A neural network for online spike classification that improves decoding accuracy

Abstract

Separating neural signals from noise can improve brain-computer interface performance and stability. However, most algorithms for separating neural action potentials from noise are not suitable for use in real time and have shown mixed effects on decoding performance. With the goal of removing noise that impedes online decoding, we sought to automate the intuition of human spike-sorters to operate in real time with an easily tunable parameter governing the stringency with which spike waveforms are classified. We trained an artificial neural network with one hidden layer on neural waveforms that were hand-labeled as either spikes or noise. The network output was a likelihood metric for each waveform it classified, and we tuned the network’s stringency by varying the minimum likelihood value for a waveform to be considered a spike. Using the network’s labels to exclude noise waveforms, we decoded remembered target location during a memory-guided saccade task from electrode arrays implanted in prefrontal cortex of rhesus macaque monkeys. The network classified waveforms in real time, and its classifications were qualitatively similar to those of a human spike-sorter. Compared with decoding with threshold crossings, in most sessions we improved decoding performance by removing waveforms with low spike likelihood values. Furthermore, decoding with our network’s classifications became more beneficial as time since array implantation increased. Our classifier serves as a feasible preprocessing step, with little risk of harm, that could be applied to both off-line neural data analyses and online decoding. NEW & NOTEWORTHY Although there are many spike-sorting methods that isolate well-defined single units, these methods typically involve human intervention and have inconsistent effects on decoding. We used human classified neural waveforms as training data to create an artificial neural network that could be tuned to separate spikes from noise that impaired decoding. We found that this network operated in real time and was suitable for both off-line data processing and online decoding.

Topologically optimal design and failure prediction using conditional generative adversarial networks

“…Even though the validation loss has sudden spikes during the learning process (see Figure 7(A)), it converges in parallel with the train loss approximately after 1800 epochs. These spikes in the validation loss curve are natural and expected, 51,[66][67][68] because the validation dataset is not used for the stage 2: CNN model training.…”

From End to End: Gaining, Sorting, and Employing High-Density Neural Single Unit Recordings

“…Prior to action potential detection, it is worth considering a filtering stage, as lower frequency local field potentials, mostly defined as frequencies below 300–500 Hz, may encumber further analyses (Issar et al, 2020 ). By this step, the quality of spikes should also enhance; hence, filters behave as balancing factors between incorrectly detected or discarded events even without previous thresholding (Zhang and Constandinou, 2021b ).…”

“…Combined methods that filter and set threshold parallelly, with adjustable weights depending on the source, are signal-to-noise ratio optimal filters and proposed to reduce computational complexity and upgrade discriminating capability (Wouters and Kloosterman, 2019 ). As a next chapter in filtering and detection paradigms, neural networks with barely one hidden layer can fulfill the tasks of preprocessing and event detection (Issar et al, 2020 ).…”

improv: A software platform for real-time and adaptive neuroscience experiments

“…But adaptive experiments, by definition, require analysis as the data arrive. Although modern computing and new analysis algorithms have made online preprocessing of large-scale recordings feasible (Friedrich, 2016; Giovannucci, 2019; Issar, 2020), significant technical barriers have prevented their integration into routine experimental pipelines. Existing algorithms and software are not constructed to operate under streaming paradigms with many parallel tasks, as is required for live experimentation.…”