This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Non-linearity sharing in deep neural networks (a flaw?)

You probably do want to include library code for fast random projections based on random sign flipping and the Walsh Hadamard transform, even if it is just to allow people to experiment.

https://discourse.numenta.org/t/non-linearity-sharing-in-deep-neural-networks-a-flaw/6033