Re:Some thoughts on machine learning with small data
by dekhn on Friday June 03, 2022 @12:14PM
(#31610337)
can you share more about models of life and death stuff with less than 30 samples? (I work tangential to a regulated health industry)
Re:Some thoughts on machine learning with small data
by crabbygrabby on Friday June 03, 2022 @12:20PM
(#31610415)
I'd like to stay anonymous on the matter, but I've worked in various regulated industries. Now days I do none of this .
Re:Some thoughts on machine learning with small data
by dekhn on Friday June 03, 2022 @12:33PM
(#31610549)
Uh, OK. because if you were doing life and death stuff with 30 samples, people probably died due to false negatives or positives in your model, in a way that would have been better handled with more samples. Sorry to hear it- it's one of the reasons health care is so shitty.
Re:Some thoughts on machine learning with small data
by crabbygrabby on Friday June 03, 2022 @01:07PM
(#31610954)
Not healthcare and no one died. My models have been deployed for two years without incident.
Re:Some thoughts on machine learning with small data
by dekhn on Friday June 03, 2022 @01:51PM
(#31611535)
oh, sorry- you mean "life and death" as in you had a murderbot (https://www.youtube.com/watch?v=xuFbxeDjRZg_ was my team's contribution) that could kill people, and your model prevented it?
Are you sure you can conclude your system is safe?
Re:Some thoughts on machine learning with small data
by crabbygrabby on Friday June 03, 2022 @02:24PM
(#31611898)
Nope no murder bots...
The disadvantage of physical systems is the data is usually expensive. In my old field I know someone who had to make a decision on a data set of 5 samples and each sample costed more than a million USD.
I've made models of physical systems that involve kind of life or death stuff with less than 30 samples.
It's not for the faint of heart and if someone doesn't know what they are doing, the system they are modelling, or how to share their results correctly... Yikes!