Code for the weight distribution analysis of deep spiking neural networks built using the SpykeTorch tool.
DSNNs Analyzed:
• MozafariDeep.py: Reimplementation of the paper "Bio-Inspired Digit Recognition Using Reward-Modulated Spike-Timing- Dependent Plasticity in Deep Convolutional Networks" (https://www.sciencedirect.com/science/article/abs/pii/S0031320319301906).
• KheradpishehDeep.py: Reimplementation of the paper "STDP-based spiking deep convolutional neural networks for object recognition" (https://www.sciencedirect.com/science/article/pii/S0893608017302903).
All code for both of the networks analyzed and the SpykeTorch tool are copied directly from the SpykeTorch GitHub repo: https://github.com/miladmozafari/SpykeTorch.
This is an analysis of the weight distributions of two existing DSNNs from the above papers. The original files contained in this repo are: extractor.py, hist.py, parser.py, sparse.py, saved_l1.net, saved_l2.net, and kherweights.txt. ALL OTHER FILES ARE FROM THE SPYKETORCH REPO, please direct any issues or questions concerning these files directly to the SpykeTorch repo.