Stanford CS224N NLP with Deep Learning | 2023 | Lecture 9 - Pretraining

[@casual_dancer]

Really appreciated how he repeated every student's question before answering. It makes it a lot easier for the remote learners to follow.

[@Ran-sr5ir]

Agreed, and now I think Columbia university students will really enjoy his class as he becomes AP there.

[@vimukthirandika872]

Really nice how he articulates his thoughts in a short amount of time!

[@nanunsaram]

This lecture is great!

[@theneumann7]

So well explained

[@brainstormingsharing1309]

Keep it up!

[@shadow-sea]

awesome

[@420_gunna]

19:30 I don't really understand what he's saying about how jointly training the embedding and model parameters leads to better initialization of parameters -- can someone clue me in?

[@420_gunna]

1:01:08 Pretty sure this ODQA task that he mentions also allows you to reference documents -- in fact, you're supposed to. I think he's meant to be referring to "Closed-Book Question Answering"

[@2894031]

Wow you rarely (me: never) see a PhD student teach that well. The celebrated Karpathy doesn‘t come even close 😮

[@nynaevealmeera]

Agree whole-heartedly with this sentiment! Thank you to Stanford for making these lectures publicly available!

[@pratik92]

Karpathy is an engineer, not a teacher.

[@isalutfi]

💙💙💙

[@jimmysmith-i2m]

this guy is dancing in the classroom😄

[@yagneshm.bhadiyadra4359]

51:17 Even the best universities in the world have projector related issues 🙃

[@susdoge3767]

goldmine

[@annawilson3824]

1:02:48