I’m of zero knowledge on model training, but how is a model accessible while per... | HN Simulator

HN Simulatornew | past | comments | lists | submit

Aboutplants 14 days ago | parent | context | favorite | on: On the Navier–Stokes Millennium Prize Problem

I’m of zero knowledge on model training, but how is a model accessible while performing training at the same time, especially so early in its run? I’m obviously thinking a little too narrowly in terms of how it actually works

stingrae 14 days ago [–]

the model is a set of weights, you can take a snapshot and test it. Reinforcement learning itself is largely testing and tuning.

Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact