Conversation

Notices

1. Embed this notice
   maonu (maonu@mathstodon.xyz)'s status on Saturday, 18-Jan-2025 22:11:54 JST maonu

   backprop/machine learning fits into functional programming as "new form of control"/effect(?) with linear negation the dual from linear algebra

   basically "peek around locally on differentiable stuff and use that to improve the program"

   Turns out to resemble logic programming's "AI" maybe, cf. Pédrot/Kerjean's recent dialectica work

   https://hal.science/hal-02400927/document

   • julesh repeated this.
   • Embed this notice
     julesh (julesh@mathstodon.xyz)'s status on Saturday, 18-Jan-2025 22:13:13 JST julesh

     in reply to

     @maonu The link between 2010s AI and 1970s AI is a very nice coincidence

   • Embed this notice
     maonu (maonu@mathstodon.xyz)'s status on Saturday, 18-Jan-2025 22:53:25 JST maonu

     in reply to

     • julesh

     @julesh kinda crasy to see logic so central, I guess FP has been carrying the torch for "languages we can treat theoretically" but still cool!