# Representation Learning using Event-based STDP

## TL;DR

This paper introduces a biologically plausible, event-based learning method for spiking neural networks that effectively extracts visual features with low reconstruction loss, suitable for hardware implementation.

## Contribution

It proposes a novel spike-timing-dependent plasticity (STDP) rule and threshold adjustment mechanism derived from vector quantization, enabling sparse, competitive learning in SNNs.

## Key findings

- Achieves low reconstruction loss comparable to state-of-the-art methods
- Demonstrates effective visual feature extraction on MNIST and natural images
- Provides a biologically plausible and hardware-friendly learning rule

## 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 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.