In this work, we explore a new Spiking Neural Network (SNN) formulation with Resonate-and-Fire (RAF) neurons (Izhikevich, 2001) trained with gradient descent via back-propagation. The RAF-SNN, while more biologically plausible, achieves performance comparable to or higher than conventional models in the Machine Learning literature across different network configurations, using similar or fewer parameters. Strikingly, the RAF-SNN proves robust against noise induced at testing/training time, under both static and dynamic conditions. Against CNN on MNIST, we show 25% higher absolute accuracy with N(0, 0.2) induced noise at testing time. Against LSTM on N-MNIST, we show 70% higher absolute accuracy with 20% induced noise at training time.
翻译:在这项工作中,我们探索了一种新的Spiking神经网络(SNN)配制,该配制配有经后推进后梯度下降训练的Resonate-and-Fire神经元(Izhikevich,2001年) 。 RAF-SNN虽然在生物学上更加合理,但在不同网络配置中,使用类似或较少的参数,其性能与机器学习文献中的常规模型相似或更高。 令人惊讶的是,RAF-SNNN证明,在静态和动态条件下,在测试/培训时,对在测试/培训时产生的噪音是强大的。 在N(0,0.2)测试时,我们显示绝对精度高25%,N(0,0.2)引出噪音。 在N-MNIST上,我们显示绝对精度高70%,在培训时,引力噪音为20%。