Hardware-Conscious Software Training (HCST) and circuit-derived modeling for fully analog ReRAM inference, including finite-gain and fixed-offset effects.
-
Updated
Oct 7, 2026 - Python
Hardware-Conscious Software Training (HCST) and circuit-derived modeling for fully analog ReRAM inference, including finite-gain and fixed-offset effects.
Differential memristive crossbar with a hardware-friendly in-situ (Manhattan/sign-rule) learning rule, tested on parity-3 — the calibrated in-memory-compute baseline of the physical-learning-substrates portfolio. Verdict #1: PASS, learns parity-3 at SNR ~24.5 (half co-located: physics activations, off-array error sign, physical-pulse increment).
To associate your repository with the crossbar-array topic, visit your repo's landing page and select "manage topics."