#Tag · bonfire.cafe

It’s always special when online connections become in-person moments. At #SfN2025 we got to meet Shonali Dhingra, a past Neuromatch Academy mentor - you might recognize her from one of our postcards!

https://www.linkedin.com/posts/neuromatch_sfn2025-sfn-sfn2025-activity-7396770568613715968-65Ze?utm_source=share&utm_medium=member_desktop&rcm=ACoAAAORGZYBlgE8yO-YSwY74ZfmxxPmPxAVQJ8

#SfN #Neuromatch #Mentorship #ComputationalNeuroscience

jonny (good kind) boosted

Neuromatch

@neuromatch@neuromatch.social · 3 days ago

We loved seeing so many of you at our #sfn2025 booth and at our community social gathering. It’s such a treat connecting with you all in person!

Come by booth 3704 to chat about:
🌟 #ComputationalNeuroscience courses
🌟 Opportunities to be a TA or mentor
🌟 If you are a former student, TA, or mentor

Neuromatch

@neuromatch@neuromatch.social · 3 days ago

We loved seeing so many of you at our #sfn2025 booth and at our community social gathering. It’s such a treat connecting with you all in person!

Come by booth 3704 to chat about:
🌟 #ComputationalNeuroscience courses
🌟 Opportunities to be a TA or mentor
🌟 If you are a former student, TA, or mentor

Neuromatch

@neuromatch@neuromatch.social · 3 days ago

Neuromatch is at #SfN2025 🎉

Come by booth 3704 to learn about:
🌟 Our virtual, paid TA opportunities
🌟 Online courses in #ComputationalNeuroscience, #DeepLearning, and #NeuroAI
🌟 Mentoring opportunities
🌟 Our Impact Scholar Program

manisha boosted

Neuromatch

@neuromatch@neuromatch.social · 4 days ago

What an incredible first day at #SfN2025!

Find us in the Nonprofit Area, Booth #3704
If you haven’t yet, come by to:
⭐ Learn about our Computational Neuroscience courses
⭐ Learn about TA and mentoring opportunities

⭐ Chat with the CEO and Academy Program Director
See you at the booth!

#Neuromatch #ComputationalNeuroscience #DeepLearning #NeuroAI #GlobalResearch #EarlyCareerResearchers #STEMEducation #DataScience

Neuromatch

@neuromatch@neuromatch.social · 4 days ago

What an incredible first day at #SfN2025!

#Neuromatch #ComputationalNeuroscience #DeepLearning #NeuroAI #GlobalResearch #EarlyCareerResearchers #STEMEducation #DataScience

Neuromatch

@neuromatch@neuromatch.social · 6 days ago

Safe travels to everyone in our community heading to San Diego for #SfN2025!

Be sure to come see us at Booth #3704 in the Nonprofit Area!

#Neuromatch #ComputationalNeuroscience #DeepLearning #NeuroAI #ClimateScience #GlobalResearch #EarlyCareerResearchers #STEMEducation #DataScience #SfN

Dan Goodman and 1 other boosted

Dan Goodman

@neuralreckoning@neuromatch.social · last week

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 and Danyal Akarca:

https://arxiv.org/abs/2510.27434

Or check out the TLDR thread on Bsky:

https://bsky.app/profile/did:plc:niqde7rkzo7ua3scet2rzyt7/post/3m5jpksani22m

#SpikingNeuralNetworks #ComputationalNeuroscience #Neuroscience

https://bsky.app

View

arXiv.org

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 exhibits complex temporal dynamics with heterogeneous delays, where signals are transmitted asynchronously between neurons. It has been theorized that this delay heterogeneity, rather than a cost to be minimized, can be exploited in embodied contexts where task-relevant information naturally sits contextually in the time domain. We test this hypothesis by training spiking neural networks to modify not only their weights but also their delays at different levels of precision. We find that delay heterogeneity enables state-of-the-art performance on temporally complex neuromorphic problems and can be achieved even when weights are extremely imprecise (1.58-bit ternary precision: just positive, negative, or absent). By enabling high performance with extremely low-precision weights, delay heterogeneity allows memory-efficient solutions that maintain state-of-the-art accuracy even when weights are compressed over an order of magnitude more aggressively than typically studied weight-only networks. We show how delays and time-constants adaptively trade-off, and reveal through ablation that task performance depends on task-appropriate delay distributions, with temporally-complex tasks requiring longer delays. Our results suggest temporal heterogeneity is an important principle for efficient computation, particularly when task-relevant information is temporal - as in the physical world - with implications for embodied intelligent systems and neuromorphic hardware.

