Self-Supervised Contrastive Learning In Spiking Neural Networks
Authors:
- 6 March 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Spiking neural networks (SNNs), inspired by the biological neural processing of the brain, are vastly growing due to their higher potential to handle spatiotemporal patterns with lower energy consumption, especially, if implemented on neuromorphic devices. In this study, we propose self-supervised contrastive learning (SSL) for SNNs to learn informative latent representations from a large set of unlabeled data. The proposed SSL pre-trained SNN is then fine-tuned on a small set of labeled samples of a downstream supervised task. To evaluate the proposed method, we trained convolutional SNNs using SSL on MNIST and CIFAR10 datasets with 80% of images as unlabeled samples, then fine-tuned the networks on the remaining 20% images. The proposed SSL-based SNNs could reach 94.23% and 62.24% recognition accuracies on testing sets of MNIST and CIFAR10, respectively.Keywords
This publication has 17 references indexed in Scilit:
- Contrastive self-supervised learning: review, progress, challenges and future research directionsInternational Journal of Multimedia Information Retrieval, 2022
- Spiking Neural Networks Trained via ProxyIEEE Access, 2022
- Directional Self-supervised Learning for Heavy Image Augmentations2022
- Contrastive Representation Learning: A Framework and ReviewIEEE Access, 2020
- A review of learning in biologically plausible spiking neural networksNeural Networks, 2020
- S4L: Self-Supervised Semi-Supervised Learning2019
- Deep learning in spiking neural networksNeural Networks, 2019
- A Review of the Integrate-and-fire Neuron Model: I. Homogeneous Synaptic InputBiological Cybernetics, 2006
- Auto- and Crosscorrelograms for the Spike Response of Leaky Integrate-and-Fire Neurons with Slow SynapsesPhysical Review Letters, 2006
- Is the integrate-and-fire model good enough?—a reviewNeural Networks, 2001