News for hackers. Stuff that matters.

A comment on The Limitations of Deep Learning. Parent comment

Re:The Limitations of Deep Learning by philipkglass on Monday July 17, 2017 @09:10PM (#14793651)
I was disagreeing with someone who wrote that we understand how neurons work and that perceptrons model them "quite well." They do not model biological neurons well at all. I agree that biological fidelity is not important for building useful ANNs.
[ Parent | on HN ]
Re:The Limitations of Deep Learning by robotresearcher on Monday July 17, 2017 @11:24PM (#14794072)
I presented (a vulgar summary of) McCulloch's hypothesis, not my own. And since I didn't use the words "quite well", you are not entitled to put them in quotes.
[ Parent | on HN ]
Re:The Limitations of Deep Learning by yorwba on Tuesday July 18, 2017 @01:25AM (#14794391)
philipkglass was referring to curiousgal's comment upthread: https://news.ycombinator.com/item?id=14790965
[ Parent | on HN ]
Re:The Limitations of Deep Learning by robotresearcher on Tuesday July 18, 2017 @01:37AM (#14794422)
OK, thanks. Too late to edit. Adjust flames accordingly. Of course a perceptron is not an accurate model of a biological neuron. But as a reduction to a minimal model it's still pretty darn interesting.
[ Parent | on HN ]