Jens Egholm

@jegp
331 Followers
94 Following
150 Posts

Working with neuromorphic and analog computing. Curious about abstractions. Cares about #FOSS

Author of Neuromorphic Intermediate Representation in Nature Communications: https://www.nature.com/articles/s41467-024-52259-9

Email[email protected]
Websitejepedersen.dk
GitHubgithub.com/jegp
LinkedInhttps://www.linkedin.com/in/jens-egholm-pedersen-69543117/

I've been thinking a lot about how to turn the theoretical benefits of neuromorphic computing into something practical during my PhD. And the new paper on "Neuromorphic computing at scale" by Dr. Kudiphipudi et al. explains exactly what we need to scale:
- R&D groups
- Easy and open-source software
- Benchmarks
- Interfacing with other tech

Which I'm happy about because it confirms my own thinking 😄 And they cite both Norse and NIR 🤗

Highly recommended read!

https://www.nature.com/articles/s41586-024-08253-8

Neuromorphic computing at scale - Nature

Approaches for the development of future at-scale neuromorphic systems based on principles of biointelligence are described, along with potential applications of scalable neuromorphic architectures and the challenges that need to be overcome.

Nature
Google just let me know that my work has been cited 100 times. I feel there's so much still to communicate, but I'm grateful my work is making a small dent in the academic world 😌

I'm so sorry, but I have to self-promote something for a second. Because this is just too cool.

Imagine this. New computer. New #neuromorphic event camera. AND ONE COMMAND TO GET IT RUNNING. Right out of the box. No magic. No installs. It. Just. Works. Thank you #nixos <3

#neuromorphic computing is promising to drive artificial intelligence much further. Here's a benchmark of SNN libraries, so you know where to start 😎
Join the open-source crowd on Discord discord.gg/C9bzWgNmqk

https://open-neuromorphic.org/blog/spiking-neural-network-framework-benchmarking/

Spiking Neural Network (SNN) Library Benchmarks

Discover the fastest Spiking Neural Network (SNN) frameworks for deep learning-based optimization. Performance, flexibility, and more analyzed in-depth

SNUFA flash talks are online, including my presentation on the Neuromorphic Intermediate Representation (#NIR) https://youtu.be/q8c7gIf9tpw?feature=shared&t=607

Happy to slowly start promoting our awesome work on bringing neuromorphic platforms together. github.com/neuromorphs/nir

Also proud to be featured with a wonderfully dorky snapshot 😂 Nicely captured @neuralreckoning

SNUFA 2023 Flash talks

YouTube
Anyone else feeling this? 😅
#neuromorphic

How do we fund software for event cameras?

Event cameras are wonderful, but the tooling is abysmal! I am in touch with developers and manufacturers in the field to push open-source tools. There is plenty of talent, but how to fund this?
#neuromorphic #eventcamera #machinevision

YouTube's speech recognition algorithm never fails to crack me up. Here are some gems from Lawvere 💎

"two monads" -> to moon hats
"cartesian closed" -> parties and clothes
"category with" -> technical wizard (!)
"category of algebras" -> category Val Venis (a wrestler)
"hom of D*" -> Mohammad do you start
"of sets or signals" -> success for seniors
"adjointness" -> edge whiteness
"toposes" -> tow poses

😂

It's time to #introduce myself! ✨

I'm a PhD student working with #neuromorphic computing and control systems. I've worked on spiking neural networks (https://github.com/norse/norse) and event-based vision (https://jegp.github.io/coordinate-regression/). I enjoy talking, thinking, and working towards better abstractions, reproducible #science and #FOSS.

Here's a demo for closed-loop control systems 🤖 https://uzh.mediaspace.cast.switch.ch/media/NEUROTECH+TutorialA+Real-time+neuromorphics+with+Norse/0_hynhzm4b/12519

Find more at https://jepedersen.dk. Can't wait to meet you all on Mastodon! ❤️

GitHub - norse/norse: Deep learning with spiking neural networks (SNNs) in PyTorch.

Deep learning with spiking neural networks (SNNs) in PyTorch. - GitHub - norse/norse: Deep learning with spiking neural networks (SNNs) in PyTorch.

GitHub