Elektrine lite

← Feed

@screwlisp@gamerplus.org

Post #1397807

2026-02-02 00:59 UTC

@aartaka@merveilles.town I had this feeling when I noticed I could just change +1 and -1 to foo and (complement foo) in a hopfield network, which is an implementation of (is dual to) 1 layer ffnn deep learning (it turned out; they didn't know this originally). Then, all the conventional wisdom about the disadvantages and advantages of deep learning seem to mostly have been artifacts of the string encoding being used. @neauoire@merveilles.town what should I read about your connexions (or dare I say, neurons!)?

Replies (1)

  • @screwlisp@gamerplus.org 2026-02-02 01:26

    By the way, could I ask if any of @dougmerritt@mathstodon.xyz @AmenZwa@mathstodon.xyz @kentpitman@climatejustice.social @rwxrwxrwx@mathstodon.xyz @ramin_hal9001@fe.disroot.org have any particular comments? I will also visit this topic on the Tuesday-evening-in-the-Americas lispy gopher climate. @aartaka@merveilles.town @neauoire@merveilles.town

    Open ##1397806