# Variation Aware Training of Hybrid Precision Neural Networks with 28nm HKMG FeFET Based Synaptic Core

arXiv: https://arxiv.org/abs/2202.10912 · HTML: https://mlsanity.com/paper/2202.10912/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 28 references that are in the map.
- First posted on arXiv 21 Feb 2022.

## Builds on (most cited first, 3 of 3)

- [Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices](https://mlsanity.com/paper/1603.07341/) (2016)
- [Mitigating Asymmetric Nonlinear Weight Update Effects in Hardware Neural Network based on Analog Resistive Synapse](https://mlsanity.com/paper/1712.05895/) (2017)
- [Alleviation of Temperature Variation Induced Accuracy Degradation in Ferroelectric FinFET Based Neural Network](https://mlsanity.com/paper/2103.03111/) (2021)

## Built on by (most cited first, 1 of 1)

- [Making Analog Training Scale: Co-Designing Mapping, Optimizer, and Converters](https://mlsanity.com/paper/2609.36584/) (2026)

## Abstract (arXiv)

This work proposes a hybrid-precision neural network training framework with an eNVM based computational memory unit executing the weighted sum operation and another SRAM unit, which stores the error in weight update during back propagation and the required number of pulses to update the weights in the hardware. The hybrid training algorithm for MLP based neural network with 28 nm ferroelectric FET (FeFET) as synaptic devices achieves inference accuracy up to 95% in presence of device and cycle variations. The architecture is primarily evaluated using behavioral or macro-model of FeFET devices with experimentally calibrated device variations and we have achieved accuracies compared to floating-point implementations.