Learning Precise Spike Timings with Eligibility Traces

TL;DR

This paper explores how eligibility traces in spiking neural networks can be extended to incorporate spike timing dependent plasticity (STDP), enabling more precise spike timing learning in SNNs.

Contribution

The paper introduces modifications to eligibility traces that allow STDP-like learning in LIF neurons, enhancing spike timing precision in SNN training.

Findings

Eligibility traces can be extended to include STDP effects.

STDP-aware LIF neurons can learn precise spike timings.

Derived gradients enable timing-based learning in simple SNN models.

Abstract

Recent research in the field of spiking neural networks (SNNs) has shown that recurrent variants of SNNs, namely long short-term SNNs (LSNNs), can be trained via error gradients just as effective as LSTMs. The underlying learning method (e-prop) is based on a formalization of eligibility traces applied to leaky integrate and fire (LIF) neurons. Here, we show that the proposed approach cannot fully unfold spike timing dependent plasticity (STDP). As a consequence, this limits in principle the inherent advantage of SNNs, that is, the potential to develop codes that rely on precise relative spike timings. We show that STDP-aware synaptic gradients naturally emerge within the eligibility equations of e-prop when derived for a slightly more complex spiking neuron model, here at the example of the Izhikevich model. We also present a simple extension of the LIF model that provides similar gradients. In a simple experiment we demonstrate that the STDP-aware LIF neurons can learn precise spike timings from an e-prop-based gradient signal.