HN user

medains

9 karma

[ my public key: https://keybase.io/medains; my proof: https://keybase.io/medains/sigs/BFoixEab_McnMgy8PAH9FK2fgcdmN9xhxSqJtjlOEw0 ]

Posts1
Comments3
View on HN

Nothing in the article suggests that it's learning - so I suspect that the weights are indeed set in the factory.

Learning on the fly would consume much more power as it back-propagates, so doesn't really make much sense as the potential performance gain would be marginal and would probably cause a performance hit when switching to a different process or thread.