Edge computing on TPU for brain implant signal analysis

Rokai, János; Ulbert, István; Márton, Gergely

doi:10.1016/j.neunet.2023.02.036

Cited by 2 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neuromorphic models have emerged as a promising approach for spike sorting in recent studies, showcasing the inherent advantages of efficient online learning [20][21][22][23][24]. Unlike traditional machine learning models that rely on static mathematical models, neuromorphic models, specifically spiking neural networks, possess natural online adaptive capabilities through plasticity-driven updating rules.…”

Section: Introductionmentioning

confidence: 99%

NeuSort: an automatic adaptive spike sorting approach with neuromorphic models

Yu,

Qi,

Pan

2023

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Spike sorting, a critical step in neural data processing, aims to classify spiking events from single electrode recordings based on different waveforms. This study aims to develop a novel online spike sorter, NeuSort, using neuromorphic models, with the ability to adaptively adjust to changes in neural signals, including waveform deformations and the appearance of new neurons. Approach. NeuSort leverages a neuromorphic model to emulate template-matching processes. This model incorporates plasticity learning mechanisms inspired by biological neural systems, facilitating real-time adjustments to online parameters. Results. Experimental findings demonstrate NeuSort’s ability to track neuron activities amidst waveform deformations and identify new neurons in real-time. NeuSort excels in handling non-stationary neural signals, significantly enhancing its applicability for long-term spike sorting tasks. Moreover, its implementation on neuromorphic chips guarantees ultra-low energy consumption during computation. Significance. NeuSort caters to the demand for real-time spike sorting in brain-machine interfaces through a neuromorphic approach. Its unsupervised, automated spike sorting process makes it a plug-and-play solution for online spike sorting.

show abstract

Section: Introductionmentioning

confidence: 99%

NeuSort: an automatic adaptive spike sorting approach with neuromorphic models

Yu,

Qi,

Pan

2023

J. Neural Eng.

View full text Add to dashboard Cite

show abstract

A fully automatic multichannel neural spike sorting algorithm with spike reduction and positional feature

Mohammadi,

Denman,

Klug

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

The sorting of neural spike data recorded by multichannel and high channel neural probes such as Neuropixels, especially in real-time, remains a significant technical challenge. Most neural spike sorting algorithms focus on sorting neural spikes post-hoc for high sorting accuracy - but reducing the processing delay for fast sorting, potentially even live sorting, is generally not possible with these alogorithms. Here we report our Graph nEtwork Multichannel (GEMsort) algorithm, which is largely based on graph network, to allow rapid neural spike sorting for multiple neural recording channels. This was accomplished by two innovations: In GEMsort, duplicated neural spikes recorded from multiple channels were eliminated from duplicate channels by only selecting the highest amplitude neural spike in any channel for subsequent processing. In addition, the channel from which the representative neural spike was recorded was used as an additional feature to differentiate between neural spikes recorded from different neurons having similar temporal features. These algorithmic modifications allow GEMsort to rapidly sort neural spikes and this approach is highly suitable to be implemented with digital circuitry for high processing speed and channel scalability. Synthetic and experimentally recorded multichannel neural recordings were used to evaluate the sorting performance of GEMsort. The sorting results of GEMsort were also compared with two other state-of-the-art sorting algorithms (Kilosort and Mountainsort) in sorting time and sorting agreements.

show abstract

Edge computing on TPU for brain implant signal analysis

Cited by 2 publications

References 41 publications

NeuSort: an automatic adaptive spike sorting approach with neuromorphic models

NeuSort: an automatic adaptive spike sorting approach with neuromorphic models

A fully automatic multichannel neural spike sorting algorithm with spike reduction and positional feature

Contact Info

Product

Resources

About