# Architectural Exploration of Hybrid Neural Decoders for Neuromorphic Implantable BMI

arXiv: https://arxiv.org/abs/2505.05983 · HTML: https://mlsanity.com/paper/2505.05983/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 32 references that are in the map.
- First posted on arXiv 9 May 2025.

## Builds on (most cited first, 7 of 7)

- [Training Spiking Neural Networks Using Lessons From Deep Learning](https://mlsanity.com/paper/2109.12894/) (2021)
- [A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)](https://mlsanity.com/paper/1708.04198/) (2017)
- [A 128 channel Extreme Learning Machine based Neural Decoder for Brain Machine Interfaces](https://mlsanity.com/paper/1509.07450/) (2015)
- [An Energy-Efficient Spiking Neural Network for Finger Velocity Decoding for Implantable Brain-Machine Interface](https://mlsanity.com/paper/2210.06287/) (2022)
- [Real-time Closed Loop Neural Decoding on a Neuromorphic Chip](https://mlsanity.com/paper/1812.03991/) (2018)
- [Combining SNNs with Filtering for Efficient Neural Decoding in Implantable Brain-Machine Interfaces](https://mlsanity.com/paper/2312.15889/) (2023)
- [Hybrid Event-Frame Neural Spike Detector for Neuromorphic Implantable BMI](https://mlsanity.com/paper/2405.08292/) (2024)

## Abstract (arXiv)

This work presents an efficient decoding pipeline for neuromorphic implantable brain-machine interfaces (Neu-iBMI), leveraging sparse neural event data from an event-based neural sensing scheme. We introduce a tunable event filter (EvFilter), which also functions as a spike detector (EvFilter-SPD), significantly reducing the number of events processed for decoding by 192X and 554X, respectively. The proposed pipeline achieves high decoding performance, up to R^2=0.73, with ANN- and SNN-based decoders, eliminating the need for signal recovery, spike detection, or sorting, commonly performed in conventional iBMI systems. The SNN-Decoder reduces computations and memory required by 5-23X compared to NN-, and LSTM-Decoders, while the ST-NN-Decoder delivers similar performance to an LSTM-Decoder requiring 2.5X fewer resources. This streamlined approach significantly reduces computational and memory demands, making it ideal for low-power, on-implant, or wearable iBMIs.