A Sparse-Integrated Filtering Residual Spiking Neural Network for High-Accuracy Spike Sorting and Co-Optimization on Memristor Platforms
IEEE Transactions on Biomedical Circuits and Systems · 2026
DOI: 10.1109/tbcas.2025.3601403 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Circuits and Systems, 2026. Verfasst von Yiwen Zhu und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Neural Networks, Computer, Action Potentials, Signal Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Key R&D Program, National Natural Science Foundation of China, Shanghai Rising-Star Program.
Abstract (Originalsprache)
Brain-computer interfaces rely on precise decoding of neural signals, where spike sorting is a critical step to extract individual neuronal activities from complex neural data. This work presents a spiking neural network (SNN) framework for efficient spike sorting, named SIFT-RSNN. In the SIFT-RSNN, raw neural signals are encoded into spike trains using a threshold-based temporal encoding strategy, then a sparse-integrated filtering module refines misfiring spikes, enhancing data sparsity for pattern learning. The RSNN module with a membrane shortcut structure ensures efficient feature transfer and improves generalization performance of the overall system. The SIFT-RSNN achieves an accuracy of 96.2% and 99.6% on the Difficult1 and Difficult2 subsets of Leicester dataset, surpassing state-of-the-art methods. We also implement it on a compute-in-memory platform with 8k memristor cells utilizing quantization-free mapping method and propose two algorithm-hardware co-optimization strategies to mitigate non-ideal hardware effects: weight outlier pre-constraint (WOP) and noise adaptation training (NAT). After optimization, our algorithm continues to outperform existing spike sorting methods, achieving accuracies of 94.2% and 99.7%, while also demonstrating improved robustness. The memristor platform only exhibits a 2% and 1.5% accuracy drop compared to software results on the two difficult subsets. Additionally, it achieves 3.52 $ \boldsymbol{\mu}$J energy consumption and 0.5 ms latency per inference. This work offers promising solutions for brain-computer interface systems and neural prosthesis applications in the future.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Key R&D Program
- National Natural Science Foundation of China
- Shanghai Rising-Star Program
- National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University
- AI for Science Foundation of Fudan University
Zitieren
APA
Zhu, Y., Chen, J., Cheng, L., Zhu, F., Zhang, X., & Liu, Q. (2026). A Sparse-Integrated Filtering Residual Spiking Neural Network for High-Accuracy Spike Sorting and Co-Optimization on Memristor Platforms. IEEE Transactions on Biomedical Circuits and Systems. https://doi.org/10.1109/tbcas.2025.3601403
Vancouver
Zhu Y, Chen J, Cheng L, Zhu F, Zhang X, Liu Q. A Sparse-Integrated Filtering Residual Spiking Neural Network for High-Accuracy Spike Sorting and Co-Optimization on Memristor Platforms. IEEE Transactions on Biomedical Circuits and Systems. 2026. doi:10.1109/tbcas.2025.3601403
BibTeX
@article{Zhu2026,
author = {Zhu, Yiwen and Chen, Jingyi and Cheng, Lingli and Zhu, Fangduo and Zhang, Xumeng and Liu, Qi},
title = {A Sparse-Integrated Filtering Residual Spiking Neural Network for High-Accuracy Spike Sorting and Co-Optimization on Memristor Platforms},
journal = {IEEE Transactions on Biomedical Circuits and Systems},
year = {2026},
doi = {10.1109/tbcas.2025.3601403}
}
EUVIMED