Spiking neural networks with Hebbian plasticity for unsupervised representation 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.
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}
}