Feedforward spiking neural networks are not transformers (yet): a learning-theoretic framework for long-range dependencies and biological efficiency

Spiking neural networks offer a promising route toward low-power sequence computation on neuromorphic hardware, but they continue to lag behind attention-based artificial neural networks on long-context tasks. A central open question is whether this gap reflects only implementation and optimization...

Celý popis

Podrobná bibliografie

Hlavní autoři:	William Fishell, Gord Fishell, Suraj Honnuraiah
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IOP Publishing 2026-01-01
Edice:	Neuromorphic Computing and Engineering
Témata:	spiking neural networks sample complexity covering numbers neuromorphic computing theoretical neuroscience
On-line přístup:	https://doi.org/10.1088/2634-4386/ae8626
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!