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

2025-06-30

AI Summary

Addressing the challenge of simultaneously achieving real-time processing, low power consumption, and high accuracy in edge-based neuronal spike sorting for brain–computer interfaces, this paper proposes Neuromorphic Sparse Sorter (NSS), an unsupervised spiking neural network model based on sparse coding. NSS uniquely integrates the Local Competition Algorithm (LCA) with configurable-bitwidth spike encoding, enabling online learning and dynamic trade-offs between energy efficiency and classification performance on the Intel Loihi 2 neuromorphic chip. Its custom neuron model and sparse representation mechanism significantly improve robustness against biological drift. Evaluated on real tetrode recordings, NSS achieves a 77% F1 score—outperforming WaveClus3 and PCA+KMeans by 10%—with only 0.25 ms inference latency and 8.6 mW power consumption. This work establishes a novel paradigm for ultra-low-latency, energy-efficient neural decoding at the edge.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Learning on the Edge & Model Compression
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

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.

Problem

• Achieving real-time, low-power spike sorting for brain-machine interfaces.
• Extracting features from noisy neural signals with reduced computation.
• Improving spike sorting accuracy on drifting neural recordings.

Innovation

• Unsupervised spiking neural network for spike sorting
• Locally Competitive Algorithm for sparse coding
• Custom neuron model for multi-bit spike coding