Representation learning using event-based STDP

Amirhossein Tavanaei (1) , Timothée Masquelier (2) , Anthony Maida (1)

1 University of Louisiana
2 CERCO - Centre de recherche cerveau et cognition

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 spikebased, 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.

Mots clés: Representation learning; Spiking neural networks; Quantization; STDP; Bio-inspired model

Domaines: Neurosciences

Amirhossein Tavanaei, Timothée Masquelier, Anthony Maida. Representation learning using event-based STDP. Neural Networks, 2018, 105, pp.294--303. ⟨10.1016/j.neunet.2018.05.018⟩. ⟨hal-02341981⟩