NELGMay 5, 2023

Spiking neural networks with Hebbian plasticity for unsupervised representation learning

arXiv:2305.03866v24 citations
Originality Incremental advance
AI Analysis

This work addresses representation learning for neuromorphic computing, but it is incremental as it adapts an existing non-spiking model to a spiking framework.

The authors tackled the problem of unsupervised representation learning by introducing a spiking neural network model with Hebbian plasticity, achieving performance close to non-spiking models and competitive with other Hebbian-based spiking networks on MNIST and F-MNIST benchmarks.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes