An STDP-Based Supervised Learning Algorithm for Spiking Neural Networks
This work addresses the challenge of supervised learning in biologically plausible SNNs, which is an incremental step in neuromorphic computing.
The authors tackled the problem of supervised learning in spiking neural networks by proposing an STDP-based algorithm for hierarchical SNNs with LIF neurons, achieving classification accuracy on MNIST that approaches that of a similarly structured MLP trained with back-propagation.
Compared with rate-based artificial neural networks, Spiking Neural Networks (SNN) provide a more biological plausible model for the brain. But how they perform supervised learning remains elusive. Inspired by recent works of Bengio et al., we propose a supervised learning algorithm based on Spike-Timing Dependent Plasticity (STDP) for a hierarchical SNN consisting of Leaky Integrate-and-fire (LIF) neurons. A time window is designed for the presynaptic neuron and only the spikes in this window take part in the STDP updating process. The model is trained on the MNIST dataset. The classification accuracy approach that of a Multilayer Perceptron (MLP) with similar architecture trained by the standard back-propagation algorithm.