Ternary neural networks on RRAM crossbars are more resilient to wire parasitics and low-resolution ADCs than binary networks, at a 40% energy efficiency cost.
Modeling analog-digital-converter energy and area for compute-in-memory accel- erator design,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating the Scalability of Binary and Ternary CNN Workloads on RRAM-based Compute-in-Memory Accelerators
Ternary neural networks on RRAM crossbars are more resilient to wire parasitics and low-resolution ADCs than binary networks, at a 40% energy efficiency cost.