# Personalized Spiking Neural Networks with Ferroelectric Synapses for EEG Signal Processing

arXiv: https://arxiv.org/abs/2601.00020 · HTML: https://mlsanity.com/paper/2601.00020/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 64 references that are in the map.
- First posted on arXiv 22 Dec 2025.

## Builds on (most cited first, 17 of 17)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rules](https://mlsanity.com/paper/1801.05219/) (2018)
- [Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators](https://mlsanity.com/paper/2302.08469/) (2023)
- [Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices](https://mlsanity.com/paper/1603.07341/) (2016)
- [An Accurate EEGNet-based Motor-Imagery Brain-Computer Interface for Low-Power Edge Computing](https://mlsanity.com/paper/2004.00077/) (2020)
- [Roadmap to Neuromorphic Computing with Emerging Technologies](https://mlsanity.com/paper/2407.02353/) (2024)
- [Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Hand Gesture Recognition](https://mlsanity.com/paper/2106.11169/) (2021)
- [Versatile CMOS Analog LIF Neuron for Memristor-Integrated Neuromorphic Circuits](https://mlsanity.com/paper/2406.19667/) (2024)
- [About Pyramid Structure in Convolutional Neural Networks](https://mlsanity.com/paper/1608.04064/) (2016)
- [A Compact Online-Learning Spiking Neuromorphic Biosignal Processor](https://mlsanity.com/paper/2209.12384/) (2022)
- [Unsupervised local learning based on voltage-dependent synaptic plasticity for resistive and ferroelectric synapses](https://mlsanity.com/paper/2510.25787/) (2025)
- [Wheelchair automation by a hybrid BCI system using SSVEP and eye blinks](https://mlsanity.com/paper/2106.11008/) (2021)
- [High-Conductance, Ohmic-like HfZrO4 Ferroelectric Memristor](https://mlsanity.com/paper/2309.12070/) (2023)
- [Energy-convergence trade off for the training of neural networks on bio-inspired hardware](https://mlsanity.com/paper/2509.18121/) (2025)

## Abstract (arXiv)

Electroencephalography (EEG)-based brain-computer interfaces (BCIs) are strongly affected by non-stationary neural signals that vary across sessions and individuals, limiting the generalization of subject-agnostic models and motivating adaptive and personalized learning on resource-constrained platforms. Programmable memristive hardware offers a promising substrate for such post-deployment adaptation; however, practical realization is challenged by limited weight resolution, device variability, nonlinear programming dynamics, and finite device endurance. In this work, we show that spiking neural networks (SNNs) can be deployed on ferroelectric memristive synaptic devices for adaptive EEG-based motor imagery decoding under realistic device constraints, achieving classification performance comparable to software-based SNNs. We fabricate, characterize, and model the weight update in ferroelectric synapses. We then evaluate the deployment of convolutional-recurrent SNN architecture using two strategies. First, we adapt to SNNs a mixed precision strategy in which gradient-based updates are accumulated digitally and converted into discrete programming events only when a threshold is exceeded. Additionally, the weight update is device-aware and accounts for the nonlinear, state-dependent programming dynamics. During learning and adaptation, this scheme mitigates possible endurance and energy constraints. Second, we evaluate the transfer of software-trained weights followed by low-overhead on-device re-tuning. We show that, subject-specific transfer learning achieved by retraining only the final network layers improves classification accuracy. These results demonstrate that programmable ferroelectric hardware can support robust, low-overhead adaptation in spiking neural networks, opening a practical path toward personalized neuromorphic processing of neural signals.