CVAug 4, 2023

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

arXiv:2308.02194v213 citationsh-index: 18
Originality Incremental advance
AI Analysis

This work addresses energy-efficient training on neuromorphic hardware for SNNs, offering a supervised learning approach that is incremental over existing STDP methods.

The paper tackles the problem of training Spiking Neural Networks (SNNs) for classification tasks using supervised STDP, proposing S2-STDP and Paired Competing Neurons (PCN) to enhance learning, and shows that these methods outperform state-of-the-art supervised STDP rules on datasets like MNIST, Fashion-MNIST, and CIFAR-10.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes