Spiking neural networks with Hebbian plasticity for unsupervised representation learning
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.