论文标题
时空学习的尖峰神经网络中有限的元动态神经元
Finite Meta-Dynamic Neurons in Spiking Neural Networks for Spatio-temporal Learning
论文作者
论文摘要
尖峰神经网络（SNN）纳入了更具生物学成分的结构和学习原理，因此在弥合人工和自然神经网络之间的鸿沟中起着至关重要的作用。尖峰是稀疏的信号，描述了基于阈值事件的触发和阈值不足的膜电位的动态计算，这为我们提供了在信息表示和计算上的替代统一和有效的方式。受到生物网络的启发，在该网络中，有限数量的元神经元共同整合了各种认知功能，我们提出并构建了元动态神经元（MDN），以改善SNNS在时空学习过程中以更好的网络概括。 MDN的设计具有基本的神经元动力学，其中包含膜电位的一阶和二阶动力学，包括某些超参数支持的空间和时间元元类型。首先是由空间（MNIST）和颞（TIDIGITS）数据集生成的MDN，然后扩展到其他各种不同的时空任务（包括时尚范围，NetTalk，NetTalk，Cifar-10，Timit和N-MNIST）。与其他SOTA SNN算法相比，达到了可比的精度，并且使用MDN的SNN与不使用MDN相比，SNN也获得了更好的概括。
Spiking Neural Networks (SNNs) have incorporated more biologically-plausible structures and learning principles, hence are playing critical roles in bridging the gap between artificial and natural neural networks. The spikes are the sparse signals describing the above-threshold event-based firing and under-threshold dynamic computation of membrane potentials, which give us an alternative uniformed and efficient way on both information representation and computation. Inspired from the biological network, where a finite number of meta neurons integrated together for various of cognitive functions, we proposed and constructed Meta-Dynamic Neurons (MDN) to improve SNNs for a better network generalization during spatio-temporal learning. The MDNs are designed with basic neuronal dynamics containing 1st-order and 2nd-order dynamics of membrane potentials, including the spatial and temporal meta types supported by some hyper-parameters. The MDNs generated from a spatial (MNIST) and a temporal (TIDigits) datasets first, and then extended to various other different spatio-temporal tasks (including Fashion-MNIST, NETtalk, Cifar-10, TIMIT and N-MNIST). The comparable accuracy was reached compared to other SOTA SNN algorithms, and a better generalization was also achieved by SNNs using MDNs than that without using MDNs.
