通过引入突触缩放提升脉冲神经网络分类性能
Effects of Introducing Synaptic Scaling on Spiking Neural Network Learning
- 在竞争性网络中融合突触缩放与尖峰时序可塑性
- 基于L2范数的突触缩放使准确率最高，达88.84%和68.01%
- 适合关注生物启发学习机制的研究者
受神经可塑性启发的无监督学习脉冲神经网络（SNN）有望成为新一代人工智能框架。本研究探讨了多种神经可塑性机制（如尖峰时序依赖可塑性STDP和突触缩放）对由脉冲神经元构成的竞争-胜者为王（WTA）网络学习的影响。使用Python实现包含多种可塑性的WTA网络，并在MNIST和Fashion-MNIST数据集上进行训练与测试。通过调整神经元数量、STDP时间常数及突触缩放的归一化方法，比较分类准确率。结果表明，基于L2范数的突触缩放最有效。当兴奋层与抑制层神经元数均设为400时，经一轮训练后，网络在MNIST上的分类准确率达88.84%，在Fashion-MNIST上达68.01%。
原文摘要 · Abstract (English)
Spiking neural networks (SNNs) employing unsupervised learning methods inspired by neural plasticity are expected to be a new framework for artificial intelligence. In this study, we investigated the effect of multiple types of neural plasticity, such as spike-time-dependent plasticity (STDP) and synaptic scaling, on the learning in a winner-take-all (WTA) network composed of spiking neurons. We implemented a WTA network with multiple types of neural plasticity using Python. The MNIST and the Fashion-MNIST datasets were used for training and testing. We varied the number of neurons, the time constant of STDP, and the normalization method used in synaptic scaling to compare classification accuracy. The results demonstrated that synaptic scaling based on the L2 norm was the most effective in improving classification performance. By implementing L2-norm-based synaptic scaling and setting the number of neurons in both excitatory and inhibitory layers to 400, the network achieved classification accuracies of 88.84 % on the MNIST dataset and 68.01 % on the Fashion-MNIST dataset after one epoch of training.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。