PGMs were in fashion in 2012, but by 2014 when Deep Learning had become all the ... | Hacker News

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

		sampo on Jan 1, 2019 \| parent \| context \| favorite \| on: Ask HN: Engineers from non-CS background, how did ... PGMs were in fashion in 2012, but by 2014 when Deep Learning had become all the rage, I think PGMs almost disappeared from the picture. Do people even remember PGMs exist now in 2019?

KidComputer on Jan 1, 2019 | [–]

You'll find plate models, PGM junk, etc in modern papers on explicit density generative models and factorizing latents on such models.

srean on Jan 1, 2019 | | [–]

Fashion is relevant only if you want to approach it as a fashion industry.

vazamb on Jan 1, 2019 | [–]

PGMs also provide the intuition behind GANs and variational autoencoders.

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact