A Faster Approach to Spiking Deep Convolutional Neural Networks
This work addresses the need for more efficient and accurate SNNs for machine learning applications, though it appears incremental as it builds on previous network structures.
The authors tackled the challenge of improving runtime and accuracy in deep convolutional spiking neural networks (SNNs) by proposing a network structure that reduces training iterations to once, uses PCA dimension reduction, weight quantization, timed outputs, and better hyperparameter tuning, resulting in fractionalized runtime and enhanced accuracy for colored image processing.
Spiking neural networks (SNNs) have closer dynamics to the brain than current deep neural networks. Their low power consumption and sample efficiency make these networks interesting. Recently, several deep convolutional spiking neural networks have been proposed. These networks aim to increase biological plausibility while creating powerful tools to be applied to machine learning tasks. Here, we suggest a network structure based on previous work to improve network runtime and accuracy. Improvements to the network include reducing training iterations to only once, effectively using principal component analysis (PCA) dimension reduction, weight quantization, timed outputs for classification, and better hyperparameter tuning. Furthermore, the preprocessing step is changed to allow the processing of colored images instead of only black and white to improve accuracy. The proposed structure fractionalizes runtime and introduces an efficient approach to deep convolutional SNNs.