Threads by latest replies - Page 2524

(956 replies)

/sfg/ - Space Flight General

No.13675760 ViewReplyLast 50OriginalReport
Crickets Edition

Previous: >>13672207
951 posts and 188 images omitted
(25 replies)
No.13678882 ViewReplyOriginalReport
Calling all set theorists: what even is a set?
20 posts omitted
(7 replies)
No.13680648 ViewReplyOriginalReport
can you befriend numbers, /sci/? which number is your best friend? mine is 8 'cause she looks like infinity when she's asleep.
2 posts and 1 image omitted
(11 replies)
No.13674925 ViewReplyOriginalReport
>Be me
>Just finished a masters of Chemical engineering
>Get hired by biology laboratory
>Get trained to centrifuge
>Centrifuge takes 5 hours for some reason
>Take them out
>Invert 20 times
mfw
6 posts and 1 image omitted
(5 replies)
No.13680786 ViewReplyOriginalReport
Has anyone used the PGS for intelligence on impute.me

I got a score of 3.4 SD based on SNPs from Hill et al study on genes associated with intelligence.

I wanted to see if other people were also getting ridiculously high scores on the PGS from inpute.me
https://www.impute.me/intelligence/
(116 replies)
No.13671700 ViewReplyLast 50OriginalReport
/sci/ humor thread
111 posts and 22 images omitted
(85 replies)
No.13677880 ViewReplyLast 50OriginalReport
Why are there no female prodigies throughout history of the likes of Einstein, Neumann, Da Vinci, Hero of Alexandria, etc.?
80 posts and 11 images omitted
(21 replies)

What happens here?

No.13679664 ViewReplyOriginalReport
16 posts and 2 images omitted
(5 replies)
(5 replies)

Gradient Boosting

No.13679429 ViewReplyOriginalReport
Question about CatBoost.

You have a dataset and you split it into 80% training and 20% testing. You want to find optimal hyperparameters of the model, so with the training set, you do cross validation and search parameter space.

CatBoost has something called the eval set which is used to help avoid overfitting, but I'm confused. My question is how to sue it during the cross validation.

Say you do CV5. So now we have iterations of 80% of the training data to predict the other 20%.

Is it fair to in every iteration use the 20% as the eval set to avoid overfitting and then still predict on those features and report the result? Or have we cheated in a way by making the 20% of the training the eval set because we stopped the training early as a function of that set.

This same concept applies to the testing set. After finding optimal hyperparameters, can I use the testing set as the eval set during final model training? Or is this again cheating?

Thank you so much!