Representation Learning using Event-based STDP

Although representation learning methods developed within the framework of traditional neural networks are relatively mature, developing a spiking representation model remains a challenging problem. This paper proposes an event-based method to train a feedforward spiking neural network (SNN) for extracting visual features. The method introduces a novel spike-timing-dependent plasticity (STDP) rule derived from a vector quantization-like objective function subject to a sparsity constraint. Independence and sparsity of the model are achieved by a threshold adjustment rule and a softmax function implementing inhibition in the representation layer consisting of WTA-thresholded spiking neurons. Together, these mechanisms implement a form of spike-based, competitive learning. Two sets of experiments are performed on the MNIST and natural image datasets. The results demonstrate a sparse spiking visual representation model with low reconstruction loss comparable with state-of-the-art visual coding approaches, yet our rule is local in both time and space, thus biologically plausible and hardware friendly.