Re:Glial brain cells, long in neurons’ shadow, reveal hidden...
by nshm on Monday January 27, 2020 @01:58PM
(#22162551)
Brain doesn't do backpropagation
[ Parent
| on HN ]
Re:Glial brain cells, long in neurons’ shadow, reveal hidden...
by chrisb on Monday January 27, 2020 @02:05PM
(#22162626)
Interesting paper here on e-prop which is a biologically plausible alternative to backprop: https://www.biorxiv.org/content/10.1101/738385v3
Re:Glial brain cells, long in neurons’ shadow, reveal hidden...
by DailyHN on Monday January 27, 2020 @02:13PM
(#22162701)
> Brain doesn't do backpropagation
What makes you so sure?
Re:Glial brain cells, long in neurons’ shadow, reveal hidden...
by Sommer on Monday January 27, 2020 @02:27PM
(#22162828)
If it did I would have learned from my mistakes.
Re:Glial brain cells, long in neurons’ shadow, reveal hidden...
by short_sells_poo on Monday January 27, 2020 @02:38PM
(#22162934)
He could have overfit due to his training size being too small. Either he has to add some noise or increase his set.
Re:Glial brain cells, long in neurons’ shadow, reveal hidden...
by tudorw on Monday January 27, 2020 @03:19PM
(#22163368)
That's a gene thing, apparently :) https://www.telegraph.co.uk/news/science/science-news/331761...