anandsubramoney - Network

I'm happy to have played a tiny role in the writing of this excellent review paper talking about scaling neuromorphic computing with 22...

I'm happy to have played a tiny role in the writing of this excellent review paper talking about scaling neuromorphic computing with 22 other people. Props to Dhireesha for leading the effort: https://www.nature.com/articles/s41586-024-08253-8

The London Interdisciplinary Doctoral program (LIDo) is open for applications for funded PhDs. Get in touch with me if you're...

The London Interdisciplinary Doctoral program (LIDo) is open for applications for funded PhDs.

Get in touch with me if you're interested in modelling learning and in-context learning with bio-plausible computational models.

Lot of other cool projects available in the program too. Closes 11th Dec.

https://lido-dtp.ac.uk/apply

(UK only) #PhD studentships available at Royal Holloway, University of London Social Purpose Centre for Doctoral Training!Get in touch with...

(UK only) #PhD studentships available at Royal Holloway, University of London Social Purpose Centre for Doctoral Training!

Get in touch with me if you're interested in working on developing bio-inspired efficient ML methods (#neuromorphic ML) to improve energy efficiency and make large AI models more widely accessible!

More info here: https://www.royalholloway.ac.uk/studying-here/fees-and-funding/research-degrees/sources-of-funding/university-studentships/

AI generated text making its appearance in very mundane email newsletters. I guess this is the future now? Has anyone looked into why AI...

AI generated text making its appearance in very mundane email newsletters. I guess this is the future now? Has anyone looked into why AI generated text is so verbose and flowery?

Now, that's some way to get back at a bad PhD advisor 😅 (from Kolmogorov's wikipedia page)

Now, that's some way to get back at a bad PhD advisor 😅
(from Kolmogorov's wikipedia page)

Why does anyone fly on <1 hour short haul flights anyway? It has got to be the most miserable way to get from point A to point B compared...

Why does anyone fly on <1 hour short haul flights anyway? It has got to be the most miserable way to get from point A to point B compared to every other mode of transport. (I wonder, sitting on a short haul flight for the first time in a long time.)

You can find the code for this paper here: https://github.com/Efficient-Scalable-Machine-Learning/beyond-weights

You can find the code for this paper here: https://github.com/Efficient-Scalable-Machine-Learning/beyond-weights

If you're attending #ACM ICONS (https://icons.ornl.gov) today, check out the talk 🎙️ by Edoardo at 15:30 local time titled...

If you're attending #ACM ICONS (https://icons.ornl.gov) today, check out the talk 🎙️ by Edoardo at 15:30 local time titled "Beyond Weights". We'll be putting up the talk video soon as well. #ICONS2023

We fixed the network weights to scaled random ternary (+x/0/-x) values and trained ONLY the synaptic delays in the network. Does this work...

We fixed the network weights to scaled random ternary (+x/0/-x) values and trained ONLY the synaptic delays in the network. Does this work at all⁉️

Turns out it does!❗️We show that this can work as well as training the weights for various image classification datasets! We tested this on MNIST and Fashion-MNIST. This has of interesting implications for neuromorphic applications.
Link to paper: https://arxiv.org/abs/2306.06237

🚨Excited to share our new short SNN paper! 🧵One of the advantages of spiking neural networks is the ability to use temporal coding to...

🚨Excited to share our new short SNN paper! 🧵One of the advantages of spiking neural networks is the ability to use temporal coding to achieve efficient processing. Inspired by recent neurobiological evidence on myelin adaptation on short timescales Edoardo studied the limits of using ONLY synaptic delays with temporal representations for processing information in SNNs.

Ooh, this is an interesting study... It connects ancient Elamite with Brahui, which implies Elamite is the root of the dravidian...

Ooh, this is an interesting study... It connects ancient Elamite with Brahui, which implies Elamite is the root of the dravidian languages!
http://journal.uob.edu.pk/journal/index.php/alburz/article/view/370

Anyone has a bluesky invite they're willing to share?

Anyone has a bluesky invite they're willing to share?

We (Royal Holloway, University of London Dept. of Computer Science) are open to hosting MSCA (Marie Skłodowska-Curie Actions) post-doctoral...

We (Royal Holloway, University of London Dept. of Computer Science) are open to hosting MSCA (Marie Skłodowska-Curie Actions) post-doctoral fellows! 🎓💼 If you're a talented researcher looking for a vibrant academic environment to pursue your post-doc journey, we warmly welcome you to consider our institution. 🌍🔬 Join us in advancing cutting-edge research and expanding horizons! 🌟 More details here: https://euraxess.ec.europa.eu/jobs/hosting/msca-postdoctoral-fellowships-royal-holloway-university-london-call-expression

#MSCA #PostDocOpportunities #ResearchExcellence #JoinOurUniversity

I'm presenting a poster in the Sparse Neural Network workshop @sparsenn at #ICLR2023 on "Efficient Real Time Recurrent Learning...

I'm presenting a poster in the Sparse Neural Network workshop @sparsenn at #ICLR2023 on "Efficient Real Time Recurrent Learning through combined activity and parameter sparsity". Come by if you're around!

Link to paper: https://arxiv.org/abs/2303.05641

Joint work with @itsmekhallu @mschoene0 Christian Mayr and David Kappel

Joint work with @itsmekhallu @mschoene0 Christian Mayr and David Kappel

Come attend my talk on "Efficient recurrent architectures through activity sparsity and sparse back-propagation through time" in...

Come attend my talk on "Efficient recurrent architectures through activity sparsity and sparse back-propagation through time" in the Auditorium at 10:00am and come by the poster session at 11:30am @ #ICLR2023

Paper: https://openreview.net/forum?id=lJdOlWg8td
Code: https://github.com/Efficient-Scalable-Machine-Learning/EvNN

I'm going to be at #iclr2023 next week presenting our work on efficient recurrent networks (https://openreview.net/forum?id=lJdOlWg8td)...

I'm going to be at #iclr2023 next week presenting our work on efficient recurrent networks (https://openreview.net/forum?id=lJdOlWg8td) at the main conference on Wednesday and efficient RTRL (https://arxiv.org/abs/2303.05641) at the Sparse Neural Networks workshop on Friday. Our collaborators also have a few open PhD positions on these topics. So, If you want to chat about efficient ML, neuromorphic, open positions or anything else, hit me up!

RT @SeethingMeadAs we head towards a #ucurising marking and assessment boycott tomorrow, this short post is aimed at interested, non-lawyers...

RT @SeethingMead
As we head towards a #ucurising marking and assessment boycott tomorrow, this short post is aimed at interested, non-lawyers who would like to know why/how I argue as I do
https://protestmatters.wordpress.com/2023/04/19/a-non-lawyers-guide-to-deductions-from-pay-for-taking-asos-marking-boycotts-and-not-rescheduling-classes/
I hope it helps

RT @neuromatchThis is a reminder to prospective students and TAs for NMA 2023: the deadline for application is approaching (-6⃣ days)! ...

RT @neuromatch
This is a reminder to prospective students and TAs for NMA 2023: the deadline for application is approaching (-6⃣ days)! You have till April 24th to submit your application through the portal: https://academy.neuromatch.io

Don't miss out on this opportunity! Apply ASAP!

RT @latifnasserLast year, a coworker randomly asked me to hand-deliver an antique violin across the country. I said yes, because why not. I...

RT @latifnasser
Last year, a coworker randomly asked me to hand-deliver an antique violin across the country. I said yes, because why not. I had no idea what I was getting into, and now I need your help. A 🧵