undefined | Better HN

0 pointsa-dub7y ago0 comments

I guess one upshot to the SVM approach is that there's math for quantifying how well a given model will generalize, subject to some assumptions.

Is there anything like that in the ANN world?

0 comments

In short, no. Not for practically large models used in common tasks like image classification or speech to text.

j / k navigate · click thread line to collapse

0 pointsa-dub7y ago0 comments

I guess one upshot to the SVM approach is that there's math for quantifying how well a given model will generalize, subject to some assumptions.

Is there anything like that in the ANN world?

In short, no. Not for practically large models used in common tasks like image classification or speech to text.

j / k navigate · click thread line to collapse