The news release on our recent publication about physical self-learning machines with a new all-physical training procedure, explained in layperson's terms:

Efficient training for artificial intelligence https://idw-online.de/de/news820323

#neuromorphic #NeuralNetworks
@MPI_ScienceOfLight

Our workshop on #neuromorphic computing closed yesterday evening. A great line up of speakers and lively discussions. The field is moving fast with many new ideas on aspects like training and progress on a variety of physical platforms (electronic, magnetic, optical, mechanical etc). Most likely to be continued in 2 years!

@MPI_ScienceOfLight
#machinelearning
@sylvaingigan

Great panel discussion today at our workshop on neuromorphic computing. Andrea Liu, @sylvaingigan , Julie Grollier, Abu Sebastian and Wolfram Pernice were discussing about which applications are most attractive, where neuromorphic systems can outperform digital neural networks, what are the ethical considerations etc.
@MPI_ScienceOfLight #neuromorphic

Looking forward to our workshop 'Frontiers of Neuromorphic Computing' that will start tomorrow morning at the @MPI_ScienceOfLight Max Planck Institute for the Science of Light.

We are trying to record at least most of the talks and release them later (with some delay) on video.

https://indico.mpl.mpg.de/event/15/

#neuromorphic #NeuralNetworks #machinelearning

@MPI_ScienceOfLight

This new physical training approach works without any mathematical algorithm or feedback control, unlike any previously available technique.

There is an urgent need for finding alternatives to power-hungry digital artificial neural networks, and the field of #neuromorphic computing strives to exploit physical systems in optics or other platforms to this end. ...

2/n

@GindyDraws @web3isgreat that's easy. Something with #quantumcomputing or #neuromorphic computing 😆

Here's a really interesting (long) paper on what a theory of computing based on arbitrary physical substrates might look like: http://arxiv.org/abs/2307.15408

#NewPaper #TheoreticalComputerScience #neuromorphic #CogSci #CognitiveScience #VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #AnalogComputing

Quantum Material Exhibits “Non-Local” Behavior That Mimics Brain Function https://thequantuminsider.com/?p=2357808 #Research #Alex_Frañó #Nano_Letters #neuromorphic #Neuromorphic_Computing #nonlocality #QMEENC #Rutgers #University_of_California #University_of_California_San_Diego #quantumdaily Insider Brief Researchers discover that at electrical stimuli passed between neighboring electrodes can also affect non-neighboring electrodes. The team suggests that this insight into non-locality could

https://www.intel.com/content/www/us/en/newsroom/news/intel-unveils-neuromorphic-loihi-2-lava-software.html

Interesting development: Intel advances in neuromorphic computation.

I think this will get interesting once this hardware is available on the market.

#ai #hardware #intel #neuromorphic #loihi2

@thezerobit for fielded devices I gotta agree. However, for algorithmic explanation of an approach to computing that might *actually* be well suited to memristors (and other proposed noisy hardware technologies) there's a reasonable amount of activity in the Vector Symbolic Architecture / Hyperdimensional Computing space:

https://duckduckgo.com/?t=h_&q=memristor+%22vector+symbolic+architecture%22+&ia=web

https://duckduckgo.com/?t=h_&q=memristor+hyperdimensional+&ia=web

#memristor #neuromorphic #VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing

I remember quite a bit of hype around memristors years ago (according to Google Trends, interest spiked in 2008 and 2010).
The HYPE was big. Memristors act a *tiny* bit like synapses, so everyone reported breathlessly on how they would be used to build AI devices (with literally zero justification or algorithmic explanation, just feels, man).

It's 2023, where are my #memristor powered #neuromorphic computers, man?

Contrarily to the hype, #AI is contributing to increase #carbonfootprint. I wrote a short summary, and proposed few ideas (sparse #neuralnetworks, simpler #LLM models, #neuromorphic hardware, #federatedlearning, #transferlearning)
https://alecrimi.substack.com/p/ai-carbon-footprint
#ml #sustainability

Dancing Magnons: Team @HZDR advances to next step toward #neuromorphic computing
Scientists of EU funded project #NIMFEIA demonstrate that their approach can be seamlessly integrated into conventional chip manufacturing, as they report:
▶️ https://www.hzdr.de/presse/magnonen

Image: HZDR / H.Schultheiß

Our manuscript on how to achieve robust computation in mixed-signal (noisy) #neuromorphic electronic systems, using the same strategies and mechanisms that animal #brains use has finally been published!!! 💥 😂
https://doi.org/10.1088/2634-4386/ace64c

The videos of the talks from the Midnight Sun Workshop on Vector Symbolic Architectures and Hyperdimensional Computing are now online at:

https://sites.google.com/ltu.se/midnightvsa/abstracts?authuser=0

#VSA #VectorSymbolicArchitecture #HDC #HyperdimensionalComputing #CogSci #CognitiveScience #neuromorphic #UnconventionalComputing

New on the Science in Parallel #podcast🎙️
Luis Ceze of the University of Washington and OctoML, Bert de Jong of Berkeley Lab, and Katie Schuman of the University of Tennessee discuss strengths and challenges of emerging processors, such as #molecular, #quantum and #neuromorphic hardware. https://scienceinparallel.libsyn.com/season-3-episode-4-beyond-exascale-exploring-emerging-hardware

#QSAcenter #DOEscience #HPC

@giacomoi

"While Moore’s law has driven exponential computing power expectations, its nearing end calls for new avenues ... neuromorphic engineering represents a paradigm shift in computing based on the implementation of spiking neural network architectures in which processing and memory are tightly colocated."
https://ieeexplore.ieee.org/document/10144567

#neuroscience #neuromorphic #MooresLaw

I'm happy to announce that Charlotte Frenkel's (and my and David Bol's) #neuromorphic paper on "Tradeoffs and Synergies Between Natural and Artificial Intelligence" is finally out: https://ieeexplore.ieee.org/document/10144567

And we conclude the theory sessions of the #ANN course with an engaging guest lecture from Inton Tsang - @inton (imec) on the topic of #SNN and #neuromorphic computing. #uantwerp

Proud to see my #UZH colleague Melika Payvand representing the #ISCAS2023 highlights on #thebird site!
(and there is even our DPI #neuromorphic circuit on her slides!)

https://pbs.twimg.com/media/FwxXL5GXgAIwTOf?format=jpg&name=4096x4096