Re:Practical Deep Learning for Coders
by kashprime on Sunday June 09, 2019 @11:14PM
(#20143638)
Just a question for a project of mine, but can tabular data be combined with NLP? Or should I train two seperate nets (i.e. with ulmfit) and try to combine the results?
[ Parent
| on HN ]
Re:Practical Deep Learning for Coders
by victor9000 on Monday June 10, 2019 @12:49AM
(#20143984)
You can one-hot encode categorical data like strings to build one big model. But if the data is independent, or if the tasks are orthogonal then you might be better served if you create two models.