What question did this study set out to answer?

This work aims to compare methods for setting thresholds in spiking neurons during the conversion from traditional neural networks.

April 10, 2026

Evaluation of the Accuracy of Converting a Traditional Neural Network into a Pulsed One with Different Methods for Selecting the Neuron Threshold

Key Points

This work aims to compare methods for setting thresholds in spiking neurons during the conversion from traditional neural networks.
Compared two methods for setting neuron thresholds
Used spoken digit classification tasks (Heidelberg Digits and Russian Speech Commands)
Analyzed output differences between traditional and spiking networks
Minimizing differences between outputs improves classification accuracy on simpler tasks
Greater losses observed on complex datasets due to premature spiking
Complexity of datasets affects the effectiveness of threshold conversion

Abstract

This work compares two of the most commonly used methods for setting the thresholds of spiking neurons when transferring weights to them from a traditional neural network. Using the example of the spoken digit classification tasks Heidelberg Digits (HD) and Russian Speech Commands (RuSC), it is demonstrated that setting the thresholds by minimizing the differences between the outputs of a traditional neural network layer and the estimated number of spikes in a spiking network allows for higher classification accuracy. However, on the more complex RuSC dataset, the losses incurred when converting a traditional network to a spiking one are greater due to the issues of premature spiking and late input.

Bookmark

Cite This Study

Rybka et al. (Sat,) studied this question.

synapsesocial.com/papers/69d893406c1944d70ce044d3 https://doi.org/https://doi.org/10.1134/s0005117925601137

Bookmark