An optimised deep spiking neural network architecture without gradients. (arXiv:2109.12813v3 [cs.NE] UPDATED)

We present an end-to-end trainable modular event-driven neural architecture
that uses local synaptic and threshold adaptation rules to perform
transformations between arbitrary spatio-temporal spike patterns. The
architecture represents a highly abstracted model of existing Spiking Neural
Network (SNN) architectures. The proposed Optimized Deep Event-driven Spiking
neural network Architecture (ODESA) can simultaneously learn hierarchical
spatio-temporal features at multiple arbitrary time scales. ODESA performs
online learning without the use of error back-propagation or the calculation of
gradients. Through the use of simple …

architecture arxiv network network architecture neural network spiking neural network