Efficient Training of Spiking Neural Networks with Temporally-Truncated Local Backpropagation through Time. (arXiv:2201.07210v1 [cs.NE])

Directly training spiking neural networks (SNNs) has remained challenging due
to complex neural dynamics and intrinsic non-differentiability in firing
functions. The well-known backpropagation through time (BPTT) algorithm
proposed to train SNNs suffers from large memory footprint and prohibits
backward and update unlocking, making it impossible to exploit the potential of
locally-supervised training methods. This work proposes an efficient and direct
training algorithm for SNNs that integrates a locally-supervised training
method with a temporally-truncated BPTT algorithm. The proposed algorithm
explores both …

arxiv networks neural networks time training