Dan Goodman

@neuralreckoning@neuromatch.social · last week

https://arxiv.org/abs/2510.27434

Or check out the TLDR thread on Bsky:

https://bsky.app/profile/did:plc:niqde7rkzo7ua3scet2rzyt7/post/3m5jpksani22m

#SpikingNeuralNetworks #ComputationalNeuroscience #Neuroscience

https://bsky.app

View

arXiv.org

Exploiting heterogeneous delays for efficient computation in low-bit neural networks

Neuromatch

@neuromatch@neuromatch.social · last week

Having some #Python skills is a prerequisite for all our Neuromatch Academy courses. We are proud to support this 3-week intensive weekend course on Python for #ComputationalNeuroscience! 🤓
Join Akinola Olayinka, Chinagorom Ibeachu, & Neuromatch's Peter Ohue for sessions exploring how Python can be applied to analyze neural data, model brain processes, & understand computational neuroscience principles.
💻 Register: https://docs.google.com/forms/d/e/1FAIpQLSd41P5V8gzLuUMlLYA9y8bp8yeUHsG6Tl7RVfsKe-qPjDUh-Q/viewform
#Neuroscience #Africa #WestAfrica #STEMEducation

Neuromatch

@neuromatch@neuromatch.social · last week

When Luai first joined Neuromatch Academy’s #DeepLearning Course, he had no experience in deep learning, just curiosity and a willingness to learn. What he discovered changed his path.

➡️ https://www.linkedin.com/feed/update/urn:li:activity:7394405408603271168

#MyNeuromatchStory #STEMEducation #OpenScience #ComputationalNeuroscience

#neuromatch #myneuromatchstory #impactstory #neuromatchacademy #globaleducation #stemeducation #openscience #computationalneuroscience #deeplearning #mentorship #scientificcommunity | Neuromatch

From curious beginner to dedicated mentor; meet Luai Waleed from Egypt. When Luai first joined Neuromatch Academy (NMA)’s Deep Learning Course, he had no experience in deep learning, just curiosity and a willingness to learn. What he discovered changed his path. 🎤 “Through Neuromatch, I turned my curiosity into a deep scientific understanding, and that lens still shapes how I view the field today. It was challenging as a complete beginner but deeply rewarding. I worked on a meaningful project that helped me apply what I was learning. With Neuromatch, I built a strong foundation in deep learning and learned how to think like a researcher.” That first experience inspired him to give back. Today, Luai mentors new learners, bringing the same spirit of collaboration and curiosity to his local community. He also volunteers with Neuromatch. 🎤 “I wanted others to feel what I felt at NMA, that mix of support, challenge, and discovery. Now I get to help others grow, and it is incredibly fulfilling. As a volunteer reviewer for the Impact Scholar Program, I treat every proposal as if it could change someone’s life because I know firsthand that it can. The volunteer atmosphere at Neuromatch is incredibly supportive and collaborative. The team is appreciative, kind, and driven, and I genuinely love being part of it.” ✨ His advice to anyone considering a Neuromatch Academy course: “Apply! It is such a positive environment. You collaborate with people from all over the world and build your network in the field. I am still in touch with my TAs and the friends I made at NMA.” Luai’s journey shows how one opportunity can grow into a cycle of learning, teaching, and inspiring others. 🤓 Learn more about our courses: https://lnkd.in/gaEhbVHz 💻 Join us in January for an Info Session: https://lnkd.in/epZrwM_y 📬 Stay in the loop: https://lnkd.in/epWXUw8k #Neuromatch #MyNeuromatchStory #ImpactStory #NeuromatchAcademy #GlobalEducation #STEMEducation #OpenScience #ComputationalNeuroscience #DeepLearning #Mentorship #ScientificCommunity

Ross Gayler and 1 other boosted

Dan Goodman

@neuralreckoning@neuromatch.social · 2 weeks ago

Talks from #SNUFA 2025 are now available on YouTube:

https://youtube.com/playlist?list=PL09WqqDbQWHEyTZPLMKEi9-RD6kax0tCR&si=Y-sJeZvIn3O062DG

