On-Chip Learning with Memristor-Based Neural Networks: Assessing Accuracy and Efficiency Under Device Variations, Conductance Errors, and Input Noise

M. Reza Eslami, Dhiman Biswas, Soheib Takhtardeshir +2

This paper presents a memristor-based compute-in-memory hardware accelerator for on-chip training and inference, focusing on its accuracy and efficiency against device variations,…