Self-heating electrochemical memory for high-precision analog computing (2505.15936v2)

Abstract: Analog computers hold promise to significantly reduce the energy consumption of artificial intelligence algorithms, but commercialization has been hampered by a fundamental scientific challenge - how to reliably store and process analog information with high precision. We present an approach based upon metal oxide memory cells that undergo controlled self-heating during programming with a newly developed, electro-thermo-chemical gate. The gate uniformly spreads heat and electrochemical reactions to enable wide, bulk-vacancy modulation which yields nine orders of magnitude in tunable analog resistance - three orders greater than other devices reported, with thousands of states. The gating profoundly reduces noise and drift to enable precision programming to targeted states within a few operations, lowering conductance errors by two orders of magnitude relative to other devices reported. Simulations show improvement in computational energy efficiency by at least 10x over other devices due to far greater scalability at higher precision. The results overturn long-held assumptions about the poor reliability and precision of analog resistance devices and opens the door to manufacturable, bulk metal-oxide devices and new applications that leverage high precision.