#neuroscience #ComputationalNeuroscience #SpikingNeuralNetworks

YouTube

SNUFA 2025 Workshop

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

Dan Goodman

@neuralreckoning@neuromatch.social · 2 weeks ago

Talks from #SNUFA 2025 are now available on YouTube:

https://youtube.com/playlist?list=PL09WqqDbQWHEyTZPLMKEi9-RD6kax0tCR&si=Y-sJeZvIn3O062DG

#neuroscience #ComputationalNeuroscience #SpikingNeuralNetworks

YouTube

SNUFA 2025 Workshop

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

Victor Buendía

@vbuendiar@fediscience.org · 4 weeks ago

For computational neuroscience / statistical physics people in Fedi: I am actively looking for a tenure-track or a junior PI position.

My background is pure statistical physics and complex systems. I mostly do stochastic processes but I'm very familiar with disordered systems too. I'm more interested by the dynamical systems side of things... How structure shapes dynamics, how dynamics are related to computation and processing . I am quite good at writing simulation code.

I also have taught a lot of hours and cosupervised students with good results. If you know about any open position or grant and you're interested in my profile, feel free to contact me!

#getfedihired #compneuro #computationalneuroscience #academicchatter #statphys

Ulrike Hahn boosted

Dan Goodman

@neuralreckoning@neuromatch.social · 4 weeks ago

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: https://snufa.net/2025/
Registration: https://www.eventbrite.co.uk/e/snufa-2025-tickets-1549418545579

Thanks to all who voted on abstracts!

#Neuroscience #ComputationalNeuroscience #SpikingNeuralNetworks

Eventbrite

SNUFA 2025

Online computational neuroscience and neuromorphic engineering workshop

SNUFA

SNUFA 2025

Spiking Neural networks as Universal Function Approximators

Dan Goodman

@neuralreckoning@neuromatch.social · 4 weeks ago

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: https://snufa.net/2025/
Registration: https://www.eventbrite.co.uk/e/snufa-2025-tickets-1549418545579

Thanks to all who voted on abstracts!

#Neuroscience #ComputationalNeuroscience #SpikingNeuralNetworks

Eventbrite

SNUFA 2025

Online computational neuroscience and neuromorphic engineering workshop

SNUFA

SNUFA 2025

Spiking Neural networks as Universal Function Approximators

Wu-Lee and 1 other boosted

Dan Goodman

@neuralreckoning@neuromatch.social · 3 months ago

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.

The project started as a tutorial on a new technique at the @CosyneMeeting 2022. We realised that the technique was easy and cheap for anyone to use with a lot of low hanging fruit.

https://neural-reckoning.github.io/cosyne-tutorial-2022/

At the tutorial we announced a 1-2 year open research project that anyone could join, starting from the materials of the tutorial, and a few starting questions we found interesting, but with no other constraints. We were inspired by the Polymath Project in mathematics.

https://en.wikipedia.org/wiki/Polymath_Project

31 people contributed to the project, joining for monthly meetings to discuss progress. All code was publicly available throughout, and when we started writing up the work in progress was also fully public. You can see that version here: https://comob-project.github.io/snn-sound-localization/paper

Not everyone who was involved made it to the paper (didn't respond or couldn't find contact details), and not all are on Mastodon, but authors include: @marcusghosh @TomasFiers
@GabrielBena @rory

We used GitHub and Jupyter notebooks to coordinate development, with a website showing everyone's current code and results to make collaboration easier. We used @mystmarkdown and GitHub actions to automate this.

https://comob-project.github.io/snn-sound-localization/

So how did it work out? Well, some things went well and others not so well. We published a paper with our results and reflections on the process. If you're interested in spiking neural networks, sound localisation, or anarchist science, check it out:

https://www.eneuro.org/content/12/7/ENEURO.0383-24.2025

Generally, the infrastructure we built worked well, as did the monthly meetings. Starting from the tutorial was a good decision because it gave everyone a common reference and meant they could easily get started.

However, the lack of direction meant that we didn't achieve very coherent results in the end. We don't think this is a catastrophic problem, but when we try again, this is something we'd like to address. If you have thoughts or would like to be involved, get in touch!

Ultimately, we didn't achieve a scientific breakthrough in this project, but we did show that without top down direction or any specific funding, we could organise a large group of scientists to work together and publish their research in a good journal. We think that's a hopeful sign for the future!

#neuroscience #computationalneuroscience #compneuro #anarchism #science