# Unsupervised Sparse Coding-based Spiking Neural Network for Real-time Spike Sorting

arXiv: https://arxiv.org/abs/2506.24041 · HTML: https://mlsanity.com/paper/2506.24041/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 66 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [Efficient Neuromorphic Signal Processing with Loihi 2](https://mlsanity.com/paper/2111.03746/) (2021)
- [The Sparse Manifold Transform](https://mlsanity.com/paper/1806.08887/) (2018)
- [Sparse Coding by Spiking Neural Networks: Convergence Theory and Computational Results](https://mlsanity.com/paper/1705.05475/) (2017)
- [Sparse Coding on Stereo Video for Object Detection](https://mlsanity.com/paper/1705.07144/) (2017)
- [A Spike in Performance: Training Hybrid-Spiking Neural Networks with Quantized Activation Functions](https://mlsanity.com/paper/2002.03553/) (2020)
- [Removing Noise from Extracellular Neural Recordings Using Fully Convolutional Denoising Autoencoders](https://mlsanity.com/paper/2109.08945/) (2021)
- [Dictionary Learning with Accumulator Neurons](https://mlsanity.com/paper/2205.15386/) (2022)
- [Adaptive Approach For Sparse Representations Using The Locally Competitive Algorithm For Audio](https://mlsanity.com/paper/2109.14705/) (2021)
- [NeuSort: An Automatic Adaptive Spike Sorting Approach with Neuromorphic Models](https://mlsanity.com/paper/2304.10273/) (2023)

## Abstract (arXiv)

Spike sorting is a crucial step in decoding multichannel extracellular neural signals, enabling the identification of individual neuronal activity. A key challenge in brain-machine interfaces (BMIs) is achieving real-time, low-power spike sorting at the edge while keeping high neural decoding performance. This study introduces the Neuromorphic Sparse Sorter (NSS), a compact two-layer spiking neural network optimized for efficient spike sorting. NSS leverages the Locally Competitive Algorithm (LCA) for sparse coding to extract relevant features from noisy events with reduced computational demands. NSS learns to sort detected spike waveforms in an online fashion and operates entirely unsupervised. To exploit multi-bit spike coding capabilities of neuromorphic platforms like Intel's Loihi 2, a custom neuron model was implemented, enabling flexible power-performance trade-offs via adjustable spike bit-widths. Evaluations on simulated and real-world tetrode signals with biological drift showed NSS outperformed established pipelines such as WaveClus3 and PCA+KMeans. With 2-bit graded spikes, NSS on Loihi 2 outperformed NSS implemented with leaky integrate-and-fire neuron and achieved an F1-score of 77% (+10% improvement) while consuming 8.6mW (+1.65mW) when tested on a drifting recording, with a computational processing time of 0.25ms (+60 us) per inference.