Re:Building an AI to predict human age from a blood sample
by gmtx725 on Sunday March 08, 2020 @11:14PM
(#22522681)
why would you use a neural net on a dataset with only 700 samples, smh
[ Parent
| on HN ]
Re:Building an AI to predict human age from a blood sample
by wyxuan on Sunday March 08, 2020 @11:25PM
(#22522732)
The relationship in the dataset seems pretty clean and clear cut, so you don't really need as large a dataset.
Re:Building an AI to predict human age from a blood sample
by 0x1221 on Monday March 09, 2020 @03:43AM
(#22523672)
If it's clean and clear cut you probably don't need deep learning either.
Re:Building an AI to predict human age from a blood sample
by gmtx725 on Monday March 09, 2020 @04:57AM
(#22523967)
Then just use a GBM or some simple linear classifier
Re:Building an AI to predict human age from a blood sample
by ruborcalor on Monday March 09, 2020 @11:34AM
(#22526199)
yes valid point haha. It's more fun to use a neural net :) but after many similar comments I plan on implementing a simpler approach and seeing how it compares