How would one train an additional output neuron for 'confidence'? | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

singularity2001 on Dec 22, 2021 | parent | context | favorite | on: Gopher – A 280B parameter language model

How would one train an additional output neuron for 'confidence'?

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