Follow

saddle points aren't real they can't hurt you

· · Web · 1 · 1 · 0

almost surely incorrect 

the entirety of 2016 was just boomer academics getting it out of their system that high dimensional problems were actually feasible when built from predominantly linear components trained by stochastic examples

almost surely incorrect 

i mean stochastically trained by examples
i put words in the wrong place sometimes ok

Sign in to participate in the conversation
Cybrespace

cybrespace: the social hub of the information superhighway jack in to the mastodon fediverse today and surf the dataflow through our cybrepunk, slightly glitchy web portal support us on patreon or liberapay!