News for hackers. Stuff that matters.

A comment on The Limitations of Deep Learning. Parent comment

Re:The Limitations of Deep Learning by divideby0829 on Monday July 17, 2017 @11:14PM (#14794046)
yeah this was my main problem, I guess he is technically right because they are geometric but many of his analogies like the paper crumpling were deeply misleading as they would imply that the transformations are linear. The fact that they are not is fundamental to neural networks working.
[ Parent | on HN ]
Re:The Limitations of Deep Learning by tsbertalan on Tuesday July 18, 2017 @01:50PM (#14798603)
Paper-crumpling is nonlinear. Maybe your complaint is rather that paper-crumpling is "only" a topology-preserving diffeomorphism?
[ Parent | on HN ]