News for hackers. Stuff that matters.
Re:An Idiot’s guide to Support vector machines (2003) [pdf] by a-dub on Monday December 31, 2018 @12:22PM (#18795590)
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?

Re:An Idiot’s guide to Support vector machines (2003) [pdf] by computerex on Monday December 31, 2018 @12:49PM (#18795796)
In short, no. Not for practically large models used in common tasks like image classification or speech to text.