Open arvoelke opened 5 years ago
Using the trick in https://github.com/nengo/nengo-loihi/issues/230#issuecomment-501916092 here's a comparison of weights=True
versus weights=False
on a 6D Legendre Memory Unit (LMU):
weights=True
weights=False
With all-to-all weights we get a fairly stable history of the input. But with DecodeNeurons
things blow up systematically (I've found some variations that look better, but they are qualitatively similar). This is running on the actual hardware on the master branch. I was seeing the same thing in my thesis (which also included the improvements in #132).
As noted in https://github.com/nengo/nengo-loihi/pull/74#issuecomment-496270060 it would be useful to include some tests that compare the performance of
weights=True
versusweights=False
in order to detect any regression in the performance ofDecodeNeurons
relative to full-weights, and to serve as a basic benchmark for experimenting with variants and future improvements.This could be made part of a more general research task that involves determining which situations make more-or-less of a difference.