Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions

NeurIPSOral2025

Authors: Zhaoxian Wu, Quan Xiao, Tayfun Gokmen, Omobayode Fagbohungbe, Tianyi Chen
Affiliation: Cornell University
Venue: NeurIPS 2025
Track: Oral

TL;DR

Leveraging a residual learning framework to support the model training on non-ideal analog in-memory computing hardware…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

memory rag

← All NeurIPS 2025 Oral papers · Browse the whole archive