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

Reinforcement Learning as a fine-tuning paradigm (ankeshanand.com) 22 points by ankeshanand on Jan 11, 2022 | past | 7 comments Contrastive Self-Supervised Learning (ankeshanand.com) 97 points by ankeshanand on Feb 1, 2020 | past | 13 comments Contrastive Self-Supervised Learning – Ankesh Anand (ankeshanand.com) 2 points by blopeur on Jan 30, 2020 | past

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