> The current implementation adopts pseudo-spiking, where activations are approximated as spike-like signals at the tensor level, rather than true asynchronous event-driven spiking on neuromorphic hardware.
Well that seems pointless to me. Propagation of sparse events in the time domain is ~the entire point of spiking neurology.
2 comments
[ 1.00 ms ] story [ 17.1 ms ] threadWell that seems pointless to me. Propagation of sparse events in the time domain is ~the entire point of spiking neurology.
Why would the authors have chosen this route?