025
Call 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...
cnsorg.org
CNS 2025 Abstract Submission
042
Reposted by Thomas Nowotny
Jamie @neworderofjamie.bsky.social · 23/01/2025
This 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.
092
Reposted by Thomas Nowotny
Tim Verstynen @tdverstynen.bsky.social · 22/01/2025
Wikipedia 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?...
donate.wikimedia.org
Make your donation now - Wikimedia Foundation
Donate to the Wikimedia Foundation, the nonprofit that hosts Wikipedia and other crucial free knowledge projects. Each year, the generosity of the 2% of readers who donate allows us to expand the reac...
4248138
Thomas Nowotny @drtnowotny.bsky.social · 21/01/2025
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. 🧪🧵
doi.org
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
1104
Reposted by Thomas Nowotny
Daniel P. Moriarity @dpmoriarity.bsky.social · 04/01/2025
"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/...
33996462
Thomas Nowotny @drtnowotny.bsky.social · 10/01/2025
We are proposing PhD project ideas along these lines:
Event-based machine learning and neuromorphic computing (EP25/53) EPSRC category: Interdisciplinary Research Lead Supervisors: James Knight and Thomas Nowotny Department: Informatics Research outline:  Event-based Spiking Neural Networks (SNNs) are inspired by the efficiency of biological neurons and with recent advances such as Eventprop (Wunderlich & Pehle (2021), Nowotny et al. (2024)) we can train them using supervised learning. However, there are technical difficulties and the methods have thus far only been applied to a few benchmark problems. Equally important, like in ML more generally, lack of labelled data is becoming a problem. Self-supervised approaches are an exciting and competitive alternative (Chen et al. (2020), Illinger et al. (2020), Halvagal & Zenke (2023)).  We are looking for PhD students interested in working on these challenges using our GPU-accelerated SNN simulation framework (Knight et al. (2021), Knight & Nowotny (2023) to: • further improve methods for gradient descent in SNNs  • extend gradient descent methods towards real-world problems • combine SNNs and self-supervised learning to solve real-world tasks • train SNNs for deployment on neuromorphic hardware like Loihi 2 Key Publications:  Nowotny T, Turner, JP, Knight, JC (2024). Loss shaping enhances exact gradient learning with EventProp in spiking neural networks, arXiv. (link) Knight, JC & Nowotny, T (2023). Easy and efficient spike-based machine learning with mlGeNN. Neuro-Inspired Computational Elements Conference, 115–120. (link)
0125
Reposted by Thomas Nowotny
Kai Kupferschmidt @kakape.bsky.social · 10/01/2025
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” 🧪
17765217
Thomas Nowotny @drtnowotny.bsky.social · 20/12/2024
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
082
Reposted by Thomas Nowotny
Jamie @neworderofjamie.bsky.social · 20/12/2024
First 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....
frontiersin.org
Frontiers | Learning delays through gradients and structure: emergence of spatiotemporal patterns in spiking neural networks
1184
Reposted by Thomas Nowotny
Blake Richards @tyrellturing.bsky.social · 11/12/2024
💯 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".
1820444
Reposted by Thomas Nowotny
Chaz Hutton @chazhutton.com · 11/12/2024
Googling Stuff: Then v Now.
This title if the comic is ‘Googling Stuff…’
The comic shows two columns: on the left is “Then” showing search results with one thing listed as “the thing you want”

On the right column is ‘Now’ - also showing search results but in this case it’s a whole bunch of stuff you don’t need:

AI TAKING A WILD STAB AT IT WITH SOME
BLATANT MISINFORMATION

SPONSORED RESULT

SPONSORED RESULT

SPONSORED RESULT

SPONSORED RESULT

PEOPLE ALSO ASK

VIEW PRODUCTS

And then right at the bottom just off screen is ‘the thing you want’
221167676346
Thomas Nowotny @drtnowotny.bsky.social · 12/12/2024
Here is another way to apply to join our group. Deadline 13 January.
041
Thomas Nowotny @drtnowotny.bsky.social · 11/12/2024
Sussex AI, the multi-disciplinary centre of things AI and data science at University of Sussex is now also on BlueSky: @sussexai.bsky.social
052
Reposted by Thomas Nowotny
Jamie @neworderofjamie.bsky.social · 09/12/2024
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!
042
Reposted by Thomas Nowotny
Greg O’Brien @thegregobrien.bsky.social · 07/12/2024
Sharing 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...
open.substack.com
Hard-forked! Casey Newton’s distorted portrait of Gary Marcus and AI skepticism
What Casey Newton’s new essay skewering AI skepticism does—and does not—get right
0122
Thomas Nowotny @drtnowotny.bsky.social · 04/12/2024
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 😅
github.com
GitHub - genn-team/genn: GeNN is a GPU-enhanced Neuronal Network simulation environment based on code generation for Nvidia CUDA.
GeNN is a GPU-enhanced Neuronal Network simulation environment based on code generation for Nvidia CUDA. - genn-team/genn
042
Thomas Nowotny @drtnowotny.bsky.social · 04/12/2024
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.
220
Thomas Nowotny @drtnowotny.bsky.social · 04/12/2024
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.
110
Thomas Nowotny @drtnowotny.bsky.social · 30/11/2024
Our lab as well ... if you are interested in comp neuro.
021
Thomas Nowotny @drtnowotny.bsky.social · 30/11/2024
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.
031
Thomas Nowotny @drtnowotny.bsky.social · 29/11/2024
Published/branded?
120
Reposted by Thomas Nowotny
Mark A. Hanson @hansonmark.bsky.social · 28/11/2024
Why 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
85811
Thomas Nowotny @drtnowotny.bsky.social · 26/11/2024
Very interesting analysis. Clearly, this cannot continue like this.
030
Thomas Nowotny @drtnowotny.bsky.social · 24/11/2024
The Organization for Computational Neuroscience (OCNS) which runs the annual CNS meetings and comp-neuro email list is now on Bsky: @cnsorg.bsky.social
192
Thomas Nowotny @drtnowotny.bsky.social · 22/11/2024
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}
100
Thomas Nowotny @drtnowotny.bsky.social · 22/11/2024
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.
0173
Reposted by Thomas Nowotny
Giulia D'Angelo @giuliadangelo.bsky.social · 22/11/2024
So, @neworderofjamie.bsky.social and I would really like to start a rock band called "Saccadic Revolution." In the meantime, we're investigating why foveation and saccades enable us to explore the world so amazingly. Thank you Sussex AI for making me feel at home! #onlyneuromorphicvibes
042