Paired Competing Neurons Improving STDP Supervised Local Learning In Spiking Neural Networks

TL;DR

This paper introduces S2-STDP, a supervised learning rule for SNNs, and a Paired Competing Neurons architecture, improving classification accuracy on image datasets by combining supervised STDP with intra-class competition.

Contribution

The paper proposes S2-STDP for supervised training of SNNs and introduces PCN architecture to enhance neuron specialization and classification performance.

Findings

Outperforms state-of-the-art supervised STDP methods on MNIST, Fashion-MNIST, and CIFAR-10.

PCN improves S2-STDP performance without extra hyperparameters.

Method is effective across different hyperparameter settings.

Abstract

Direct training of Spiking Neural Networks (SNNs) on neuromorphic hardware has the potential to significantly reduce the energy consumption of artificial neural network training. SNNs trained with Spike Timing-Dependent Plasticity (STDP) benefit from gradient-free and unsupervised local learning, which can be easily implemented on ultra-low-power neuromorphic hardware. However, classification tasks cannot be performed solely with unsupervised STDP. In this paper, we propose Stabilized Supervised STDP (S2-STDP), a supervised STDP learning rule to train the classification layer of an SNN equipped with unsupervised STDP for feature extraction. S2-STDP integrates error-modulated weight updates that align neuron spikes with desired timestamps derived from the average firing time within the layer. Then, we introduce a training architecture called Paired Competing Neurons (PCN) to further enhance the learning capabilities of our classification layer trained with S2-STDP. PCN associates each class with paired neurons and encourages neuron specialization toward target or non-target samples through intra-class competition. We evaluate our methods on image recognition datasets, including MNIST, Fashion-MNIST, and CIFAR-10. Results show that our methods outperform state-of-the-art supervised STDP learning rules, for comparable architectures and numbers of neurons. Further analysis demonstrates that the use of PCN enhances the performance of S2-STDP, regardless of the hyperparameter set and without introducing any additional hyperparameters.