Hal will be stopped for maintenance from friday on june 10 at 4pm until monday june 13 at 9am. More information
Skip to Main content Skip to Navigation
Journal articles

Representation learning using event-based STDP

Abstract : 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.
Document type :
Journal articles
Complete list of metadata

Contributor : Maxime Rosito Connect in order to contact the contributor
Submitted on : Thursday, April 28, 2022 - 10:58:37 AM
Last modification on : Thursday, April 28, 2022 - 11:04:12 AM


Explicit agreement for this submission




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



Record views


Files downloads