Learning Spiking Neural Network from Easy to Hard task

TL;DR

This paper introduces a curriculum learning approach to Spiking Neural Networks, enabling them to learn from easy to hard data, which improves biological plausibility and performance on various datasets.

Contribution

It is the first to incorporate curriculum learning into SNNs, enhancing biological plausibility and adaptive learning by using a confidence-aware loss function.

Findings

Improved performance on static and neuromorphic datasets

Enhanced biological interpretability of SNNs

Effective handling of data difficulty levels

Abstract

Starting with small and simple concepts, and gradually introducing complex and difficult concepts is the natural process of human learning. Spiking Neural Networks (SNNs) aim to mimic the way humans process information, but current SNNs models treat all samples equally, which does not align with the principles of human learning and overlooks the biological plausibility of SNNs. To address this, we propose a CL-SNN model that introduces Curriculum Learning(CL) into SNNs, making SNNs learn more like humans and providing higher biological interpretability. CL is a training strategy that advocates presenting easier data to models before gradually introducing more challenging data, mimicking the human learning process. We use a confidence-aware loss to measure and process the samples with different difficulty levels. By learning the confidence of different samples, the model reduces the contribution of difficult samples to parameter optimization automatically. We conducted experiments on static image datasets MNIST, Fashion-MNIST, CIFAR10, and neuromorphic datasets N-MNIST, CIFAR10-DVS, DVS-Gesture. The results are promising. To our best knowledge, this is the first proposal to enhance the biologically plausibility of SNNs by introducing CL.