论文标题
用于尖峰神经网络的基于STDP的监督学习算法
An STDP-Based Supervised Learning Algorithm for Spiking Neural Networks
论文作者
论文摘要
与基于速率的人工神经网络相比，尖峰神经网络（SNN）为大脑提供了更生物学上的模型。但是他们如何执行监督学习仍然难以捉摸。受Bengio等人的最新作品的启发，我们提出了一种基于峰值的依赖性可塑性（STDP）的监督学习算法，该算法是针对由泄漏的集成和传火神经元组成的分层SNN的。一个时间窗口是为突触前神经元设计的，只有此窗口中的尖峰才能参与STDP更新过程。该模型在MNIST数据集上进行了训练。分类精度方法是多层感知器（MLP）的分类精度，该方法具有由标准的后传播算法训练的类似体系结构。
Compared with rate-based artificial neural networks, Spiking Neural Networks (SNN) provide a more biological plausible model for the brain. But how they perform supervised learning remains elusive. Inspired by recent works of Bengio et al., we propose a supervised learning algorithm based on Spike-Timing Dependent Plasticity (STDP) for a hierarchical SNN consisting of Leaky Integrate-and-fire (LIF) neurons. A time window is designed for the presynaptic neuron and only the spikes in this window take part in the STDP updating process. The model is trained on the MNIST dataset. The classification accuracy approach that of a Multilayer Perceptron (MLP) with similar architecture trained by the standard back-propagation algorithm.
