Lessons from a year of AI research
jetnew.notion.site
Lessons from a year of AI research
1–10 of 48 posts
Re: Lessons from a year of AI research
#2The one that matters is missing: how do you get the best random seeds? /s
Re: Lessons from a year of AI research
#3The one that matters is missing: how do you get the best random seeds? /s
41. Remember to consider variance of results and the usage of random seeds.
Re: Lessons from a year of AI research
#4The one that matters is missing: how do you get the best random seeds? /s
4
There you go.
Re: Lessons from a year of AI research
#5Find peace in doing trial and error statistical black box studies after x years of formal systems studies. I couldnt do that for my part.
Re: Lessons from a year of AI research
#6The one that matters is missing: how do you get the best random seeds? /s
Great one! Actual question: has anyone looked if pseudo randomnes is worse than full randomness?
Re: Lessons from a year of AI research
#7Re: Lessons from a year of AI research
#8The one that matters is missing: how do you get the best random seeds? /s
Great one! Actual question: has anyone looked if pseudo randomnes is worse than full randomness?
I once (8 years ago) did a comparison between random, pseudorandom and quasirandom. Quasirandom worked ever so slightly better than the other two in speed and final performance, but not enough to warrant the additional complexity of implementation.
Re: Lessons from a year of AI research
#9Re: Lessons from a year of AI research
#10The title here and on the blog differs, I don't know why submiters pick other titles. I mean I wouldn't quote a newspaper or paper with a wrong title, would I?