Conversation

Notices

1. Embed this notice
   kuteboiCoder (kuteboicoder@subs4social.xyz)'s status on Wednesday, 20-Nov-2024 11:10:25 JST kuteboiCoder

   • iced depresso

   ATTN @icedquinn@blob.cat
   
   RE: https://social.marxist.network/users/yogthos/statuses/113511356586108687

   • Embed this notice
     iced depresso (icedquinn@blob.cat)'s status on Wednesday, 20-Nov-2024 11:10:24 JST iced depresso

     in reply to
     @KuteboiCoder i'll take a look, but yeah. especially some of the stuff like liquid state machines are being tested on like, 2,000 neuron "reservoirs," and are detecting features in video. or KAN networks that are more expensive to train (because they have a multi-point b-spline for activator functions) but require so many less that you still come out ahead.
     
     it also looks like deep learning is a meme. decoder/encoder networks seem to be fixed by genetics or some one-off initialization process, and only one or two layers at the back actually handle interpreting (and, maybe, communicate to themselves with loops--as is theorized with the phenological loop, esp. people talking to themselves to solve problems)
   • Embed this notice
     iced depresso (icedquinn@blob.cat)'s status on Wednesday, 20-Nov-2024 11:49:55 JST iced depresso

     in reply to
     @KuteboiCoder just reading papers. i have an rx6800 but i have been putting off fixing the linux install to use that for quite a while
   • Embed this notice
     kuteboiCoder (kuteboicoder@subs4social.xyz)'s status on Wednesday, 20-Nov-2024 11:49:56 JST kuteboiCoder

     in reply to

     • iced depresso

     @icedquinn@blob.cat
     
     what hardware are you using? Do you have a GPU sitting around or are you using hourly cloud?

   • Embed this notice
     iced depresso (icedquinn@blob.cat)'s status on Wednesday, 20-Nov-2024 11:51:25 JST iced depresso

     in reply to

     • iced depresso
     @KuteboiCoder some of the people in the spike net space are either not using gpus at all (just using a rack of cpu servers and evolution) or just one chunky GPU, because the networks are so small you can tinker with them on a just a 2,000$ desktop machine :blobcatgamer:
   • Embed this notice
     kuteboiCoder (kuteboicoder@subs4social.xyz)'s status on Wednesday, 20-Nov-2024 11:52:34 JST kuteboiCoder

     in reply to

     • iced depresso

     @icedquinn@blob.cat
     
     diint know that.

   • Embed this notice
     iced depresso (icedquinn@blob.cat)'s status on Wednesday, 20-Nov-2024 11:52:34 JST iced depresso

     in reply to
     @KuteboiCoder yeah i'm just wasting all my time trying to find social fulfillment instead of working :blobcatfrowningbig: