We develop a unified platform to evaluate Ideal, Linear, and Non-linear Pr0.7Ca0.3MnO3 memristor-based synapse models, each getting progressively closer to hardware realism, alongside four STDP learning rules in a two-layer SNN with LIF neurons and adaptive thresholds for five-class MNIST classification. On MNIST with small train set and large test set, our two-layer SNN with ideal, 25-state, and 12-state nonlinear memristor synapses achieves 92.73 %, 91.07 %, and 80 % accuracy, respectively, while converging faster and using fewer parameters than comparable ANN/CNN baselines.
@article{arxiv.2506.19377,
title = {A Unified Platform to Evaluate STDP Learning Rule and Synapse Model using Pattern Recognition in a Spiking Neural Network},
author = {Jaskirat Singh Maskeen and Sandip Lashkare},
journal= {arXiv preprint arXiv:2506.19377},
year = {2025}
}
Comments
This is a preprint with 12 pages and 12 figures. It has been accepted for presentation at ICANN 2025. The final authenticated version will be available in the proceedings published by Springer in the Lecture Notes in Computer Science (LNCS) series