Representation learning using event-based STDP

• Published in: Neural networks Vol. 105; pp. 294 - 303
• Main Authors: Tavanaei, Amirhossein, Masquelier, Timothée, Maida, Anthony
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.09.2018; Elsevier
• Subjects: Bio-inspired model; Cognitive science; Neuroscience; Quantization; Representation learning; Spiking neural networks; STDP; Representation learning; Quantization; STDP; Bio-inspired model; Spiking neural networks
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2018.05.018

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) layer for extracting visual features. The method introduces a novel spike-timing-dependent plasticity (STDP) learning rule and a threshold adjustment rule both derived from a vector quantization-like objective function subject to a sparsity constraint. The STDP rule is obtained by the gradient of a vector quantization criterion that is converted to spike-based, spatio-temporally local update rules in a spiking network of leaky, integrate-and-fire (LIF) neurons. Independence and sparsity of the model are achieved by the threshold adjustment rule and by 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.