A Unified Platform to Evaluate STDP Learning Rule and Synapse Model using Pattern Recognition in a Spiking Neural Network

2025/06/24 by Maskeen, Jaskirat Singh, Lashkare, Sandip
#FOS: Computer and information sciences #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.2506.19377

Abstract

We develop a unified platform to evaluate Ideal, Linear, and Non-linear Pr_0.7Ca_0.3MnO₃ 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.

Citations

• Fully Spiking Neural Network for Legged Robots
• Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networks
• BackEISNN: A Deep Spiking Neural Network with Adaptive Self-Feedback and Balanced Excitatory-Inhibitory Neurons
• A simple and efficient SNN and its performance & robustness evaluation method to enable hardware implementation
• Gradient-based learning applied to document recognition

Related

• A Fully Memristive Spiking Neural Network with Unsupervised Learning
• Spiking Neural Networks for Inference and Learning: A Memristor-based Design Perspective
• Implementation of Multiple-Step Quantized STDP Based on Novel Memristive Synapses
• Spike Agreement Dependent Plasticity: A scalable Bio-Inspired learning paradigm for Spiking Neural Networks
• Multiple-Step Quantized Triplet STDP Implemented with Memristive Synapse