AI RESEARCH
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations
arXiv CS.LG
•
ArXi:2605.15216v1 Announce Type: cross Always-on AI applications, from environmental sensors to biomedical implants, require ultra-low power consumption. Analog circuits offer a path to sub-microwatt inference, yet existing analog implementations are limited to feedforward architectures: extending them to recurrent dynamics has been considered impractical due to noise accumulation through temporal feedback. We nstrate that this barrier can be overcome through hardware-software co-design.