Trained models from our paper. Code that generated these models found here: GitHub - audreydunn/spikemoid Notes: every folder at the lowest level has an info.txt which maps the models in that folder to the section of the paper Warnings: the testing loss stats reported for gestures are correct but incorrectly scaled. Rather than dividing the sum of the batches losses by the number of batches we divide by the total number of samples. In the paper we scale the learning curve up to adjust for this oversight
DE detection methods, and showing only false positive rates between 0 and 0.04, and false negative r...
Spike sorting is the process of retrieving the spike times of individual neurons that are present in...
Hods, and different sets of true positives. For these charts only the equal spike-ins are used as tr...
A Multi-Label Classification Dataset based on the NMNIST (Neuromorphic MNIST) dataset with two digit
Spiking Neural Networks (SNNs) are a promising research paradigm for low power edge-based computing....
The reported accuracy is measured on balanced test sets to mitigate class imbalance, median value an...
Rization normalization strategies. For these charts only the equal spike-ins are used as true negati...
Fig A. Improvement on test set loss saturates as the number of transition matrices increases. (a) Te...
Collection of datasets used in SpikeInterface Reports. Description of recordings: - recordings_50c...
Multiple measures have been developed to quantify the similarity between two spike trains. These mea...
<p>: Spike-to-spike variability plotted against the SNR of the recording shows a rapid increase in v...
<p>a. Comparison of estimated rates of false positive spikes () with actual proportion of false posi...
Information Theory enables the quantification of how much information a neuronal response carries ab...
Arization and DE detection methods. For these charts only the equal spike-ins are used as true negat...
WOS: 000399461300063We describe a method for computing a pair of spike detection thresholds, called ...
DE detection methods, and showing only false positive rates between 0 and 0.04, and false negative r...
Spike sorting is the process of retrieving the spike times of individual neurons that are present in...
Hods, and different sets of true positives. For these charts only the equal spike-ins are used as tr...
A Multi-Label Classification Dataset based on the NMNIST (Neuromorphic MNIST) dataset with two digit
Spiking Neural Networks (SNNs) are a promising research paradigm for low power edge-based computing....
The reported accuracy is measured on balanced test sets to mitigate class imbalance, median value an...
Rization normalization strategies. For these charts only the equal spike-ins are used as true negati...
Fig A. Improvement on test set loss saturates as the number of transition matrices increases. (a) Te...
Collection of datasets used in SpikeInterface Reports. Description of recordings: - recordings_50c...
Multiple measures have been developed to quantify the similarity between two spike trains. These mea...
<p>: Spike-to-spike variability plotted against the SNR of the recording shows a rapid increase in v...
<p>a. Comparison of estimated rates of false positive spikes () with actual proportion of false posi...
Information Theory enables the quantification of how much information a neuronal response carries ab...
Arization and DE detection methods. For these charts only the equal spike-ins are used as true negat...
WOS: 000399461300063We describe a method for computing a pair of spike detection thresholds, called ...
DE detection methods, and showing only false positive rates between 0 and 0.04, and false negative r...
Spike sorting is the process of retrieving the spike times of individual neurons that are present in...
Hods, and different sets of true positives. For these charts only the equal spike-ins are used as tr...