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.

翻译：采用受神经可塑性启发的无监督学习方法的脉冲神经网络（SNNs）有望成为人工智能的新框架。本研究探讨了多种神经可塑性类型，如脉冲时间依赖可塑性（STDP）和突触缩放，对由脉冲神经元构成的赢者通吃（WTA）网络学习的影响。我们使用Python实现了一个具备多种神经可塑性的WTA网络。采用MNIST和Fashion-MNIST数据集进行训练与测试。通过改变神经元数量、STDP时间常数以及突触缩放中使用的归一化方法，比较了分类准确率。结果表明，基于L2范数的突触缩放对提升分类性能最为有效。通过实施基于L2范数的突触缩放，并将兴奋层和抑制层的神经元数量均设为400，该网络在单轮训练后，在MNIST数据集上达到了88.84%的分类准确率，在Fashion-MNIST数据集上达到了68.01%的分类准确率。