English

Spiking neural networks with Hebbian plasticity for unsupervised representation learning

Neural and Evolutionary Computing 2023-05-12 v2 Machine Learning

Abstract

We introduce a novel spiking neural network model for learning distributed internal representations from data in an unsupervised procedure. We achieved this by transforming the non-spiking feedforward Bayesian Confidence Propagation Neural Network (BCPNN) model, employing an online correlation-based Hebbian-Bayesian learning and rewiring mechanism, shown previously to perform representation learning, into a spiking neural network with Poisson statistics and low firing rate comparable to in vivo cortical pyramidal neurons. We evaluated the representations learned by our spiking model using a linear classifier and show performance close to the non-spiking BCPNN, and competitive with other Hebbian-based spiking networks when trained on MNIST and F-MNIST machine learning benchmarks.

Keywords

Cite

@article{arxiv.2305.03866,
  title  = {Spiking neural networks with Hebbian plasticity for unsupervised representation learning},
  author = {Naresh Ravichandran and Anders Lansner and Pawel Herman},
  journal= {arXiv preprint arXiv:2305.03866},
  year   = {2023}
}
R2 v1 2026-06-28T10:27:25.790Z