Learning Precise Spike Timings with Eligibility Traces
This addresses a bottleneck in spiking neural networks for researchers in neuromorphic computing, but it is incremental as it builds on existing e-prop methods.
The paper tackled the limitation of existing spiking neural network training methods in fully exploiting spike timing dependent plasticity (STDP), which restricts the ability to learn precise spike timings. They demonstrated that STDP-aware synaptic gradients emerge in more complex neuron models, enabling learning of precise spike timings in a simple experiment.
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.