Sign Up to like & get
recommendations!
0
Published in 2025 at "IEEE Transactions on Electron Devices"
DOI: 10.1109/ted.2024.3516731
Abstract: Analog compute-in-memory (ACiM) systems show promise for energy-efficient AI inference, but their performance is hindered by variations in conductance, resulting in reduced accuracy. This work investigates the impact of mean error, which represents the discrepancy…
read more here.
Keywords:
mean error;
analog compute;
memory;
accuracy ... See more keywords