Membrane-Dependent Neuromorphic Learning Rule for Unsupervised Spike Pattern Detection

TL;DR

This paper introduces a simple, hardware-friendly neuromorphic learning rule based on membrane potential that enables unsupervised spike pattern detection, replicating STDP capabilities and suitable for neuromorphic devices.

Contribution

The authors propose a novel, unidirectional post-synaptic potential dependent learning rule that is easy to implement on hardware and capable of unsupervised spike pattern classification.

Findings

Replicates pairwise STDP computational capabilities.

Enables unsupervised learning and classification of spatio-temporal spike patterns.

Suitable for hardware implementation due to unidirectional memory access.

Abstract

Several learning rules for synaptic plasticity, that depend on either spike timing or internal state variables, have been proposed in the past imparting varying computational capabilities to Spiking Neural Networks. Due to design complications these learning rules are typically not implemented on neuromorphic devices leaving the devices to be only capable of inference. In this work we propose a unidirectional post-synaptic potential dependent learning rule that is only triggered by pre-synaptic spikes, and easy to implement on hardware. We demonstrate that such a learning rule is functionally capable of replicating computational capabilities of pairwise STDP. Further more, we demonstrate that this learning rule can be used to learn and classify spatio-temporal spike patterns in an unsupervised manner using individual neurons. We argue that this learning rule is computationally powerful and also ideal for hardware implementations due to its unidirectional memory access.