… the characteristics of spiking neurons. This paper analyzes problems in the
backpropagation-based … plausible learning methods to train SNNs with high performance and …

… (SNN) reduces energy consumption with spike-driven computing. This paper proposes a
graph-based spatio-temporal backpropagation (G-STBP) to train SNN, aiming to enhance spike …

… Then, according to the recomputed sl and the backpropagated Vxl+1, we get the gradients
of Conv parameters in layer l + 1. Also, we get the spatial part of Vsl in Eq. (5), as in Fig. …

… neuron model, which can make use of the spatio-temporal … algorithm that uses spatio-temporal
back propagation by defining a loss … and has a high performance in spatio-temporal fields. …

… We propose a spiking neural network model that encodes information in the relative timing of
… , “Spatio-temporal backpropagation for training high-performance spiking neural networks,” …

… spiking neural network model trained with an algorithm based on spike latency and temporal
difference backpropagation… model can achieve high performance for spatiotemporal pattern …

… spiking neural networks. We further show that HRSNN can achieve similar performance to
state-of-the-art backpropagation trained … high-performance HRSNN for classifying complex …

… Neurons in artificial neural networks (ANNs) are characterized by a single, static, and …
spiking neural networks (SNNs) compute based upon discrete spike events and spatio-temporal …

… , we can obtain highperformance SNNs with superior training … Online spatio-temporal
learning in deep neural networks. … High-performance large-scale image recognition without …

… -training algorithm, Spatio-Temporal BackPropagation (STBP), to improve not only the accuracy
but also the spike … high-performance spiking neural networks,” Frontiers in neuroscience, …