Domain wall dynamics in HM/FM nanotracks emulate ReLU neurons and step-like quantized synapses, yielding simulated ANN accuracies of 97% on MNIST and 86% on Fashion-MNIST.
Experimental demonstration and tolerancing of a large-scale neural network (165 000 synapses) using phase-change memory as the synaptic weight element
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mes-hall 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Spintronic Neuromorphic Hardware Using Domain Wall Based Neurons and Quantized Synapses
Domain wall dynamics in HM/FM nanotracks emulate ReLU neurons and step-like quantized synapses, yielding simulated ANN accuracies of 97% on MNIST and 86% on Fashion-MNIST.