Spike-based computation using classical recurrent neural networks

arXiv:2306.03623v3 Announce Type: replace-cross
Abstract: Spiking neural networks are a type of artificial neural networks in which communication between neurons is only made of events, also called spikes. This property allows neural networks to make asynchronous and sparse computations and therefore drastically decrease energy consumption when run on specialised hardware. However, training such networks is known to be difficult, mainly due to the non-differentiability of the spike activation, which prevents the use of classical backpropagation. This is because state-of-the-art spiking …

abstract artificial artificial neural networks arxiv asynchronous communication computation consumption cs.lg cs.ne energy events hardware however networks neural networks neurons property recurrent neural networks spiking neural networks training type