News for hackers. Stuff that matters.

A comment on MIT 6.S191: Recurrent Neural Networks, Transformers, and Attention. Parent comment

Re:MIT 6.S191: Recurrent Neural Networks, Transformers, and ... by seer on Saturday April 01, 2023 @10:37PM (#35406578)
I’ve been watching https://karpathy.ai/zero-to-hero.html and they seem amazing so far, literally go to gpt from basic math and programming - he first codes the libs from scratch to show you how the internals work, and only then uses an off the shelf production lib.
[ Parent | on HN ]
Re:MIT 6.S191: Recurrent Neural Networks, Transformers, and ... by quickthrower2 on Saturday April 01, 2023 @10:41PM (#35406600)
Yes this is a great course, on every level. I recommend to do the exercises after each lecture to cement the concepts too. The exercises are good too. Stretching but achievable.
[ Parent | on HN ]
Re:MIT 6.S191: Recurrent Neural Networks, Transformers, and ... by j1br on Saturday April 01, 2023 @11:00PM (#35406718)
what do you mean by exercises are there any specific exercises or the ones who is solving while he's explaining the material?
[ Parent | on HN ]
Re:MIT 6.S191: Recurrent Neural Networks, Transformers, and ... by quickthrower2 on Sunday April 02, 2023 @01:17AM (#35407419)
under the first video there is a link to a google colab document with exercises - different but similar to what is in the video.
[ Parent | on HN ]
Re:MIT 6.S191: Recurrent Neural Networks, Transformers, and ... by nightski on Saturday April 01, 2023 @11:35PM (#35406919)
It's a great resource, but very focused on language models. I'd say if you are looking for a general overview of deep learning that fastai is fantastic.
[ Parent | on HN ]