all AI news
EXODUS: Stable and Efficient Training of Spiking Neural Networks. (arXiv:2205.10242v1 [cs.NE])
stat.ML updates on arXiv.org arxiv.org
Spiking Neural Networks (SNNs) are gaining significant traction in machine
learning tasks where energy-efficiency is of utmost importance. Training such
networks using the state-of-the-art back-propagation through time (BPTT) is,
however, very time-consuming. Previous work by Shrestha and Orchard [2018]
employs an efficient GPU-accelerated back-propagation algorithm called SLAYER,
which speeds up training considerably. SLAYER, however, does not take into
account the neuron reset mechanism while computing the gradients, which we
argue to be the source of numerical instability. To counteract this, …
arxiv exodus networks neural networks spiking neural networks training