Bravo
If ARM was an arm, BRN would be its biceps💪!
It looks like this chap Osvaldo Simeone from King's College is researching a different approach, a hybrid analogue-digital hardware architecture. This paper is very recent 16 Aug 2024.
Says here that "Xpikeformer achieves up to a 17.8--19.2× reduction in energy consumption compared to state-of-the-art digital ANN transformers and up to a 5.9--6.8× reduction compared to fully digital SNN transformers. "
Unfortunately am not tech savvy enough to know if this is bad news for us or if it could be something that benefits our technology as well.
Introducing Xpikeformer.
@Diogenese here's one more for you!
arxiv.org
Says here that "Xpikeformer achieves up to a 17.8--19.2× reduction in energy consumption compared to state-of-the-art digital ANN transformers and up to a 5.9--6.8× reduction compared to fully digital SNN transformers. "
Unfortunately am not tech savvy enough to know if this is bad news for us or if it could be something that benefits our technology as well.
Introducing Xpikeformer.
@Diogenese here's one more for you!
Xpikeformer: Hybrid Analog-Digital Hardware Acceleration for Spiking Transformers
This paper introduces Xpikeformer, a hybrid analog-digital hardware architecture designed to accelerate spiking neural network (SNN)-based transformer models. By combining the energy efficiency and temporal dynamics of SNNs with the powerful sequence modeling capabilities of transformers...