SPICE simulations demonstrate on-chip learning in a fully connected neural network using conventional MOSFETs as synapses, achieving high accuracy on the Iris dataset with performance comparable to NVM-based systems.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On-chip learning in a conventional silicon MOSFET based Analog Hardware Neural Network
SPICE simulations demonstrate on-chip learning in a fully connected neural network using conventional MOSFETs as synapses, achieving high accuracy on the Iris dataset with performance comparable to NVM-based systems.