That's an interesting point. I guess you're relying on the duality between addition and convolution in the log space? A kind of homomorphic filtering?

Scale-covariant spiking wavelets We establish a theoretical connection between wavelet transforms and spiking neural networks through scale-space theory. We rely on the scale-covariant guarantees in the leaky integrate-and-fire neuro...

I'll be presenting our work at ICASSP 2026 👋

#neuromorphic #signalprocessing #icassp2026

arxiv.org/abs/2602.02020

Illustration of leaky integrate-and-fire neurons integrating positive and negative parts of a signal

How does spiking neural networks handle continuous signals?
Turns out, they can use the same tricks used JPEGs and telecom (wavelets)!

It's 100x more efficient. It's lossy, but causal and implementable directly in analog circuits. And maybe a path toward fast, low-power spiking signal processing?

There's unfortunately not much to read - yet!
We would love your input and feedback Dan. We want this to be as close to "something that's needed" as we possibly can. Can I drop you a line?

Front page of the website for the book: Practical Spiking Neural Networks

The field of #neuromorphics is lacking *accessible*, *intuitive*, and *practical* introductions. Ramashish Gaurav, Petruț Antoniu Bogdan, and I are setting out to fix this with a book on Practical Spiking Neural Networks! ✅

Any and all contributions are welcome! 💕

Early access at: snnbook.net

I'm proud to chair this initiative, bringing together leading scientists, students, and volunteers to build an open and sustainable ecosystem for neuromorphics.

Check it out and sign up. We can use your help :-)

#neuromorphic #ComputerVision #EventBasedVision

My humble hope: this could be a turning point for SNNs to excel in what they were designed for: sparse, spatio-temporal signal processing.

The best part? Everything is open-source. Steal it, modify it, send it to hardware with the Neuromorphic Intermediate Representation - just please cite us :-)

Covariant spatio-temporal receptive fields for spiking neural networks - Nature Communications Neuromorphic computing mimics brain efficiency but lacks theoretical guidance. Here, authors develop a computational foundation for processing signals in space and time in spiking neural networks that...

New paper on covariant #neuromorphic networks!

We're connecting decades of work in computer vision with decades of work in spiking networks. And, in an event-based vision task against regular ANNs of similar complexity, spiking networks are doing much, much better!

www.nature.com/articles/s41...

Can you unpack this a bit?
Some argue that large models work well in machine learning because of the mysterious fact that gradient descent improves at scale, despite non-convexity (arxiv.org/pdf/2105.04026).
Would you agree? If so, how does this apply to simulations?

Ah, yes, thank you. I initially read the quote to mean that physics restrict the algorithm, not that physics IS the algorithm.
For finding solutions, as you write, this distinction is important. Restrictions have to be baked in from the beginning, otherwise any “solution” will be meaningless.

This is actually interesting. Did she believe that the role of silicon in VLSI systems is similar to the role of neural substrates in nervous systems?

If so, I would agree with Brad that I don't see the big difference. But simulations will always be a poor man's approximation

Why stop there? If I had something to sell, I would want to hijack every neuromodulator I could get my hands on. Eternal chemical bliss 🏴‍☠️

That's a great point! We cannot equate the hardware with the model. "NeuroAI" is indeed not a model.

I wonder whether the ambiguity would stand if we had a solid understanding of how the substrate related to the algorithm. Where does physics/hardware stop and where does computation begin?

Oh dear, that's terrible and borderline denigrative 😬

I'm wondering how to address this. Isn't part of the reason why some words remain less viscous that they have strong definitions? Could it be that part of the problem is that #NeuroAI is too vague? What if we need better definitions?
We could start with "intelligence"...

I agree that languages inevitably evolve, but at the same time words have to *mean* something.
Personally, I consider "neuromorphic" to apply to concepts outside hardware. I am open to changing my mind, but there have been so many conflicting takes on this that I am, frankly, confused.

Neuromorphic Programming: Emerging Directions for Brain-Inspired Hardware The value of brain-inspired neuromorphic computers critically depends on our ability to program them for relevant tasks. Currently, neuromorphic hardware often relies on machine learning methods adapt...

Curious about #neuromorphic computing? 🧠💻
We want to revolutionalize the way we program brain-inspired systems and are plotting a course in a new publication with Steven Abreu: ieeexplore.ieee.org/abstract/doc... (or open access arxiv.org/abs/2410.22352)
Let's build better neuromorphics together! 🚀

It seems like a neat paper on DSP, but could you tell me how this relates to continous computation?

GERD: Geometric event response data generation Event-based vision sensors are appealing because of their time resolution, higher dynamic range, and low-power consumption. They also provide data that is fundamentally different from conventional fra...

New preprint out on a data generator for geometric event responses. Here's to hoping this will make event-based models more aware of geometry and symmetry ✨

#neuromorphic #computervision #dataset

arxiv.org/abs/2412.03259

I think that's exactly the right mindset. It'll be hard to balance concerns when the new wave of hardware hits, but sticking to the "fast weights" bit is crucial. Nice.
My hunch still is that this requires a continuous representation, but I may be wrong 🤔 maybe we should do a survey?

open-neuromorphic.org ☺️

I'm still not sold on the MLIR angle. It may help integration of existing models, but MLIR is inherently digital. Wouldn't that hinder the computational expressivity of mixed-signal hardware?

Just listened to the Lex Fridman podcast with Yann Lecun, emphasizing the importance of open #AI. Couldn't agree more!
As an open source maintainer for #neuromorphic tech, thank you for the praise and encouragement. I needed that today ❤️

open.spotify.com/episode/0bXy...

#neuromorphic computing is promising to drive artificial intelligence much further---and this blogpost benchmarks SNN libraries, so you know where to start.
Join us on Discord discord.gg/C9bzWgNmqk

open-neuromorphic.org/blog/spiking...