News for hackers. Stuff that matters.

A comment on A Brief Overview of Deep Learning.

Re:A Brief Overview of Deep Learning by m0g on Tuesday February 10, 2015 @09:54AM (#9027415)
Biological analogies are too often misleading and confusing when talking about deep learning[1]. We currently have very little knowledge of the way the brain works and most analogies are only wild assumptions. The ones contained in this article are blunt and based on strictly nothing but the author's feelings. Please read with care.

[1]: http://spectrum.ieee.org/robotics/artificial-intelligence/ma...

[ Parent | on HN ]
Re:A Brief Overview of Deep Learning by nl on Tuesday February 10, 2015 @10:19AM (#9027588)
The author's "feelings" are useful when they were one of the authors of AlexNet[1]. A 10% improvement on ImageNet[2] makes one think he might know a little about the subject.

[1] http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf

[2] http://www.image-net.org/challenges/LSVRC/2012/results.html (Look for SuperVision)

[ Parent | on HN ]
Re:A Brief Overview of Deep Learning by m0g on Tuesday February 10, 2015 @10:31AM (#9027681)
Well, I'm talking specifically about the biology analogies, and no, being good at ML doesn't mean you know anything about the brain.
[ Parent | on HN ]