Reproduce “An Unsupervised STDP-based Spiking Neural Network Inspired By Biologically Plausible Learning Rules and Connections” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yiting Dong, Dongcheng Zhao, Yang Li, Yi Zeng
The authors propose an unsupervised spiking neural network that coordinates STDP with adaptive synaptic filtering, threshold balancing, lateral inhibition, and sample-temporal batch updates. These mechanisms regulate currents, firing, competition, and weight updates without labeled error correction. The system reports 97.9% accuracy on MNIST, versus 95.0% for a published STDP-only system, but this is a literature comparison, not a controlled component test.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.