The Bayesian Geometry of Transformer Attention | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		The Bayesian Geometry of Transformer Attention (arxiv.org)
		4 points by samwillis 22 days ago \| hide \| past \| favorite \| 1 comment

samwillis 22 days ago [–]

Higher level overview and links to the other related papers: https://medium.com/@vishalmisra/attention-is-bayesian-infere...

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