Live data from Hacker News

MIT 6.S191: Recurrent Neural Networks, Transformers, and Attention [video]

youtube.com

1–10 of 63 posts

Re: MIT 6.S191: Recurrent Neural Networks, Transformers, and Attention [video]

#7

I wonder why that parameter is called "h"? Hmmm ... Why not just say the word "hysteresis" and bring some magnets to class for show-and-tell to help your students develop an intuition for the "h" parameter in RNNs.

hysteresis is also important to understand for working with radio networking.

Re: MIT 6.S191: Recurrent Neural Networks, Transformers, and Attention [video]

#9
post #5

[flagged]

Might as well be complete, and filter out websites based on MIT developed programming languages

https://en.wikipedia.org/wiki/Hacker_News (Note the programming language, and find what it's based on)

https://en.wikipedia.org/wiki/Lisp_(programming_language)

Re: MIT 6.S191: Recurrent Neural Networks, Transformers, and Attention [video]

#10
post #5

[flagged]

Might as well be complete, and filter out websites based on MIT developed programming languages https://en.wikipedia.org/wiki/Hacker_News (Note the programming language, and find what it's based on) https://en.wikipedia.org/wiki/Lisp_(programming_language)

[flagged]
Post reply on HN